[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-agent-advisor":3,"mdc--i5vrq4-key":37,"related-repo-aws-labs-agent-advisor":2106,"related-org-aws-labs-agent-advisor":2206},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":35,"mdContent":36},"agent-advisor","plan and build AWS AI agents","Unified entry point for AI-agent work on AWS: evaluate and pick a runtime, generate a full migration plan (for existing workloads), and build an executable POC — all in one flow. Triggers on: which runtime for my agent, AgentCore vs ECS vs EKS vs Lambda, AgentCore vs Lambda MicroVMs, deploy an AI agent on AWS, agent architecture on AWS, I have an agent idea what do I build, move my agents to AWS, migrate my agents to AWS with a plan, agent migration plan, add AgentCore services, add memory\u002Fgateway\u002Fidentity\u002Fpolicy to my agent, enable AgentCore Memory, add observability to my agent, I'm already on AWS and want to add agent capabilities, migrate Temporal workers to AWS, Temporal to AWS, run Temporal on AWS, Temporal workers on AWS, we use Temporal and want to move to AWS, our service is orchestrated by Temporal, what do I build on AWS for my Temporal workers, move a Temporal-based service to AWS, Temporal Cloud or self-hosted on AWS. Runs a phased flow: Intake (entry point + technical background), Discover (lightweight code detection), Clarify (adaptive questions), deterministic scoring, Design (runtime + deployment model + services + model), Estimate (coarse cost), Generate (layered recommendation doc + scaffolding), then optional gated stages: Migration Plan (full plan generated in-skill by reusing this plugin's gcp-to-aws engine, with the advisor's decisions carried over) and POC (deployment plan + deployable proof-of-concept on the recommended runtime — AgentCore, ECS, EKS, or Lambda; generated deliverables by default, or assisted build in your account on explicit opt-in). Systems with several workloads (interacting or independent agents, batch jobs, services) are decomposed into workload units, each getting its own verdict with a consolidation option. An add-capabilities branch (for teams already running agents on AWS) recommends which AgentCore services to enable on any runtime — no runtime scoring. Temporal systems dissolve into the same unit flow — worker polling tiers and Activity execution classes become units (rules in the Temporal decision reference); Workflow orchestration code is never rewritten — never a Step Functions translation. Requires at least one agentic component: a purely non-agent system (only plain services \u002F batch jobs \u002F HTTP endpoints, or a Temporal worker whose Activities are all non-agent) is out of scope — Clarify halts it (scope gate) and points to gcp-to-aws \u002F heroku-to-aws \u002F llm-to-bedrock. Not for: pure compute\u002Fdata migration with no AI agent; pure LLM SDK rewrite without agent architecture (use llm-to-bedrock); or detailed per-model pricing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"aws-labs","AWS Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws-labs.png","awslabs",[13,17,20,23],{"name":14,"slug":15,"type":16},"Agents","agents","tag",{"name":18,"slug":19,"type":16},"Engineering","engineering",{"name":21,"slug":22,"type":16},"AI Infrastructure","ai-infrastructure",{"name":24,"slug":25,"type":16},"AWS","aws",14,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fstartups","2026-08-14T04:51:57.95352",null,15,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":34},[],"Official AWS Startups repository that hosts plugins, skills, tools and resources to support startup builders on AWS","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fstartups\u002Ftree\u002FHEAD\u002Fadvisor\u002Fplugins\u002Faws-startup-advisor\u002Fskills\u002Fagent-advisor","---\nname: agent-advisor\ndescription: \"Unified entry point for AI-agent work on AWS: evaluate and pick a runtime, generate a full migration plan (for existing workloads), and build an executable POC — all in one flow. Triggers on: which runtime for my agent, AgentCore vs ECS vs EKS vs Lambda, AgentCore vs Lambda MicroVMs, deploy an AI agent on AWS, agent architecture on AWS, I have an agent idea what do I build, move my agents to AWS, migrate my agents to AWS with a plan, agent migration plan, add AgentCore services, add memory\u002Fgateway\u002Fidentity\u002Fpolicy to my agent, enable AgentCore Memory, add observability to my agent, I'm already on AWS and want to add agent capabilities, migrate Temporal workers to AWS, Temporal to AWS, run Temporal on AWS, Temporal workers on AWS, we use Temporal and want to move to AWS, our service is orchestrated by Temporal, what do I build on AWS for my Temporal workers, move a Temporal-based service to AWS, Temporal Cloud or self-hosted on AWS. Runs a phased flow: Intake (entry point + technical background), Discover (lightweight code detection), Clarify (adaptive questions), deterministic scoring, Design (runtime + deployment model + services + model), Estimate (coarse cost), Generate (layered recommendation doc + scaffolding), then optional gated stages: Migration Plan (full plan generated in-skill by reusing this plugin's gcp-to-aws engine, with the advisor's decisions carried over) and POC (deployment plan + deployable proof-of-concept on the recommended runtime — AgentCore, ECS, EKS, or Lambda; generated deliverables by default, or assisted build in your account on explicit opt-in). Systems with several workloads (interacting or independent agents, batch jobs, services) are decomposed into workload units, each getting its own verdict with a consolidation option. An add-capabilities branch (for teams already running agents on AWS) recommends which AgentCore services to enable on any runtime — no runtime scoring. Temporal systems dissolve into the same unit flow — worker polling tiers and Activity execution classes become units (rules in the Temporal decision reference); Workflow orchestration code is never rewritten — never a Step Functions translation. Requires at least one agentic component: a purely non-agent system (only plain services \u002F batch jobs \u002F HTTP endpoints, or a Temporal worker whose Activities are all non-agent) is out of scope — Clarify halts it (scope gate) and points to gcp-to-aws \u002F heroku-to-aws \u002F llm-to-bedrock. Not for: pure compute\u002Fdata migration with no AI agent; pure LLM SDK rewrite without agent architecture (use llm-to-bedrock); or detailed per-model pricing.\"\n---\n\n# AWS Agent Advisor\n\nHelps startups decide how and where to run AI agents on AWS. Deterministic scoring\nrecommends a runtime; the conversation adapts to the user's technical background.\n\n## Definitions\n\n- **\"Load\"** = Read the file with the Read tool and follow it. Do not summarize or skip.\n- **`$RUN_DIR`** = the run directory under `.agent-advisor\u002F` (e.g. `.agent-advisor\u002F0630-1430\u002F`),\n  created in Intake.\n- **`$PLUGIN`** = `${CLAUDE_PLUGIN_ROOT}` (the installed plugin root). On Claude Code this token\n  substitutes inline. **If `${CLAUDE_PLUGIN_ROOT}` does not resolve** (some Cursor\u002FCodex builds,\n  or a literal `${CLAUDE_PLUGIN_ROOT}` string showing up in a path error), fall back to the\n  skill's own directory: this SKILL.md lives at `\u003Cplugin>\u002Fskills\u002Fagent-advisor\u002FSKILL.md`, so the\n  engine and its data are all inside this skill — scripts at `.\u002Fscripts\u002F...`, runtime profiles at\n  `.\u002Freferences\u002Fruntimes\u002F...`, and decision refs at `.\u002Freferences\u002Fdecision-refs\u002F...` relative to\n  it. Prefer `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fagent-advisor\u002F...`; use the relative fallback only when\n  it fails to resolve.\n\n## Prerequisites\n\n- `uv` available (for scoring). Check: `uv --version`. If missing, tell the user to install\n  it from the official install guide (https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002F — e.g. `brew install uv` or `pipx install uv`) and stop.\n\n## Phase Structure (frontmatter)\n\nPhase, fragment, and assembler files carry a YAML frontmatter block that declares how each\nphase is composed — its inputs, triggers, fragments, assembler, artifacts, gates, and\nordering. The execution contract is the vendored `references\u002Fvendored\u002Fdsl\u002FINTERPRETER.md`:\nit defines every frontmatter key, the fragment\u002Fassembler model, the gate protocol\n(`HANDOFF_OK` \u002F `GATE_FAIL`), and the interpreter loop. **Load it first** (once, at the\nstart of a run), then execute each phase file's prose body. Elsewhere in this skill,\n`INTERPRETER.md` (without a path) refers to this loaded contract.\n\n## Execution\n\nThis skill is driven by the interpreter loop in `INTERPRETER.md` (§ The interpreter loop):\nit reads `.phase-status.json`, determines the current phase, runs each phase's\n`_preconditions` \u002F fragments \u002F `_assemble` \u002F `_postconditions`, advances on `HANDOFF_OK`\nvia `_advances_to`, and validates state. The backbone (intake → discover → clarify →\nconfirm → design → estimate → generate → migration-plan → poc → complete) and the\none sidebar branch (add-capabilities) are derived\nfrom the phase files' frontmatter — they are not restated here.\n\n**Cold start (entry phase).** With no run under `.agent-advisor\u002F` carrying a\n`.phase-status.json`, begin at `references\u002Fphases\u002Fintake\u002Fintake.md` — this skill's entry\nphase (the one carrying `_init: true`). On a warm start, `current_phase` in\n`.phase-status.json` is authoritative (`INTERPRETER.md` § The interpreter loop).\n\n**Skill bindings (`INTERPRETER.md` § Skill bindings).** This skill declares:\n\n- **Run root**: `.agent-advisor\u002F` — `$RUN_DIR` is this skill's name for the run directory\n  (`.agent-advisor\u002F[MMDD-HHMM]\u002F`). Intake's own prose performs the `_init` bootstrap.\n- **State shape**: § State file below (advisor-specific keys such as `entry_point`,\n  `audience`, `recommendation_reviewed`, `migration_plan_ctx`, `migration_plan_unavailable`);\n  the shared state schema is not vendored.\n- **Run seed (optional)**: `$RUN_DIR\u002Fseed.json`, else `.agent-advisor\u002Fseed.json` at the run root\n  (schema `scripts\u002Fschemas\u002Fseed.json`) supplies\n  machine-readable answers for a non-interactive run — the Clarify dimensions, the two gate\n  answers, the POC mode, the live-probe answer, and a `co_recommend` tie-break. It is the\n  HIGHEST-precedence source for every value it carries (clarify.md Step 2.5), which is what makes\n  a repeated run's score comparable: the deterministic engine gets byte-identical input. A gate\n  the seed omits is declined; a dimension the seed omits falls through to detection, then prose,\n  then an `assumed` value that MUST be recorded in `$RUN_DIR\u002FUNANSWERED.md`. With no seed, the\n  interactive flow is unchanged.\n- **Resolved statuses**: `skipped` (routing resolved the phase without running it), plus\n  `not_applicable` for `migration_plan` only.\n- **Conditional backbone routing**: the entry-point routing below. When a routing rule\n  marks a phase not-applicable, set it `skipped` and advance through its `_advances_to` in\n  the same state write.\n\n## Routing & gates (orchestration)\n\nSidebar placement and conditional backbone routing are orchestration prose owned by\nthis file (`INTERPRETER.md` § Skill bindings, § Backbone vs sidebar).\n\n**Entry-point routing:**\n\n- `build_scratch` → skip Discover; Clarify → Confirm → Design → Estimate → Generate → **Gate 2 → POC (any winning runtime)**. No migration plan (nothing existing to migrate).\n- `build_deploy` → Discover (if code) → Clarify → Confirm → Design → Estimate → Generate → **Gate 1 → Migration Plan (if existing non-AWS AI workload detected and user confirms)** → **Gate 2 → POC (any winning runtime)**.\n- `migrate` → Discover (if code) → Clarify → Confirm → Design → Estimate (target-state run cost; migration TCO comparison stays with the Migration Plan engine) → Generate → **Gate 1 → Migration Plan (in-skill, reusing the sibling `gcp-to-aws` skill)** → **Gate 2 → POC (any winning runtime, when the plan was produced)**. Declining Gate 1 keeps the classic handoff: pointer to `\u002Faws-startup-advisor:llm-to-bedrock` with `handoff-summary.md`.\n- `add_capabilities` → load `references\u002Fphases\u002Fadd-capabilities\u002Fadd-capabilities.md` and follow it (no runtime\n  scoring; writes `capabilities-recommendation.md`). This is a self-contained branch — it does\n  NOT pass through Clarify \u002F Confirm \u002F Design \u002F Estimate \u002F Generate, so the phase gate\n  below never applies to it.\n- Temporal detection routes into `migrate` with temporal units pre-seeded (see discover).\n\n**Gate semantics (backbone tail):**\n\n- **Gate 1 → `migration_plan`** runs only when `generate` is done AND\n  `recommendation_reviewed == true` (generate.md Step 5.5) AND entry point ∈ {migrate,\n  build_deploy} AND the run is migration-eligible (generate.md Step 6) AND the user\n  confirmed Gate 1. Otherwise resolve it: `not_applicable` (build_scratch \u002F no migratable\n  workload) or `skipped` (declined) — and advance.\n- **Gate 2 → `poc`** runs only when `phases.poc == \"in_progress\"` (set when the user\n  answers Gate 2 \"yes\" — asked in generate.md Step 7 or migration-plan.md Step 6) AND\n  `recommendation_reviewed == true`. Any winning runtime (agentcore \u002F ecs \u002F eks \u002F lambda \u002F\n  lambda_microvms) — the POC shape follows the verdict (poc.md Step 3 dispatch on\n  `references\u002Fdecision-refs\u002Fpoc-shapes.md`). Gate 2 is only offered when `migration_plan`\n  ∈ {completed, skipped, not_applicable} — or `in_progress` on build_deploy only (Stage 2\n  failed\u002Faborted; fallback POC from design.json per migration-plan.md failure handling);\n  for entry point `migrate`, only when `migration_plan == \"completed\"` (the POC implements the\n  plan) OR when the stage resolved `not_applicable` with `migration_plan_unavailable ==\n  \"engine_absent\"` — a standalone deployment that does not bundle the migration engine, where\n  Gate 2 is offered by migration-plan.md Step -1 and the POC is design-backed. A migrate-POC\n  with no plan for any OTHER reason (the user declined) has nothing to implement.\n- Persisting Gate 2 as `phases.poc = \"in_progress\"` BEFORE poc.md loads makes the\n  confirmation resumable: if the session breaks between the \"yes\" and the load, the\n  interpreter re-enters `poc` without re-asking. (A declared deviation from\n  `INTERPRETER.md` § The interpreter loop step 5's gate-then-`in_progress` ordering — the\n  user's confirmation is the entry event worth persisting.)\n\n**Phase gate:** Do NOT load design.md \u002F estimate.md \u002F generate.md unless\n`$RUN_DIR\u002F.phase-status.json` exists and BOTH `phases.clarify == \"completed\"` AND\n`phases.confirm == \"completed\"`. Confirm confirms the deployment model, the service\nset, and (for a co_recommend tie) the user's `chosen_runtime` — Design and the diagram depend on\nits `confirm.json` output, so it must not be skipped. If the user asks to skip Clarify or Pass 2,\nrefuse briefly and run it.\n\n## State file (`.phase-status.json`)\n\n```json\n{\n  \"run_id\": \"0630-1430\",\n  \"entry_point\": \"build_scratch\",\n  \"audience\": \"technical\",\n  \"current_phase\": \"clarify\",\n  \"phases\": {\n    \"intake\": \"completed\",\n    \"discover\": \"skipped\",\n    \"clarify\": \"in_progress\",\n    \"confirm\": \"pending\",\n    \"design\": \"pending\",\n    \"estimate\": \"pending\",\n    \"generate\": \"pending\",\n    \"migration_plan\": \"pending\",\n    \"poc\": \"pending\"\n  }\n}\n```\n\nStatus values: `pending` → `in_progress` → `completed`, plus `skipped`. Use read-merge-write:\nread before each update, change only the advancing keys, keep prior phases.\n\n`recommendation_reviewed` (top level, boolean) is set to `true` by generate.md Step 5.5 when\nthe user explicitly confirms they have seen the recommendation. Gate 1, Gate 2, and the\n`migration_plan` \u002F `poc` states all require it — no gate may be asked while it is absent.\n\n`migration_plan` additionally uses `not_applicable` (build_scratch, or no migratable workload\ndetected). When Stage 2 runs, `migration_plan_ctx` is added at the top level:\n`{\"repo\": \"\u003Cabs path to target repo>\", \"migration_dir\": \"\u003Cabs path to .migration\u002F\u003Cid>\u002F>\"}` —\nStage 3 reads gcp-to-aws artifacts ONLY via this recorded path, never by re-globbing.\n\n## Files\n\n| File                                                 | Purpose                                                                                                        |\n| ---------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- |\n| `references\u002Fvendored\u002Fdsl\u002FINTERPRETER.md`             | Vendored DSL execution contract (interpreter loop + gate protocol)                                             |\n| `references\u002Fphases\u002Fintake\u002Fintake.md`                 | Entry point + technical background + open context                                                              |\n| `references\u002Fphases\u002Fdiscover\u002Fdiscover.md`             | Lightweight code detection                                                                                     |\n| `references\u002Fphases\u002Fclarify\u002Fclarify.md`               | Clarify orchestrator + answer mapping to scoring keys                                                          |\n| `references\u002Fphases\u002Fclarify\u002Fclarify-technical.md`     | Technical-background question wording                                                                          |\n| `references\u002Fphases\u002Fclarify\u002Fclarify-business.md`      | Business-background question wording                                                                           |\n| `references\u002Fphases\u002Fconfirm\u002Fconfirm.md`               | Winner-specific follow-ups                                                                                     |\n| `references\u002Fphases\u002Fdesign\u002Fdesign.md`                 | Assemble recommendation; Migrate handoff branch                                                                |\n| `references\u002Fphases\u002Festimate\u002Festimate.md`             | Coarse cost magnitude                                                                                          |\n| `references\u002Fphases\u002Fgenerate\u002Fgenerate.md`             | Layered recommendation doc + scaffolding                                                                       |\n| `references\u002Fphases\u002Fmigration-plan\u002Fmigration-plan.md` | Stage 2: full migration plan via the sibling gcp-to-aws engine                                                 |\n| `references\u002Fdecision-refs\u002Ftemporal.md`               | Temporal rules: Tier 1\u002F2 tables, adapter, runbooks, commercials (consumed by discover\u002Fclarify\u002Fdesign\u002Fgenerate) |\n| `references\u002Fdecision-refs\u002Fpoc-shapes.md`             | Per-runtime POC deploy shapes (ECS\u002FEKS\u002FLambda\u002FMicroVMs\u002FTemporal)                                               |\n| `references\u002Fdecision-refs\u002F*.md`                      | Runtime service cards, model defaults, freshness                                                               |\n| `references\u002Fdecision-refs\u002Fworkload-classes.md`       | Deterministic verdicts for non-agent workload units (batch\u002Fservice\u002Fio)                                         |\n| `references\u002Fruntimes\u002F*.json`                         | Runtime registry (read by scoring.py)                                                                          |\n| `scripts\u002Fscoring.py`                                 | Deterministic scoring engine                                                                                   |\n| `scripts\u002Ftest_temporal_decision_refs.py`             | Content lock for the Temporal decision reference                                                               |\n| `scripts\u002Ftest_poc_shapes.py`                         | Content lock for the POC deploy shapes                                                                         |\n| `scripts\u002Ftest_workload_classes.py`                   | Content lock for workload-classes.md (verdicts table)                                                          |\n| `scripts\u002Ftest_unit_grouping.py`                      | Unit grouping + pattern matching (workload-class assignment)                                                   |\n| `scripts\u002Ftest_collapse_invariant.py`                 | Collapse-invariant ordering enforcement (A→B implies [B] ⊆ [A] outputs)                                        |\n",{"data":38,"body":39},{"name":4,"description":6},{"type":40,"children":41},"root",[42,51,57,64,194,200,248,254,298,304,362,424,441,646,652,664,672,803,811,975,1025,1038,1587,1618,1649,1681,1687,2100],{"type":43,"tag":44,"props":45,"children":47},"element","h1",{"id":46},"aws-agent-advisor",[48],{"type":49,"value":50},"text","AWS Agent Advisor",{"type":43,"tag":52,"props":53,"children":54},"p",{},[55],{"type":49,"value":56},"Helps startups decide how and where to run AI agents on AWS. Deterministic scoring\nrecommends a runtime; the conversation adapts to the user's technical background.",{"type":43,"tag":58,"props":59,"children":61},"h2",{"id":60},"definitions",[62],{"type":49,"value":63},"Definitions",{"type":43,"tag":65,"props":66,"children":67},"ul",{},[68,80,111],{"type":43,"tag":69,"props":70,"children":71},"li",{},[72,78],{"type":43,"tag":73,"props":74,"children":75},"strong",{},[76],{"type":49,"value":77},"\"Load\"",{"type":49,"value":79}," = Read the file with the Read tool and follow it. Do not summarize or skip.",{"type":43,"tag":69,"props":81,"children":82},{},[83,93,95,101,103,109],{"type":43,"tag":73,"props":84,"children":85},{},[86],{"type":43,"tag":87,"props":88,"children":90},"code",{"className":89},[],[91],{"type":49,"value":92},"$RUN_DIR",{"type":49,"value":94}," = the run directory under ",{"type":43,"tag":87,"props":96,"children":98},{"className":97},[],[99],{"type":49,"value":100},".agent-advisor\u002F",{"type":49,"value":102}," (e.g. ",{"type":43,"tag":87,"props":104,"children":106},{"className":105},[],[107],{"type":49,"value":108},".agent-advisor\u002F0630-1430\u002F",{"type":49,"value":110},"),\ncreated in Intake.",{"type":43,"tag":69,"props":112,"children":113},{},[114,123,125,131,133,145,147,152,154,160,162,168,170,176,178,184,186,192],{"type":43,"tag":73,"props":115,"children":116},{},[117],{"type":43,"tag":87,"props":118,"children":120},{"className":119},[],[121],{"type":49,"value":122},"$PLUGIN",{"type":49,"value":124}," = ",{"type":43,"tag":87,"props":126,"children":128},{"className":127},[],[129],{"type":49,"value":130},"${CLAUDE_PLUGIN_ROOT}",{"type":49,"value":132}," (the installed plugin root). On Claude Code this token\nsubstitutes inline. ",{"type":43,"tag":73,"props":134,"children":135},{},[136,138,143],{"type":49,"value":137},"If ",{"type":43,"tag":87,"props":139,"children":141},{"className":140},[],[142],{"type":49,"value":130},{"type":49,"value":144}," does not resolve",{"type":49,"value":146}," (some Cursor\u002FCodex builds,\nor a literal ",{"type":43,"tag":87,"props":148,"children":150},{"className":149},[],[151],{"type":49,"value":130},{"type":49,"value":153}," string showing up in a path error), fall back to the\nskill's own directory: this SKILL.md lives at ",{"type":43,"tag":87,"props":155,"children":157},{"className":156},[],[158],{"type":49,"value":159},"\u003Cplugin>\u002Fskills\u002Fagent-advisor\u002FSKILL.md",{"type":49,"value":161},", so the\nengine and its data are all inside this skill — scripts at ",{"type":43,"tag":87,"props":163,"children":165},{"className":164},[],[166],{"type":49,"value":167},".\u002Fscripts\u002F...",{"type":49,"value":169},", runtime profiles at\n",{"type":43,"tag":87,"props":171,"children":173},{"className":172},[],[174],{"type":49,"value":175},".\u002Freferences\u002Fruntimes\u002F...",{"type":49,"value":177},", and decision refs at ",{"type":43,"tag":87,"props":179,"children":181},{"className":180},[],[182],{"type":49,"value":183},".\u002Freferences\u002Fdecision-refs\u002F...",{"type":49,"value":185}," relative to\nit. Prefer ",{"type":43,"tag":87,"props":187,"children":189},{"className":188},[],[190],{"type":49,"value":191},"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fagent-advisor\u002F...",{"type":49,"value":193},"; use the relative fallback only when\nit fails to resolve.",{"type":43,"tag":58,"props":195,"children":197},{"id":196},"prerequisites",[198],{"type":49,"value":199},"Prerequisites",{"type":43,"tag":65,"props":201,"children":202},{},[203],{"type":43,"tag":69,"props":204,"children":205},{},[206,212,214,220,222,230,232,238,240,246],{"type":43,"tag":87,"props":207,"children":209},{"className":208},[],[210],{"type":49,"value":211},"uv",{"type":49,"value":213}," available (for scoring). Check: ",{"type":43,"tag":87,"props":215,"children":217},{"className":216},[],[218],{"type":49,"value":219},"uv --version",{"type":49,"value":221},". If missing, tell the user to install\nit from the official install guide (",{"type":43,"tag":223,"props":224,"children":228},"a",{"href":225,"rel":226},"https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002F",[227],"nofollow",[229],{"type":49,"value":225},{"type":49,"value":231}," — e.g. ",{"type":43,"tag":87,"props":233,"children":235},{"className":234},[],[236],{"type":49,"value":237},"brew install uv",{"type":49,"value":239}," or ",{"type":43,"tag":87,"props":241,"children":243},{"className":242},[],[244],{"type":49,"value":245},"pipx install uv",{"type":49,"value":247},") and stop.",{"type":43,"tag":58,"props":249,"children":251},{"id":250},"phase-structure-frontmatter",[252],{"type":49,"value":253},"Phase Structure (frontmatter)",{"type":43,"tag":52,"props":255,"children":256},{},[257,259,265,267,273,275,281,283,288,290,296],{"type":49,"value":258},"Phase, fragment, and assembler files carry a YAML frontmatter block that declares how each\nphase is composed — its inputs, triggers, fragments, assembler, artifacts, gates, and\nordering. The execution contract is the vendored ",{"type":43,"tag":87,"props":260,"children":262},{"className":261},[],[263],{"type":49,"value":264},"references\u002Fvendored\u002Fdsl\u002FINTERPRETER.md",{"type":49,"value":266},":\nit defines every frontmatter key, the fragment\u002Fassembler model, the gate protocol\n(",{"type":43,"tag":87,"props":268,"children":270},{"className":269},[],[271],{"type":49,"value":272},"HANDOFF_OK",{"type":49,"value":274}," \u002F ",{"type":43,"tag":87,"props":276,"children":278},{"className":277},[],[279],{"type":49,"value":280},"GATE_FAIL",{"type":49,"value":282},"), and the interpreter loop. ",{"type":43,"tag":73,"props":284,"children":285},{},[286],{"type":49,"value":287},"Load it first",{"type":49,"value":289}," (once, at the\nstart of a run), then execute each phase file's prose body. Elsewhere in this skill,\n",{"type":43,"tag":87,"props":291,"children":293},{"className":292},[],[294],{"type":49,"value":295},"INTERPRETER.md",{"type":49,"value":297}," (without a path) refers to this loaded contract.",{"type":43,"tag":58,"props":299,"children":301},{"id":300},"execution",[302],{"type":49,"value":303},"Execution",{"type":43,"tag":52,"props":305,"children":306},{},[307,309,314,316,322,324,330,332,338,339,345,347,352,354,360],{"type":49,"value":308},"This skill is driven by the interpreter loop in ",{"type":43,"tag":87,"props":310,"children":312},{"className":311},[],[313],{"type":49,"value":295},{"type":49,"value":315}," (§ The interpreter loop):\nit reads ",{"type":43,"tag":87,"props":317,"children":319},{"className":318},[],[320],{"type":49,"value":321},".phase-status.json",{"type":49,"value":323},", determines the current phase, runs each phase's\n",{"type":43,"tag":87,"props":325,"children":327},{"className":326},[],[328],{"type":49,"value":329},"_preconditions",{"type":49,"value":331}," \u002F fragments \u002F ",{"type":43,"tag":87,"props":333,"children":335},{"className":334},[],[336],{"type":49,"value":337},"_assemble",{"type":49,"value":274},{"type":43,"tag":87,"props":340,"children":342},{"className":341},[],[343],{"type":49,"value":344},"_postconditions",{"type":49,"value":346},", advances on ",{"type":43,"tag":87,"props":348,"children":350},{"className":349},[],[351],{"type":49,"value":272},{"type":49,"value":353},"\nvia ",{"type":43,"tag":87,"props":355,"children":357},{"className":356},[],[358],{"type":49,"value":359},"_advances_to",{"type":49,"value":361},", and validates state. The backbone (intake → discover → clarify →\nconfirm → design → estimate → generate → migration-plan → poc → complete) and the\none sidebar branch (add-capabilities) are derived\nfrom the phase files' frontmatter — they are not restated here.",{"type":43,"tag":52,"props":363,"children":364},{},[365,370,372,377,379,384,386,392,394,400,402,408,410,415,417,422],{"type":43,"tag":73,"props":366,"children":367},{},[368],{"type":49,"value":369},"Cold start (entry phase).",{"type":49,"value":371}," With no run under ",{"type":43,"tag":87,"props":373,"children":375},{"className":374},[],[376],{"type":49,"value":100},{"type":49,"value":378}," carrying a\n",{"type":43,"tag":87,"props":380,"children":382},{"className":381},[],[383],{"type":49,"value":321},{"type":49,"value":385},", begin at ",{"type":43,"tag":87,"props":387,"children":389},{"className":388},[],[390],{"type":49,"value":391},"references\u002Fphases\u002Fintake\u002Fintake.md",{"type":49,"value":393}," — this skill's entry\nphase (the one carrying ",{"type":43,"tag":87,"props":395,"children":397},{"className":396},[],[398],{"type":49,"value":399},"_init: true",{"type":49,"value":401},"). On a warm start, ",{"type":43,"tag":87,"props":403,"children":405},{"className":404},[],[406],{"type":49,"value":407},"current_phase",{"type":49,"value":409}," in\n",{"type":43,"tag":87,"props":411,"children":413},{"className":412},[],[414],{"type":49,"value":321},{"type":49,"value":416}," is authoritative (",{"type":43,"tag":87,"props":418,"children":420},{"className":419},[],[421],{"type":49,"value":295},{"type":49,"value":423}," § The interpreter loop).",{"type":43,"tag":52,"props":425,"children":426},{},[427,439],{"type":43,"tag":73,"props":428,"children":429},{},[430,432,437],{"type":49,"value":431},"Skill bindings (",{"type":43,"tag":87,"props":433,"children":435},{"className":434},[],[436],{"type":49,"value":295},{"type":49,"value":438}," § Skill bindings).",{"type":49,"value":440}," This skill declares:",{"type":43,"tag":65,"props":442,"children":443},{},[444,484,532,589,622],{"type":43,"tag":69,"props":445,"children":446},{},[447,452,454,459,461,466,468,474,476,482],{"type":43,"tag":73,"props":448,"children":449},{},[450],{"type":49,"value":451},"Run root",{"type":49,"value":453},": ",{"type":43,"tag":87,"props":455,"children":457},{"className":456},[],[458],{"type":49,"value":100},{"type":49,"value":460}," — ",{"type":43,"tag":87,"props":462,"children":464},{"className":463},[],[465],{"type":49,"value":92},{"type":49,"value":467}," is this skill's name for the run directory\n(",{"type":43,"tag":87,"props":469,"children":471},{"className":470},[],[472],{"type":49,"value":473},".agent-advisor\u002F[MMDD-HHMM]\u002F",{"type":49,"value":475},"). Intake's own prose performs the ",{"type":43,"tag":87,"props":477,"children":479},{"className":478},[],[480],{"type":49,"value":481},"_init",{"type":49,"value":483}," bootstrap.",{"type":43,"tag":69,"props":485,"children":486},{},[487,492,494,500,502,508,510,516,517,523,524,530],{"type":43,"tag":73,"props":488,"children":489},{},[490],{"type":49,"value":491},"State shape",{"type":49,"value":493},": § State file below (advisor-specific keys such as ",{"type":43,"tag":87,"props":495,"children":497},{"className":496},[],[498],{"type":49,"value":499},"entry_point",{"type":49,"value":501},",\n",{"type":43,"tag":87,"props":503,"children":505},{"className":504},[],[506],{"type":49,"value":507},"audience",{"type":49,"value":509},", ",{"type":43,"tag":87,"props":511,"children":513},{"className":512},[],[514],{"type":49,"value":515},"recommendation_reviewed",{"type":49,"value":509},{"type":43,"tag":87,"props":518,"children":520},{"className":519},[],[521],{"type":49,"value":522},"migration_plan_ctx",{"type":49,"value":509},{"type":43,"tag":87,"props":525,"children":527},{"className":526},[],[528],{"type":49,"value":529},"migration_plan_unavailable",{"type":49,"value":531},");\nthe shared state schema is not vendored.",{"type":43,"tag":69,"props":533,"children":534},{},[535,540,541,547,549,555,557,563,565,571,573,579,581,587],{"type":43,"tag":73,"props":536,"children":537},{},[538],{"type":49,"value":539},"Run seed (optional)",{"type":49,"value":453},{"type":43,"tag":87,"props":542,"children":544},{"className":543},[],[545],{"type":49,"value":546},"$RUN_DIR\u002Fseed.json",{"type":49,"value":548},", else ",{"type":43,"tag":87,"props":550,"children":552},{"className":551},[],[553],{"type":49,"value":554},".agent-advisor\u002Fseed.json",{"type":49,"value":556}," at the run root\n(schema ",{"type":43,"tag":87,"props":558,"children":560},{"className":559},[],[561],{"type":49,"value":562},"scripts\u002Fschemas\u002Fseed.json",{"type":49,"value":564},") supplies\nmachine-readable answers for a non-interactive run — the Clarify dimensions, the two gate\nanswers, the POC mode, the live-probe answer, and a ",{"type":43,"tag":87,"props":566,"children":568},{"className":567},[],[569],{"type":49,"value":570},"co_recommend",{"type":49,"value":572}," tie-break. It is the\nHIGHEST-precedence source for every value it carries (clarify.md Step 2.5), which is what makes\na repeated run's score comparable: the deterministic engine gets byte-identical input. A gate\nthe seed omits is declined; a dimension the seed omits falls through to detection, then prose,\nthen an ",{"type":43,"tag":87,"props":574,"children":576},{"className":575},[],[577],{"type":49,"value":578},"assumed",{"type":49,"value":580}," value that MUST be recorded in ",{"type":43,"tag":87,"props":582,"children":584},{"className":583},[],[585],{"type":49,"value":586},"$RUN_DIR\u002FUNANSWERED.md",{"type":49,"value":588},". With no seed, the\ninteractive flow is unchanged.",{"type":43,"tag":69,"props":590,"children":591},{},[592,597,598,604,606,612,614,620],{"type":43,"tag":73,"props":593,"children":594},{},[595],{"type":49,"value":596},"Resolved statuses",{"type":49,"value":453},{"type":43,"tag":87,"props":599,"children":601},{"className":600},[],[602],{"type":49,"value":603},"skipped",{"type":49,"value":605}," (routing resolved the phase without running it), plus\n",{"type":43,"tag":87,"props":607,"children":609},{"className":608},[],[610],{"type":49,"value":611},"not_applicable",{"type":49,"value":613}," for ",{"type":43,"tag":87,"props":615,"children":617},{"className":616},[],[618],{"type":49,"value":619},"migration_plan",{"type":49,"value":621}," only.",{"type":43,"tag":69,"props":623,"children":624},{},[625,630,632,637,639,644],{"type":43,"tag":73,"props":626,"children":627},{},[628],{"type":49,"value":629},"Conditional backbone routing",{"type":49,"value":631},": the entry-point routing below. When a routing rule\nmarks a phase not-applicable, set it ",{"type":43,"tag":87,"props":633,"children":635},{"className":634},[],[636],{"type":49,"value":603},{"type":49,"value":638}," and advance through its ",{"type":43,"tag":87,"props":640,"children":642},{"className":641},[],[643],{"type":49,"value":359},{"type":49,"value":645}," in\nthe same state write.",{"type":43,"tag":58,"props":647,"children":649},{"id":648},"routing-gates-orchestration",[650],{"type":49,"value":651},"Routing & gates (orchestration)",{"type":43,"tag":52,"props":653,"children":654},{},[655,657,662],{"type":49,"value":656},"Sidebar placement and conditional backbone routing are orchestration prose owned by\nthis file (",{"type":43,"tag":87,"props":658,"children":660},{"className":659},[],[661],{"type":49,"value":295},{"type":49,"value":663}," § Skill bindings, § Backbone vs sidebar).",{"type":43,"tag":52,"props":665,"children":666},{},[667],{"type":43,"tag":73,"props":668,"children":669},{},[670],{"type":49,"value":671},"Entry-point routing:",{"type":43,"tag":65,"props":673,"children":674},{},[675,693,717,764,791],{"type":43,"tag":69,"props":676,"children":677},{},[678,684,686,691],{"type":43,"tag":87,"props":679,"children":681},{"className":680},[],[682],{"type":49,"value":683},"build_scratch",{"type":49,"value":685}," → skip Discover; Clarify → Confirm → Design → Estimate → Generate → ",{"type":43,"tag":73,"props":687,"children":688},{},[689],{"type":49,"value":690},"Gate 2 → POC (any winning runtime)",{"type":49,"value":692},". No migration plan (nothing existing to migrate).",{"type":43,"tag":69,"props":694,"children":695},{},[696,702,704,709,711,715],{"type":43,"tag":87,"props":697,"children":699},{"className":698},[],[700],{"type":49,"value":701},"build_deploy",{"type":49,"value":703}," → Discover (if code) → Clarify → Confirm → Design → Estimate → Generate → ",{"type":43,"tag":73,"props":705,"children":706},{},[707],{"type":49,"value":708},"Gate 1 → Migration Plan (if existing non-AWS AI workload detected and user confirms)",{"type":49,"value":710}," → ",{"type":43,"tag":73,"props":712,"children":713},{},[714],{"type":49,"value":690},{"type":49,"value":716},".",{"type":43,"tag":69,"props":718,"children":719},{},[720,726,728,741,742,747,749,755,757,763],{"type":43,"tag":87,"props":721,"children":723},{"className":722},[],[724],{"type":49,"value":725},"migrate",{"type":49,"value":727}," → Discover (if code) → Clarify → Confirm → Design → Estimate (target-state run cost; migration TCO comparison stays with the Migration Plan engine) → Generate → ",{"type":43,"tag":73,"props":729,"children":730},{},[731,733,739],{"type":49,"value":732},"Gate 1 → Migration Plan (in-skill, reusing the sibling ",{"type":43,"tag":87,"props":734,"children":736},{"className":735},[],[737],{"type":49,"value":738},"gcp-to-aws",{"type":49,"value":740}," skill)",{"type":49,"value":710},{"type":43,"tag":73,"props":743,"children":744},{},[745],{"type":49,"value":746},"Gate 2 → POC (any winning runtime, when the plan was produced)",{"type":49,"value":748},". Declining Gate 1 keeps the classic handoff: pointer to ",{"type":43,"tag":87,"props":750,"children":752},{"className":751},[],[753],{"type":49,"value":754},"\u002Faws-startup-advisor:llm-to-bedrock",{"type":49,"value":756}," with ",{"type":43,"tag":87,"props":758,"children":760},{"className":759},[],[761],{"type":49,"value":762},"handoff-summary.md",{"type":49,"value":716},{"type":43,"tag":69,"props":765,"children":766},{},[767,773,775,781,783,789],{"type":43,"tag":87,"props":768,"children":770},{"className":769},[],[771],{"type":49,"value":772},"add_capabilities",{"type":49,"value":774}," → load ",{"type":43,"tag":87,"props":776,"children":778},{"className":777},[],[779],{"type":49,"value":780},"references\u002Fphases\u002Fadd-capabilities\u002Fadd-capabilities.md",{"type":49,"value":782}," and follow it (no runtime\nscoring; writes ",{"type":43,"tag":87,"props":784,"children":786},{"className":785},[],[787],{"type":49,"value":788},"capabilities-recommendation.md",{"type":49,"value":790},"). This is a self-contained branch — it does\nNOT pass through Clarify \u002F Confirm \u002F Design \u002F Estimate \u002F Generate, so the phase gate\nbelow never applies to it.",{"type":43,"tag":69,"props":792,"children":793},{},[794,796,801],{"type":49,"value":795},"Temporal detection routes into ",{"type":43,"tag":87,"props":797,"children":799},{"className":798},[],[800],{"type":49,"value":725},{"type":49,"value":802}," with temporal units pre-seeded (see discover).",{"type":43,"tag":52,"props":804,"children":805},{},[806],{"type":43,"tag":73,"props":807,"children":808},{},[809],{"type":49,"value":810},"Gate semantics (backbone tail):",{"type":43,"tag":65,"props":812,"children":813},{},[814,859,941],{"type":43,"tag":69,"props":815,"children":816},{},[817,827,829,835,837,843,845,850,852,857],{"type":43,"tag":73,"props":818,"children":819},{},[820,822],{"type":49,"value":821},"Gate 1 → ",{"type":43,"tag":87,"props":823,"children":825},{"className":824},[],[826],{"type":49,"value":619},{"type":49,"value":828}," runs only when ",{"type":43,"tag":87,"props":830,"children":832},{"className":831},[],[833],{"type":49,"value":834},"generate",{"type":49,"value":836}," is done AND\n",{"type":43,"tag":87,"props":838,"children":840},{"className":839},[],[841],{"type":49,"value":842},"recommendation_reviewed == true",{"type":49,"value":844}," (generate.md Step 5.5) AND entry point ∈ {migrate,\nbuild_deploy} AND the run is migration-eligible (generate.md Step 6) AND the user\nconfirmed Gate 1. Otherwise resolve it: ",{"type":43,"tag":87,"props":846,"children":848},{"className":847},[],[849],{"type":49,"value":611},{"type":49,"value":851}," (build_scratch \u002F no migratable\nworkload) or ",{"type":43,"tag":87,"props":853,"children":855},{"className":854},[],[856],{"type":49,"value":603},{"type":49,"value":858}," (declined) — and advance.",{"type":43,"tag":69,"props":860,"children":861},{},[862,873,874,880,882,887,889,895,897,902,904,910,912,917,919,925,927,932,933,939],{"type":43,"tag":73,"props":863,"children":864},{},[865,867],{"type":49,"value":866},"Gate 2 → ",{"type":43,"tag":87,"props":868,"children":870},{"className":869},[],[871],{"type":49,"value":872},"poc",{"type":49,"value":828},{"type":43,"tag":87,"props":875,"children":877},{"className":876},[],[878],{"type":49,"value":879},"phases.poc == \"in_progress\"",{"type":49,"value":881}," (set when the user\nanswers Gate 2 \"yes\" — asked in generate.md Step 7 or migration-plan.md Step 6) AND\n",{"type":43,"tag":87,"props":883,"children":885},{"className":884},[],[886],{"type":49,"value":842},{"type":49,"value":888},". Any winning runtime (agentcore \u002F ecs \u002F eks \u002F lambda \u002F\nlambda_microvms) — the POC shape follows the verdict (poc.md Step 3 dispatch on\n",{"type":43,"tag":87,"props":890,"children":892},{"className":891},[],[893],{"type":49,"value":894},"references\u002Fdecision-refs\u002Fpoc-shapes.md",{"type":49,"value":896},"). Gate 2 is only offered when ",{"type":43,"tag":87,"props":898,"children":900},{"className":899},[],[901],{"type":49,"value":619},{"type":49,"value":903},"\n∈ {completed, skipped, not_applicable} — or ",{"type":43,"tag":87,"props":905,"children":907},{"className":906},[],[908],{"type":49,"value":909},"in_progress",{"type":49,"value":911}," on build_deploy only (Stage 2\nfailed\u002Faborted; fallback POC from design.json per migration-plan.md failure handling);\nfor entry point ",{"type":43,"tag":87,"props":913,"children":915},{"className":914},[],[916],{"type":49,"value":725},{"type":49,"value":918},", only when ",{"type":43,"tag":87,"props":920,"children":922},{"className":921},[],[923],{"type":49,"value":924},"migration_plan == \"completed\"",{"type":49,"value":926}," (the POC implements the\nplan) OR when the stage resolved ",{"type":43,"tag":87,"props":928,"children":930},{"className":929},[],[931],{"type":49,"value":611},{"type":49,"value":756},{"type":43,"tag":87,"props":934,"children":936},{"className":935},[],[937],{"type":49,"value":938},"migration_plan_unavailable == \"engine_absent\"",{"type":49,"value":940}," — a standalone deployment that does not bundle the migration engine, where\nGate 2 is offered by migration-plan.md Step -1 and the POC is design-backed. A migrate-POC\nwith no plan for any OTHER reason (the user declined) has nothing to implement.",{"type":43,"tag":69,"props":942,"children":943},{},[944,946,952,954,959,961,966,968,973],{"type":49,"value":945},"Persisting Gate 2 as ",{"type":43,"tag":87,"props":947,"children":949},{"className":948},[],[950],{"type":49,"value":951},"phases.poc = \"in_progress\"",{"type":49,"value":953}," BEFORE poc.md loads makes the\nconfirmation resumable: if the session breaks between the \"yes\" and the load, the\ninterpreter re-enters ",{"type":43,"tag":87,"props":955,"children":957},{"className":956},[],[958],{"type":49,"value":872},{"type":49,"value":960}," without re-asking. (A declared deviation from\n",{"type":43,"tag":87,"props":962,"children":964},{"className":963},[],[965],{"type":49,"value":295},{"type":49,"value":967}," § The interpreter loop step 5's gate-then-",{"type":43,"tag":87,"props":969,"children":971},{"className":970},[],[972],{"type":49,"value":909},{"type":49,"value":974}," ordering — the\nuser's confirmation is the entry event worth persisting.)",{"type":43,"tag":52,"props":976,"children":977},{},[978,983,985,991,993,999,1001,1007,1009,1015,1017,1023],{"type":43,"tag":73,"props":979,"children":980},{},[981],{"type":49,"value":982},"Phase gate:",{"type":49,"value":984}," Do NOT load design.md \u002F estimate.md \u002F generate.md unless\n",{"type":43,"tag":87,"props":986,"children":988},{"className":987},[],[989],{"type":49,"value":990},"$RUN_DIR\u002F.phase-status.json",{"type":49,"value":992}," exists and BOTH ",{"type":43,"tag":87,"props":994,"children":996},{"className":995},[],[997],{"type":49,"value":998},"phases.clarify == \"completed\"",{"type":49,"value":1000}," AND\n",{"type":43,"tag":87,"props":1002,"children":1004},{"className":1003},[],[1005],{"type":49,"value":1006},"phases.confirm == \"completed\"",{"type":49,"value":1008},". Confirm confirms the deployment model, the service\nset, and (for a co_recommend tie) the user's ",{"type":43,"tag":87,"props":1010,"children":1012},{"className":1011},[],[1013],{"type":49,"value":1014},"chosen_runtime",{"type":49,"value":1016}," — Design and the diagram depend on\nits ",{"type":43,"tag":87,"props":1018,"children":1020},{"className":1019},[],[1021],{"type":49,"value":1022},"confirm.json",{"type":49,"value":1024}," output, so it must not be skipped. If the user asks to skip Clarify or Pass 2,\nrefuse briefly and run it.",{"type":43,"tag":58,"props":1026,"children":1028},{"id":1027},"state-file-phase-statusjson",[1029,1031,1036],{"type":49,"value":1030},"State file (",{"type":43,"tag":87,"props":1032,"children":1034},{"className":1033},[],[1035],{"type":49,"value":321},{"type":49,"value":1037},")",{"type":43,"tag":1039,"props":1040,"children":1045},"pre",{"className":1041,"code":1042,"language":1043,"meta":1044,"style":1044},"language-json shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","{\n  \"run_id\": \"0630-1430\",\n  \"entry_point\": \"build_scratch\",\n  \"audience\": \"technical\",\n  \"current_phase\": \"clarify\",\n  \"phases\": {\n    \"intake\": \"completed\",\n    \"discover\": \"skipped\",\n    \"clarify\": \"in_progress\",\n    \"confirm\": \"pending\",\n    \"design\": \"pending\",\n    \"estimate\": \"pending\",\n    \"generate\": \"pending\",\n    \"migration_plan\": \"pending\",\n    \"poc\": \"pending\"\n  }\n}\n","json","",[1046],{"type":43,"tag":87,"props":1047,"children":1048},{"__ignoreMap":1044},[1049,1061,1105,1141,1178,1215,1241,1281,1318,1354,1392,1429,1466,1502,1537,1569,1578],{"type":43,"tag":1050,"props":1051,"children":1054},"span",{"class":1052,"line":1053},"line",1,[1055],{"type":43,"tag":1050,"props":1056,"children":1058},{"style":1057},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[1059],{"type":49,"value":1060},"{\n",{"type":43,"tag":1050,"props":1062,"children":1064},{"class":1052,"line":1063},2,[1065,1070,1076,1081,1086,1091,1097,1101],{"type":43,"tag":1050,"props":1066,"children":1067},{"style":1057},[1068],{"type":49,"value":1069},"  \"",{"type":43,"tag":1050,"props":1071,"children":1073},{"style":1072},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[1074],{"type":49,"value":1075},"run_id",{"type":43,"tag":1050,"props":1077,"children":1078},{"style":1057},[1079],{"type":49,"value":1080},"\"",{"type":43,"tag":1050,"props":1082,"children":1083},{"style":1057},[1084],{"type":49,"value":1085},":",{"type":43,"tag":1050,"props":1087,"children":1088},{"style":1057},[1089],{"type":49,"value":1090}," \"",{"type":43,"tag":1050,"props":1092,"children":1094},{"style":1093},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[1095],{"type":49,"value":1096},"0630-1430",{"type":43,"tag":1050,"props":1098,"children":1099},{"style":1057},[1100],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1102,"children":1103},{"style":1057},[1104],{"type":49,"value":501},{"type":43,"tag":1050,"props":1106,"children":1108},{"class":1052,"line":1107},3,[1109,1113,1117,1121,1125,1129,1133,1137],{"type":43,"tag":1050,"props":1110,"children":1111},{"style":1057},[1112],{"type":49,"value":1069},{"type":43,"tag":1050,"props":1114,"children":1115},{"style":1072},[1116],{"type":49,"value":499},{"type":43,"tag":1050,"props":1118,"children":1119},{"style":1057},[1120],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1122,"children":1123},{"style":1057},[1124],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1126,"children":1127},{"style":1057},[1128],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1130,"children":1131},{"style":1093},[1132],{"type":49,"value":683},{"type":43,"tag":1050,"props":1134,"children":1135},{"style":1057},[1136],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1138,"children":1139},{"style":1057},[1140],{"type":49,"value":501},{"type":43,"tag":1050,"props":1142,"children":1144},{"class":1052,"line":1143},4,[1145,1149,1153,1157,1161,1165,1170,1174],{"type":43,"tag":1050,"props":1146,"children":1147},{"style":1057},[1148],{"type":49,"value":1069},{"type":43,"tag":1050,"props":1150,"children":1151},{"style":1072},[1152],{"type":49,"value":507},{"type":43,"tag":1050,"props":1154,"children":1155},{"style":1057},[1156],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1158,"children":1159},{"style":1057},[1160],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1162,"children":1163},{"style":1057},[1164],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1166,"children":1167},{"style":1093},[1168],{"type":49,"value":1169},"technical",{"type":43,"tag":1050,"props":1171,"children":1172},{"style":1057},[1173],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1175,"children":1176},{"style":1057},[1177],{"type":49,"value":501},{"type":43,"tag":1050,"props":1179,"children":1181},{"class":1052,"line":1180},5,[1182,1186,1190,1194,1198,1202,1207,1211],{"type":43,"tag":1050,"props":1183,"children":1184},{"style":1057},[1185],{"type":49,"value":1069},{"type":43,"tag":1050,"props":1187,"children":1188},{"style":1072},[1189],{"type":49,"value":407},{"type":43,"tag":1050,"props":1191,"children":1192},{"style":1057},[1193],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1195,"children":1196},{"style":1057},[1197],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1199,"children":1200},{"style":1057},[1201],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1203,"children":1204},{"style":1093},[1205],{"type":49,"value":1206},"clarify",{"type":43,"tag":1050,"props":1208,"children":1209},{"style":1057},[1210],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1212,"children":1213},{"style":1057},[1214],{"type":49,"value":501},{"type":43,"tag":1050,"props":1216,"children":1218},{"class":1052,"line":1217},6,[1219,1223,1228,1232,1236],{"type":43,"tag":1050,"props":1220,"children":1221},{"style":1057},[1222],{"type":49,"value":1069},{"type":43,"tag":1050,"props":1224,"children":1225},{"style":1072},[1226],{"type":49,"value":1227},"phases",{"type":43,"tag":1050,"props":1229,"children":1230},{"style":1057},[1231],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1233,"children":1234},{"style":1057},[1235],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1237,"children":1238},{"style":1057},[1239],{"type":49,"value":1240}," {\n",{"type":43,"tag":1050,"props":1242,"children":1244},{"class":1052,"line":1243},7,[1245,1250,1256,1260,1264,1268,1273,1277],{"type":43,"tag":1050,"props":1246,"children":1247},{"style":1057},[1248],{"type":49,"value":1249},"    \"",{"type":43,"tag":1050,"props":1251,"children":1253},{"style":1252},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[1254],{"type":49,"value":1255},"intake",{"type":43,"tag":1050,"props":1257,"children":1258},{"style":1057},[1259],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1261,"children":1262},{"style":1057},[1263],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1265,"children":1266},{"style":1057},[1267],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1269,"children":1270},{"style":1093},[1271],{"type":49,"value":1272},"completed",{"type":43,"tag":1050,"props":1274,"children":1275},{"style":1057},[1276],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1278,"children":1279},{"style":1057},[1280],{"type":49,"value":501},{"type":43,"tag":1050,"props":1282,"children":1284},{"class":1052,"line":1283},8,[1285,1289,1294,1298,1302,1306,1310,1314],{"type":43,"tag":1050,"props":1286,"children":1287},{"style":1057},[1288],{"type":49,"value":1249},{"type":43,"tag":1050,"props":1290,"children":1291},{"style":1252},[1292],{"type":49,"value":1293},"discover",{"type":43,"tag":1050,"props":1295,"children":1296},{"style":1057},[1297],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1299,"children":1300},{"style":1057},[1301],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1303,"children":1304},{"style":1057},[1305],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1307,"children":1308},{"style":1093},[1309],{"type":49,"value":603},{"type":43,"tag":1050,"props":1311,"children":1312},{"style":1057},[1313],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1315,"children":1316},{"style":1057},[1317],{"type":49,"value":501},{"type":43,"tag":1050,"props":1319,"children":1321},{"class":1052,"line":1320},9,[1322,1326,1330,1334,1338,1342,1346,1350],{"type":43,"tag":1050,"props":1323,"children":1324},{"style":1057},[1325],{"type":49,"value":1249},{"type":43,"tag":1050,"props":1327,"children":1328},{"style":1252},[1329],{"type":49,"value":1206},{"type":43,"tag":1050,"props":1331,"children":1332},{"style":1057},[1333],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1335,"children":1336},{"style":1057},[1337],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1339,"children":1340},{"style":1057},[1341],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1343,"children":1344},{"style":1093},[1345],{"type":49,"value":909},{"type":43,"tag":1050,"props":1347,"children":1348},{"style":1057},[1349],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1351,"children":1352},{"style":1057},[1353],{"type":49,"value":501},{"type":43,"tag":1050,"props":1355,"children":1357},{"class":1052,"line":1356},10,[1358,1362,1367,1371,1375,1379,1384,1388],{"type":43,"tag":1050,"props":1359,"children":1360},{"style":1057},[1361],{"type":49,"value":1249},{"type":43,"tag":1050,"props":1363,"children":1364},{"style":1252},[1365],{"type":49,"value":1366},"confirm",{"type":43,"tag":1050,"props":1368,"children":1369},{"style":1057},[1370],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1372,"children":1373},{"style":1057},[1374],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1376,"children":1377},{"style":1057},[1378],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1380,"children":1381},{"style":1093},[1382],{"type":49,"value":1383},"pending",{"type":43,"tag":1050,"props":1385,"children":1386},{"style":1057},[1387],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1389,"children":1390},{"style":1057},[1391],{"type":49,"value":501},{"type":43,"tag":1050,"props":1393,"children":1395},{"class":1052,"line":1394},11,[1396,1400,1405,1409,1413,1417,1421,1425],{"type":43,"tag":1050,"props":1397,"children":1398},{"style":1057},[1399],{"type":49,"value":1249},{"type":43,"tag":1050,"props":1401,"children":1402},{"style":1252},[1403],{"type":49,"value":1404},"design",{"type":43,"tag":1050,"props":1406,"children":1407},{"style":1057},[1408],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1410,"children":1411},{"style":1057},[1412],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1414,"children":1415},{"style":1057},[1416],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1418,"children":1419},{"style":1093},[1420],{"type":49,"value":1383},{"type":43,"tag":1050,"props":1422,"children":1423},{"style":1057},[1424],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1426,"children":1427},{"style":1057},[1428],{"type":49,"value":501},{"type":43,"tag":1050,"props":1430,"children":1432},{"class":1052,"line":1431},12,[1433,1437,1442,1446,1450,1454,1458,1462],{"type":43,"tag":1050,"props":1434,"children":1435},{"style":1057},[1436],{"type":49,"value":1249},{"type":43,"tag":1050,"props":1438,"children":1439},{"style":1252},[1440],{"type":49,"value":1441},"estimate",{"type":43,"tag":1050,"props":1443,"children":1444},{"style":1057},[1445],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1447,"children":1448},{"style":1057},[1449],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1451,"children":1452},{"style":1057},[1453],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1455,"children":1456},{"style":1093},[1457],{"type":49,"value":1383},{"type":43,"tag":1050,"props":1459,"children":1460},{"style":1057},[1461],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1463,"children":1464},{"style":1057},[1465],{"type":49,"value":501},{"type":43,"tag":1050,"props":1467,"children":1469},{"class":1052,"line":1468},13,[1470,1474,1478,1482,1486,1490,1494,1498],{"type":43,"tag":1050,"props":1471,"children":1472},{"style":1057},[1473],{"type":49,"value":1249},{"type":43,"tag":1050,"props":1475,"children":1476},{"style":1252},[1477],{"type":49,"value":834},{"type":43,"tag":1050,"props":1479,"children":1480},{"style":1057},[1481],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1483,"children":1484},{"style":1057},[1485],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1487,"children":1488},{"style":1057},[1489],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1491,"children":1492},{"style":1093},[1493],{"type":49,"value":1383},{"type":43,"tag":1050,"props":1495,"children":1496},{"style":1057},[1497],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1499,"children":1500},{"style":1057},[1501],{"type":49,"value":501},{"type":43,"tag":1050,"props":1503,"children":1504},{"class":1052,"line":26},[1505,1509,1513,1517,1521,1525,1529,1533],{"type":43,"tag":1050,"props":1506,"children":1507},{"style":1057},[1508],{"type":49,"value":1249},{"type":43,"tag":1050,"props":1510,"children":1511},{"style":1252},[1512],{"type":49,"value":619},{"type":43,"tag":1050,"props":1514,"children":1515},{"style":1057},[1516],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1518,"children":1519},{"style":1057},[1520],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1522,"children":1523},{"style":1057},[1524],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1526,"children":1527},{"style":1093},[1528],{"type":49,"value":1383},{"type":43,"tag":1050,"props":1530,"children":1531},{"style":1057},[1532],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1534,"children":1535},{"style":1057},[1536],{"type":49,"value":501},{"type":43,"tag":1050,"props":1538,"children":1539},{"class":1052,"line":30},[1540,1544,1548,1552,1556,1560,1564],{"type":43,"tag":1050,"props":1541,"children":1542},{"style":1057},[1543],{"type":49,"value":1249},{"type":43,"tag":1050,"props":1545,"children":1546},{"style":1252},[1547],{"type":49,"value":872},{"type":43,"tag":1050,"props":1549,"children":1550},{"style":1057},[1551],{"type":49,"value":1080},{"type":43,"tag":1050,"props":1553,"children":1554},{"style":1057},[1555],{"type":49,"value":1085},{"type":43,"tag":1050,"props":1557,"children":1558},{"style":1057},[1559],{"type":49,"value":1090},{"type":43,"tag":1050,"props":1561,"children":1562},{"style":1093},[1563],{"type":49,"value":1383},{"type":43,"tag":1050,"props":1565,"children":1566},{"style":1057},[1567],{"type":49,"value":1568},"\"\n",{"type":43,"tag":1050,"props":1570,"children":1572},{"class":1052,"line":1571},16,[1573],{"type":43,"tag":1050,"props":1574,"children":1575},{"style":1057},[1576],{"type":49,"value":1577},"  }\n",{"type":43,"tag":1050,"props":1579,"children":1581},{"class":1052,"line":1580},17,[1582],{"type":43,"tag":1050,"props":1583,"children":1584},{"style":1057},[1585],{"type":49,"value":1586},"}\n",{"type":43,"tag":52,"props":1588,"children":1589},{},[1590,1592,1597,1598,1603,1604,1609,1611,1616],{"type":49,"value":1591},"Status values: ",{"type":43,"tag":87,"props":1593,"children":1595},{"className":1594},[],[1596],{"type":49,"value":1383},{"type":49,"value":710},{"type":43,"tag":87,"props":1599,"children":1601},{"className":1600},[],[1602],{"type":49,"value":909},{"type":49,"value":710},{"type":43,"tag":87,"props":1605,"children":1607},{"className":1606},[],[1608],{"type":49,"value":1272},{"type":49,"value":1610},", plus ",{"type":43,"tag":87,"props":1612,"children":1614},{"className":1613},[],[1615],{"type":49,"value":603},{"type":49,"value":1617},". Use read-merge-write:\nread before each update, change only the advancing keys, keep prior phases.",{"type":43,"tag":52,"props":1619,"children":1620},{},[1621,1626,1628,1634,1636,1641,1642,1647],{"type":43,"tag":87,"props":1622,"children":1624},{"className":1623},[],[1625],{"type":49,"value":515},{"type":49,"value":1627}," (top level, boolean) is set to ",{"type":43,"tag":87,"props":1629,"children":1631},{"className":1630},[],[1632],{"type":49,"value":1633},"true",{"type":49,"value":1635}," by generate.md Step 5.5 when\nthe user explicitly confirms they have seen the recommendation. Gate 1, Gate 2, and the\n",{"type":43,"tag":87,"props":1637,"children":1639},{"className":1638},[],[1640],{"type":49,"value":619},{"type":49,"value":274},{"type":43,"tag":87,"props":1643,"children":1645},{"className":1644},[],[1646],{"type":49,"value":872},{"type":49,"value":1648}," states all require it — no gate may be asked while it is absent.",{"type":43,"tag":52,"props":1650,"children":1651},{},[1652,1657,1659,1664,1666,1671,1673,1679],{"type":43,"tag":87,"props":1653,"children":1655},{"className":1654},[],[1656],{"type":49,"value":619},{"type":49,"value":1658}," additionally uses ",{"type":43,"tag":87,"props":1660,"children":1662},{"className":1661},[],[1663],{"type":49,"value":611},{"type":49,"value":1665}," (build_scratch, or no migratable workload\ndetected). When Stage 2 runs, ",{"type":43,"tag":87,"props":1667,"children":1669},{"className":1668},[],[1670],{"type":49,"value":522},{"type":49,"value":1672}," is added at the top level:\n",{"type":43,"tag":87,"props":1674,"children":1676},{"className":1675},[],[1677],{"type":49,"value":1678},"{\"repo\": \"\u003Cabs path to target repo>\", \"migration_dir\": \"\u003Cabs path to .migration\u002F\u003Cid>\u002F>\"}",{"type":49,"value":1680}," —\nStage 3 reads gcp-to-aws artifacts ONLY via this recorded path, never by re-globbing.",{"type":43,"tag":58,"props":1682,"children":1684},{"id":1683},"files",[1685],{"type":49,"value":1686},"Files",{"type":43,"tag":1688,"props":1689,"children":1690},"table",{},[1691,1710],{"type":43,"tag":1692,"props":1693,"children":1694},"thead",{},[1695],{"type":43,"tag":1696,"props":1697,"children":1698},"tr",{},[1699,1705],{"type":43,"tag":1700,"props":1701,"children":1702},"th",{},[1703],{"type":49,"value":1704},"File",{"type":43,"tag":1700,"props":1706,"children":1707},{},[1708],{"type":49,"value":1709},"Purpose",{"type":43,"tag":1711,"props":1712,"children":1713},"tbody",{},[1714,1731,1747,1764,1781,1798,1815,1832,1849,1866,1883,1900,1917,1933,1950,1967,1984,2001,2018,2035,2052,2069],{"type":43,"tag":1696,"props":1715,"children":1716},{},[1717,1726],{"type":43,"tag":1718,"props":1719,"children":1720},"td",{},[1721],{"type":43,"tag":87,"props":1722,"children":1724},{"className":1723},[],[1725],{"type":49,"value":264},{"type":43,"tag":1718,"props":1727,"children":1728},{},[1729],{"type":49,"value":1730},"Vendored DSL execution contract (interpreter loop + gate protocol)",{"type":43,"tag":1696,"props":1732,"children":1733},{},[1734,1742],{"type":43,"tag":1718,"props":1735,"children":1736},{},[1737],{"type":43,"tag":87,"props":1738,"children":1740},{"className":1739},[],[1741],{"type":49,"value":391},{"type":43,"tag":1718,"props":1743,"children":1744},{},[1745],{"type":49,"value":1746},"Entry point + technical background + open context",{"type":43,"tag":1696,"props":1748,"children":1749},{},[1750,1759],{"type":43,"tag":1718,"props":1751,"children":1752},{},[1753],{"type":43,"tag":87,"props":1754,"children":1756},{"className":1755},[],[1757],{"type":49,"value":1758},"references\u002Fphases\u002Fdiscover\u002Fdiscover.md",{"type":43,"tag":1718,"props":1760,"children":1761},{},[1762],{"type":49,"value":1763},"Lightweight code detection",{"type":43,"tag":1696,"props":1765,"children":1766},{},[1767,1776],{"type":43,"tag":1718,"props":1768,"children":1769},{},[1770],{"type":43,"tag":87,"props":1771,"children":1773},{"className":1772},[],[1774],{"type":49,"value":1775},"references\u002Fphases\u002Fclarify\u002Fclarify.md",{"type":43,"tag":1718,"props":1777,"children":1778},{},[1779],{"type":49,"value":1780},"Clarify orchestrator + answer mapping to scoring keys",{"type":43,"tag":1696,"props":1782,"children":1783},{},[1784,1793],{"type":43,"tag":1718,"props":1785,"children":1786},{},[1787],{"type":43,"tag":87,"props":1788,"children":1790},{"className":1789},[],[1791],{"type":49,"value":1792},"references\u002Fphases\u002Fclarify\u002Fclarify-technical.md",{"type":43,"tag":1718,"props":1794,"children":1795},{},[1796],{"type":49,"value":1797},"Technical-background question wording",{"type":43,"tag":1696,"props":1799,"children":1800},{},[1801,1810],{"type":43,"tag":1718,"props":1802,"children":1803},{},[1804],{"type":43,"tag":87,"props":1805,"children":1807},{"className":1806},[],[1808],{"type":49,"value":1809},"references\u002Fphases\u002Fclarify\u002Fclarify-business.md",{"type":43,"tag":1718,"props":1811,"children":1812},{},[1813],{"type":49,"value":1814},"Business-background question wording",{"type":43,"tag":1696,"props":1816,"children":1817},{},[1818,1827],{"type":43,"tag":1718,"props":1819,"children":1820},{},[1821],{"type":43,"tag":87,"props":1822,"children":1824},{"className":1823},[],[1825],{"type":49,"value":1826},"references\u002Fphases\u002Fconfirm\u002Fconfirm.md",{"type":43,"tag":1718,"props":1828,"children":1829},{},[1830],{"type":49,"value":1831},"Winner-specific follow-ups",{"type":43,"tag":1696,"props":1833,"children":1834},{},[1835,1844],{"type":43,"tag":1718,"props":1836,"children":1837},{},[1838],{"type":43,"tag":87,"props":1839,"children":1841},{"className":1840},[],[1842],{"type":49,"value":1843},"references\u002Fphases\u002Fdesign\u002Fdesign.md",{"type":43,"tag":1718,"props":1845,"children":1846},{},[1847],{"type":49,"value":1848},"Assemble recommendation; Migrate handoff branch",{"type":43,"tag":1696,"props":1850,"children":1851},{},[1852,1861],{"type":43,"tag":1718,"props":1853,"children":1854},{},[1855],{"type":43,"tag":87,"props":1856,"children":1858},{"className":1857},[],[1859],{"type":49,"value":1860},"references\u002Fphases\u002Festimate\u002Festimate.md",{"type":43,"tag":1718,"props":1862,"children":1863},{},[1864],{"type":49,"value":1865},"Coarse cost magnitude",{"type":43,"tag":1696,"props":1867,"children":1868},{},[1869,1878],{"type":43,"tag":1718,"props":1870,"children":1871},{},[1872],{"type":43,"tag":87,"props":1873,"children":1875},{"className":1874},[],[1876],{"type":49,"value":1877},"references\u002Fphases\u002Fgenerate\u002Fgenerate.md",{"type":43,"tag":1718,"props":1879,"children":1880},{},[1881],{"type":49,"value":1882},"Layered recommendation doc + scaffolding",{"type":43,"tag":1696,"props":1884,"children":1885},{},[1886,1895],{"type":43,"tag":1718,"props":1887,"children":1888},{},[1889],{"type":43,"tag":87,"props":1890,"children":1892},{"className":1891},[],[1893],{"type":49,"value":1894},"references\u002Fphases\u002Fmigration-plan\u002Fmigration-plan.md",{"type":43,"tag":1718,"props":1896,"children":1897},{},[1898],{"type":49,"value":1899},"Stage 2: full migration plan via the sibling gcp-to-aws engine",{"type":43,"tag":1696,"props":1901,"children":1902},{},[1903,1912],{"type":43,"tag":1718,"props":1904,"children":1905},{},[1906],{"type":43,"tag":87,"props":1907,"children":1909},{"className":1908},[],[1910],{"type":49,"value":1911},"references\u002Fdecision-refs\u002Ftemporal.md",{"type":43,"tag":1718,"props":1913,"children":1914},{},[1915],{"type":49,"value":1916},"Temporal rules: Tier 1\u002F2 tables, adapter, runbooks, commercials (consumed by discover\u002Fclarify\u002Fdesign\u002Fgenerate)",{"type":43,"tag":1696,"props":1918,"children":1919},{},[1920,1928],{"type":43,"tag":1718,"props":1921,"children":1922},{},[1923],{"type":43,"tag":87,"props":1924,"children":1926},{"className":1925},[],[1927],{"type":49,"value":894},{"type":43,"tag":1718,"props":1929,"children":1930},{},[1931],{"type":49,"value":1932},"Per-runtime POC deploy shapes (ECS\u002FEKS\u002FLambda\u002FMicroVMs\u002FTemporal)",{"type":43,"tag":1696,"props":1934,"children":1935},{},[1936,1945],{"type":43,"tag":1718,"props":1937,"children":1938},{},[1939],{"type":43,"tag":87,"props":1940,"children":1942},{"className":1941},[],[1943],{"type":49,"value":1944},"references\u002Fdecision-refs\u002F*.md",{"type":43,"tag":1718,"props":1946,"children":1947},{},[1948],{"type":49,"value":1949},"Runtime service cards, model defaults, freshness",{"type":43,"tag":1696,"props":1951,"children":1952},{},[1953,1962],{"type":43,"tag":1718,"props":1954,"children":1955},{},[1956],{"type":43,"tag":87,"props":1957,"children":1959},{"className":1958},[],[1960],{"type":49,"value":1961},"references\u002Fdecision-refs\u002Fworkload-classes.md",{"type":43,"tag":1718,"props":1963,"children":1964},{},[1965],{"type":49,"value":1966},"Deterministic verdicts for non-agent workload units (batch\u002Fservice\u002Fio)",{"type":43,"tag":1696,"props":1968,"children":1969},{},[1970,1979],{"type":43,"tag":1718,"props":1971,"children":1972},{},[1973],{"type":43,"tag":87,"props":1974,"children":1976},{"className":1975},[],[1977],{"type":49,"value":1978},"references\u002Fruntimes\u002F*.json",{"type":43,"tag":1718,"props":1980,"children":1981},{},[1982],{"type":49,"value":1983},"Runtime registry (read by scoring.py)",{"type":43,"tag":1696,"props":1985,"children":1986},{},[1987,1996],{"type":43,"tag":1718,"props":1988,"children":1989},{},[1990],{"type":43,"tag":87,"props":1991,"children":1993},{"className":1992},[],[1994],{"type":49,"value":1995},"scripts\u002Fscoring.py",{"type":43,"tag":1718,"props":1997,"children":1998},{},[1999],{"type":49,"value":2000},"Deterministic scoring engine",{"type":43,"tag":1696,"props":2002,"children":2003},{},[2004,2013],{"type":43,"tag":1718,"props":2005,"children":2006},{},[2007],{"type":43,"tag":87,"props":2008,"children":2010},{"className":2009},[],[2011],{"type":49,"value":2012},"scripts\u002Ftest_temporal_decision_refs.py",{"type":43,"tag":1718,"props":2014,"children":2015},{},[2016],{"type":49,"value":2017},"Content lock for the Temporal decision reference",{"type":43,"tag":1696,"props":2019,"children":2020},{},[2021,2030],{"type":43,"tag":1718,"props":2022,"children":2023},{},[2024],{"type":43,"tag":87,"props":2025,"children":2027},{"className":2026},[],[2028],{"type":49,"value":2029},"scripts\u002Ftest_poc_shapes.py",{"type":43,"tag":1718,"props":2031,"children":2032},{},[2033],{"type":49,"value":2034},"Content lock for the POC deploy shapes",{"type":43,"tag":1696,"props":2036,"children":2037},{},[2038,2047],{"type":43,"tag":1718,"props":2039,"children":2040},{},[2041],{"type":43,"tag":87,"props":2042,"children":2044},{"className":2043},[],[2045],{"type":49,"value":2046},"scripts\u002Ftest_workload_classes.py",{"type":43,"tag":1718,"props":2048,"children":2049},{},[2050],{"type":49,"value":2051},"Content lock for workload-classes.md (verdicts table)",{"type":43,"tag":1696,"props":2053,"children":2054},{},[2055,2064],{"type":43,"tag":1718,"props":2056,"children":2057},{},[2058],{"type":43,"tag":87,"props":2059,"children":2061},{"className":2060},[],[2062],{"type":49,"value":2063},"scripts\u002Ftest_unit_grouping.py",{"type":43,"tag":1718,"props":2065,"children":2066},{},[2067],{"type":49,"value":2068},"Unit grouping + pattern matching (workload-class assignment)",{"type":43,"tag":1696,"props":2070,"children":2071},{},[2072,2081],{"type":43,"tag":1718,"props":2073,"children":2074},{},[2075],{"type":43,"tag":87,"props":2076,"children":2078},{"className":2077},[],[2079],{"type":49,"value":2080},"scripts\u002Ftest_collapse_invariant.py",{"type":43,"tag":1718,"props":2082,"children":2083},{},[2084,2086,2091,2093,2098],{"type":49,"value":2085},"Collapse-invariant ordering enforcement (A→B implies ",{"type":43,"tag":1050,"props":2087,"children":2088},{},[2089],{"type":49,"value":2090},"B",{"type":49,"value":2092}," ⊆ ",{"type":43,"tag":1050,"props":2094,"children":2095},{},[2096],{"type":49,"value":2097},"A",{"type":49,"value":2099}," outputs)",{"type":43,"tag":2101,"props":2102,"children":2103},"style",{},[2104],{"type":49,"value":2105},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":2107,"total":1283},[2108,2115,2129,2145,2158,2175,2193],{"slug":4,"name":4,"fn":5,"description":6,"org":2109,"tags":2110,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2111,2112,2113,2114],{"name":14,"slug":15,"type":16},{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"slug":2116,"name":2116,"fn":2117,"description":2118,"org":2119,"tags":2120,"stars":26,"repoUrl":27,"updatedAt":2128},"architect-for-startups","advise on AWS architecture for startups","Startup-tailored AWS architecture advice that adjusts recommendations to the company's stage (pre-revenue through Series B+), team size, runway, and available credits. Use when a founder wants guidance or a recommendation rather than code changes: which services to choose, how to plan or review an architecture, how to stretch credits and control cost, or how to prepare architecture for a fundraise or technical diligence. For an interactive discovery flow that scaffolds and writes the architecture into the codebase, use start-building-for-startups. Do not use for: writing or scaffolding code, factual AWS Activate \u002F programs \u002F credits lookups (see knowledge-base-for-startups), a single copy-paste prompt (see prompt-library-for-startups), or migration intent such as GCP-to-AWS or Heroku-to-AWS (see the migration skills: `gcp-to-aws`, `heroku-to-aws`, `llm-to-bedrock`).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2121,2124,2125],{"name":2122,"slug":2123,"type":16},"Architecture","architecture",{"name":24,"slug":25,"type":16},{"name":2126,"slug":2127,"type":16},"Strategy","strategy","2026-08-14T04:27:18.122372",{"slug":738,"name":738,"fn":2130,"description":2131,"org":2132,"tags":2133,"stars":26,"repoUrl":27,"updatedAt":2144},"migrate workloads from GCP to AWS","Migrate workloads from Google Cloud Platform to AWS — including AI and agentic workloads regardless of cloud provider. Triggers on: migrate from GCP, GCP to AWS, move off Google Cloud, migrate Terraform to AWS, migrate Cloud SQL to RDS, migrate GKE to EKS, migrate Cloud Run to Fargate, Google Cloud migration, migrate from OpenAI to Bedrock, move off OpenAI, switch from ChatGPT API to AWS, migrate from Gemini to Bedrock, migrate LangChain to Bedrock, migrate LangGraph to AWS, migrate agentic workloads to AWS, move AI workloads to AWS, migrate my AI app to AWS. Runs a 6-phase process: discover GCP resources from Terraform files, app code, or billing exports, clarify migration requirements, design AWS architecture, estimate costs, generate migration artifacts, and collect optional feedback. Clarify must finish before Design, Estimate, or Generate. Includes AI provider migration guidance (for example, OpenAI to Amazon Bedrock) by selecting closest-fit Bedrock model families for required modality, latency\u002Fquality targets, context windows, and cost constraints. Model mapping is compatibility-guided, not 1:1 parity; validate prompts, tool-calling behavior, and eval metrics before cutover. Do not use for: Azure or on-premises migrations to AWS, AWS-to-GCP reverse migration, general AWS architecture advice without migration intent, GCP-to-GCP refactoring, or multi-cloud deployments that do not involve migrating off GCP.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2134,2135,2138,2141],{"name":24,"slug":25,"type":16},{"name":2136,"slug":2137,"type":16},"Google Cloud","google-cloud",{"name":2139,"slug":2140,"type":16},"Infrastructure","infrastructure",{"name":2142,"slug":2143,"type":16},"Migration","migration","2026-08-14T04:52:07.358543",{"slug":2146,"name":2146,"fn":2147,"description":2148,"org":2149,"tags":2150,"stars":26,"repoUrl":27,"updatedAt":2157},"heroku-to-aws","migrate workloads from Heroku to AWS","Migrate workloads from Heroku to AWS. Triggers on: migrate from Heroku, Heroku to AWS, move off Heroku, migrate Heroku app, migrate Heroku Postgres to RDS, migrate Heroku Redis to ElastiCache, migrate Heroku Kafka to MSK, migrate dynos to Elastic Beanstalk, migrate dynos to Fargate, Heroku migration, move from Heroku to AWS, migrate Heroku Private Space, Heroku to Elastic Beanstalk, Heroku to ECS, Heroku to Fargate, leave Heroku, migrate off Heroku platform, what-if workshop, reprice Heroku migration, compare migration scenarios, workshop mode. Runs a 6-phase process: discover Heroku resources live via the authenticated Heroku CLI (read-only, consent-gated) and\u002For from Terraform files, Procfile\u002Fapp.json, and optional billing exports, clarify migration requirements, design AWS architecture, estimate costs, generate migration artifacts, and collect optional feedback. After Estimate, an optional what-if workshop can reprice region\u002FHA\u002Fcompute\u002FGraviton scenarios without re-discovery. Clarify must finish before Design, Estimate, or Generate. Uses a flat resource model (no clustering or dependency graphs) with deterministic mapping tables for core services (Dynos → Elastic Beanstalk by default, Postgres → RDS\u002FAurora, Redis → ElastiCache, Kafka → MSK) and a fast-path table for 13+ common add-ons. Cedar\u002FFir generation detection is detect-only in v1. Pipeline\u002FReview Apps are detect-only. Do not use for: GCP or Azure migrations to AWS, AWS-to-Heroku reverse migration, general AWS architecture advice without migration intent, Heroku-to-Heroku refactoring, or multi-cloud deployments that do not involve migrating off Heroku.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2151,2152,2155,2156],{"name":24,"slug":25,"type":16},{"name":2153,"slug":2154,"type":16},"Heroku","heroku",{"name":2139,"slug":2140,"type":16},{"name":2142,"slug":2143,"type":16},"2026-08-14T04:52:09.216805",{"slug":2159,"name":2159,"fn":2160,"description":2161,"org":2162,"tags":2163,"stars":26,"repoUrl":27,"updatedAt":2174},"knowledge-base-for-startups","retrieve AWS startup reference content","AWS Startups reference content — Activate FAQ, credits guide, programs, partner offers, sample architectures, and hundreds of learn articles spanning generative AI, cloud architecture, cost optimization, security, fundraising, go-to-market, and real-world startup case studies. Use when the user asks factual questions about AWS Activate (eligibility, credits, programs, providers), wants a sample architecture or solution guide, or needs an AWS-curated learn article on a specific startup topic. For copy-paste AI prompts (RAG chatbot, MVP scaffold, security baseline, GPU quota, etc.), see the prompt-library-for-startups skill. Do not use for: account-specific lookups (credits balance, Activate membership status, application status), real-time event listings beyond the events stub, or content not present in the bundled `references\u002F` tree.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2164,2165,2168,2171],{"name":24,"slug":25,"type":16},{"name":2166,"slug":2167,"type":16},"Cloud","cloud",{"name":2169,"slug":2170,"type":16},"Documentation","documentation",{"name":2172,"slug":2173,"type":16},"Research","research","2026-07-25T05:32:19.312255",{"slug":2176,"name":2176,"fn":2177,"description":2178,"org":2179,"tags":2180,"stars":26,"repoUrl":27,"updatedAt":2192},"llm-to-bedrock","migrate LLM calls to Amazon Bedrock","Use when the user wants to migrate code that calls OpenAI, Gemini\u002FGoogle AI, or the Anthropic API to Amazon Bedrock — a pure model\u002FSDK rewrite. End-to-end: assesses the codebase, then rewrites SDK calls, evaluates output quality against Bedrock, and delivers a ready-to-merge git branch. Not for: agent runtime selection, agentic architecture decisions, or agent migration planning — use agent-advisor for those. Not for standalone Bedrock cost estimates or infrastructure-only migration. The Assess phase is handled by this plugin's own gcp-to-aws skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2181,2182,2185,2188,2189],{"name":24,"slug":25,"type":16},{"name":2183,"slug":2184,"type":16},"Gemini","gemini",{"name":2186,"slug":2187,"type":16},"LLM","llm",{"name":2142,"slug":2143,"type":16},{"name":2190,"slug":2191,"type":16},"OpenAI","openai","2026-08-14T04:51:58.393797",{"slug":2194,"name":2194,"fn":2195,"description":2196,"org":2197,"tags":2198,"stars":26,"repoUrl":27,"updatedAt":2205},"prompt-library-for-startups","provide AI coding prompts for startups","AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly detection, GPU quota requests, EKS deployment, Well-Architected review, etc.) plus downloadable installable agents (Multi-Account Transition Advisor, Bill Shock Preventer, Service Quota Agent, Bedrock Model Availability Agent, AWS DB Advisor). Use when the user asks for a prompt to do X on AWS, wants an installable agent for multi-account \u002F cost monitoring \u002F quota management \u002F Bedrock model availability \u002F database selection, or asks how to use AWS prompts. For migration intent (GCP to AWS, OpenAI\u002FGemini to Bedrock), route to the migration skills in this plugin (`gcp-to-aws`, `heroku-to-aws`, `llm-to-bedrock`). Do not use for: factual AWS Activate \u002F programs \u002F credits questions, learn articles, sample architectures, or for prompts that are not in the bundled `references\u002Fprompt-library\u002F` tree.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2199,2200,2203,2204],{"name":24,"slug":25,"type":16},{"name":2201,"slug":2202,"type":16},"Coding","coding",{"name":18,"slug":19,"type":16},{"name":2186,"slug":2187,"type":16},"2026-08-14T04:27:16.118669",{"items":2207,"total":2383},[2208,2227,2248,2258,2269,2282,2292,2302,2323,2338,2353,2368],{"slug":2209,"name":2209,"fn":2210,"description":2211,"org":2212,"tags":2213,"stars":2224,"repoUrl":2225,"updatedAt":2226},"agentcore-investigation","investigate Bedrock AgentCore runtime sessions","Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session\u002Ftrace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2214,2215,2218,2221],{"name":24,"slug":25,"type":16},{"name":2216,"slug":2217,"type":16},"Debugging","debugging",{"name":2219,"slug":2220,"type":16},"Logs","logs",{"name":2222,"slug":2223,"type":16},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":2228,"name":2229,"fn":2230,"description":2231,"org":2232,"tags":2233,"stars":2224,"repoUrl":2225,"updatedAt":2247},"amazon-aurora-dsql","amazon aurora dsql","build applications with Aurora DSQL","Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django\u002FHibernate\u002FRails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2234,2237,2238,2241,2244],{"name":2235,"slug":2236,"type":16},"Aurora","aurora",{"name":24,"slug":25,"type":16},{"name":2239,"slug":2240,"type":16},"Database","database",{"name":2242,"slug":2243,"type":16},"Serverless","serverless",{"name":2245,"slug":2246,"type":16},"SQL","sql","2026-08-04T05:35:10.770847",{"slug":2249,"name":2250,"fn":2230,"description":2231,"org":2251,"tags":2252,"stars":2224,"repoUrl":2225,"updatedAt":2257},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2253,2254,2255,2256],{"name":24,"slug":25,"type":16},{"name":2239,"slug":2240,"type":16},{"name":2242,"slug":2243,"type":16},{"name":2245,"slug":2246,"type":16},"2026-08-04T05:35:05.694395",{"slug":2259,"name":2260,"fn":2230,"description":2231,"org":2261,"tags":2262,"stars":2224,"repoUrl":2225,"updatedAt":2268},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2263,2264,2265,2266,2267],{"name":24,"slug":25,"type":16},{"name":2239,"slug":2240,"type":16},{"name":2142,"slug":2143,"type":16},{"name":2242,"slug":2243,"type":16},{"name":2245,"slug":2246,"type":16},"2026-08-04T05:35:08.749669",{"slug":2270,"name":2271,"fn":2230,"description":2231,"org":2272,"tags":2273,"stars":2224,"repoUrl":2225,"updatedAt":2281},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2274,2275,2276,2279,2280],{"name":24,"slug":25,"type":16},{"name":2239,"slug":2240,"type":16},{"name":2277,"slug":2278,"type":16},"PostgreSQL","postgresql",{"name":2242,"slug":2243,"type":16},{"name":2245,"slug":2246,"type":16},"2026-08-04T05:35:06.713102",{"slug":2283,"name":2284,"fn":2230,"description":2231,"org":2285,"tags":2286,"stars":2224,"repoUrl":2225,"updatedAt":2291},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2287,2288,2289,2290],{"name":24,"slug":25,"type":16},{"name":2239,"slug":2240,"type":16},{"name":2242,"slug":2243,"type":16},{"name":2245,"slug":2246,"type":16},"2026-08-04T05:35:10.086942",{"slug":2293,"name":2293,"fn":2230,"description":2231,"org":2294,"tags":2295,"stars":2224,"repoUrl":2225,"updatedAt":2301},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2296,2297,2298,2299,2300],{"name":24,"slug":25,"type":16},{"name":2239,"slug":2240,"type":16},{"name":2142,"slug":2143,"type":16},{"name":2242,"slug":2243,"type":16},{"name":2245,"slug":2246,"type":16},"2026-08-04T05:35:07.751779",{"slug":2303,"name":2303,"fn":2304,"description":2305,"org":2306,"tags":2307,"stars":2320,"repoUrl":2321,"updatedAt":2322},"cost-efficiency-analyzer","analyze cost efficiency and expenses","Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for \"are we spending too much\", \"cost breakdown\", \"expense analysis\", or \"how efficient are our operations\". NOT for revenue or top-line analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2308,2311,2314,2317],{"name":2309,"slug":2310,"type":16},"Accounting","accounting",{"name":2312,"slug":2313,"type":16},"Analytics","analytics",{"name":2315,"slug":2316,"type":16},"Cost Optimization","cost-optimization",{"name":2318,"slug":2319,"type":16},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":2324,"name":2324,"fn":2325,"description":2326,"org":2327,"tags":2328,"stars":2320,"repoUrl":2321,"updatedAt":2337},"executive-financial-briefing","generate executive financial briefings","Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or \"how is the business doing\". Covers the full P&L picture in one page. Also use for \"give me the highlights\", \"what do I need to know\", or \"quick financial update\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2329,2330,2331,2334],{"name":24,"slug":25,"type":16},{"name":2318,"slug":2319,"type":16},{"name":2332,"slug":2333,"type":16},"Management","management",{"name":2335,"slug":2336,"type":16},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":2339,"name":2339,"fn":2340,"description":2341,"org":2342,"tags":2343,"stars":2320,"repoUrl":2321,"updatedAt":2352},"multi-quarter-trend-analysis","analyze multi-quarter financial trends","Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for \"how are we trending\", \"show me the trend\", \"track performance over time\", \"quarter over quarter comparison across all quarters\", or any multi-period longitudinal analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2344,2345,2346,2349],{"name":2312,"slug":2313,"type":16},{"name":2318,"slug":2319,"type":16},{"name":2347,"slug":2348,"type":16},"Financial Statements","financial-statements",{"name":2350,"slug":2351,"type":16},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":2354,"name":2354,"fn":2355,"description":2356,"org":2357,"tags":2358,"stars":2320,"repoUrl":2321,"updatedAt":2367},"pdf","process and manipulate PDF documents","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2359,2362,2365],{"name":2360,"slug":2361,"type":16},"Automation","automation",{"name":2363,"slug":2364,"type":16},"Documents","documents",{"name":2366,"slug":2354,"type":16},"PDF","2026-07-12T08:41:44.135656",{"slug":2369,"name":2369,"fn":2370,"description":2371,"org":2372,"tags":2373,"stars":2320,"repoUrl":2321,"updatedAt":2382},"quarterly-kpi-calculator","calculate quarterly financial KPIs","Calculates quarterly financial KPIs from P&L data. P&L figures can be provided directly by the user or fetched from the financial data MCP server. Use when the user wants KPI calculations such as Gross Margin %, EBITDA Margin %, Operating Expense Ratio, or Revenue Growth % QoQ. Also use for quarterly performance review, P&L analysis, or interpreting financial ratios against benchmarks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2374,2375,2378,2379],{"name":2309,"slug":2310,"type":16},{"name":2376,"slug":2377,"type":16},"Data Analysis","data-analysis",{"name":2318,"slug":2319,"type":16},{"name":2380,"slug":2381,"type":16},"KPI","kpi","2026-07-12T08:39:59.54971",125]