[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-heroku-to-aws":3,"mdc-5i1m1o-key":37,"related-org-aws-labs-heroku-to-aws":1332,"related-repo-aws-labs-heroku-to-aws":1510},{"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},"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},"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},"Migration","migration","tag",{"name":18,"slug":19,"type":16},"Infrastructure","infrastructure",{"name":21,"slug":22,"type":16},"AWS","aws",{"name":24,"slug":25,"type":16},"Heroku","heroku",14,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fstartups","2026-08-14T04:52:09.216805",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\u002Fheroku-to-aws","---\nname: heroku-to-aws\ndescription: \"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.\"\n---\n\n# Heroku-to-AWS Migration Skill\n\n## Philosophy\n\n- **Full platform exit by default**: Heroku is in sustaining engineering (KTLO) — stability and support only, no new investment. Enterprise contracts are no longer sold to new customers. This skill assumes complete departure from Heroku (compute, data, and add-ons) within a user-defined window. Do not recommend indefinite continued use of Heroku.\n- **PaaS-to-PaaS by default, recommendation-shaped**: Elastic Beanstalk (Docker platform, AL2023) is the default compute target because it preserves Heroku's managed platform model (source deployment, platform-managed environments, and lower operational burden than direct container orchestration). Clarify presents a per-formation compute recommendation before asking for confirmation. Fargate remains the override for direct container control and is used automatically for horizontally scaled non-web processes that EB SingleInstance cannot preserve; EKS remains the override for teams with Kubernetes expertise. ECS Express Mode may be mentioned only as a forward-look for the Fargate override path, not as a replacement for the EB default. Do not recommend AWS App Runner (no longer accepting new customers as of April 2026).\n- **Interim cutover is bounded**: If a user chooses data-first migration (database on AWS, app temporarily on Heroku), treat this as a bounded phase (weeks, not quarters). Require a target exit date and surface KTLO platform risk warnings.\n- **Re-platform by default**: Select AWS services that match Heroku workload types (e.g., Dynos → Elastic Beanstalk, Heroku Postgres → RDS\u002FAurora, Heroku Redis → ElastiCache, Kafka → MSK).\n- **Dev sizing unless specified**: Default to development-tier capacity (e.g., db.t4g.micro, single AZ). Upgrade only on user direction.\n- **No human one-time migration costs**: Do not present human labor, professional services, or people-time work as dollar estimates or \"one-time migration cost\" budget categories. Vendor charges grounded in data (for example Heroku invoice line items in the infra estimate when billing exists) are allowed.\n- **Live-first discovery, read-only and consent-gated**: The user's authenticated Heroku CLI is a first-class discovery source — most startups have no `heroku_*` Terraform, and the account is authoritative for what actually runs. Live capture is strictly read-only (an exact-command whitelist of list\u002Finfo commands), requires explicit consent, never captures config var values (key names only), and never extracts the API token. Terraform files (`.tf` with `heroku_*` resources) and repo artifacts (Procfile, app.json) remain fully supported; when both live and Terraform data exist, live wins for current state, Terraform supplements structure and provenance, and disagreements are surfaced as drift — never silently resolved.\n- **Flat resource model**: Heroku resources are organized per-app without dependency graphs or clustering. No topological sorting, typed edges, or cluster formation logic. Resources are processed as a flat list in input order.\n- **Deterministic mappings**: Core services use fixed lookup tables (Dyno Type Table, Postgres Plan Table, Redis Plan Table, Kafka Plan Table). Common add-ons use the Fast-Path Table. Unknown add-ons hit the specialist gate.\n- **DMS has Heroku constraints**: AWS DMS cannot perform continuous replication (CDC) with Heroku Postgres because Heroku does not grant the REPLICATION role. DMS is for one-time bulk migration with a cutover window only. The skill must surface this constraint when DMS is selected.\n- **What-if after Estimate**: After costs are computed, SAs can enter an optional what-if workshop sidebar (`references\u002Fphases\u002Fworkshop\u002Fworkshop.md`) to change region, HA, compute target, or CPU architecture (x86 vs Graviton), refresh Design + Estimate, and compare up to 5 priced scenarios — without re-running Discover. Region dollar deltas need awspricing MCP; without it, rates stay us-east-1-cache-based. Workshop arch defaults to **x86_64** here (EB tables historically x86-first).\n\n---\n\n## Definitions\n\n- **\"Load\"** = Read the file using the Read tool and follow its instructions. Do not summarize or skip sections.\n- **`$MIGRATION_DIR`** = The run-specific directory under `.migration\u002F` (e.g., `.migration\u002F0315-1030\u002F`). Set during Phase 1 (Discover).\n\n---\n\n## Phase Structure (frontmatter)\n\nPhase and unit files carry a YAML frontmatter block that declares how the phase is\ncomposed — its inputs, the fragments it runs, the assembler that combines them,\nwhat it produces, its gates, and what it requires\u002Fadvances-to. The DSL interpreter\ncontract is the vendored `references\u002Fvendored\u002Fdsl\u002FINTERPRETER.md`: it defines every\nfrontmatter key, the fragment\u002Fassembler model, and the interpreter loop. **Load it\nfirst** (once, at the start of a migration), then execute a phase file's prose\nbody. Elsewhere in this skill, `INTERPRETER.md` (without a path) refers to this\nsame loaded contract.\n\nFrontmatter is being introduced phase-by-phase; a phase file without it runs from\nits prose as before.\n\n---\n\n## Context Loading Rules\n\nEach phase loads reference files on demand. To keep per-turn context manageable and prevent instruction-following degradation:\n\n- **Budget:** Each phase should load no more than ~800 lines of instructions (excluding user artifacts like JSON profiles and MCP tool results).\n- **Conditional loading:** Reference files with trigger conditions MUST NOT be loaded unless the condition is met. Do not speculatively load files.\n- **No duplication:** Mapping tables, pricing data, and shared warnings exist in one canonical file. Other files reference them; they do not copy them inline.\n- **Progressive depth:** Phase orchestrators (`design.md`, `generate.md`) contain short routing logic that points to detailed sub-files. Load the sub-file only when its path is selected.\n\nEach phase declares its own conditional reference\u002Fknowledge loads in frontmatter (a fragment `_trigger` or a `_knowledge` entry's `_when`); do not maintain a separate load-condition table here.\n\nWhen adding new reference files, verify the phase's total loaded instructions remain under budget. If a new file would exceed ~800 lines when combined with other loaded refs, split it or make it conditional.\n\n---\n\n## Execution\n\nThis skill is driven by the interpreter loop in `INTERPRETER.md` (§ The interpreter\nloop): it reads `.phase-status.json`, determines the current phase, runs each\nphase's `_preconditions` \u002F fragments \u002F `_assemble` \u002F `_postconditions`, advances on\n`HANDOFF_OK` via `_advances_to`, and validates state. The phase set, ordering, and\ngates are all derived from the phase files' frontmatter and `INTERPRETER.md` — they\nare not restated here.\n\n**Cold start (entry phase).** On a cold start — no `.migration\u002F` run with a\n`.phase-status.json` yet — begin at `references\u002Fphases\u002Fdiscover\u002Fdiscover.md`, this\nskill's entry phase (the one carrying `_init: true`). The interpreter loads THIS\nphase directly; it does not scan every phase's frontmatter to discover the root.\nAll subsequent phases are reached by following each phase's `_advances_to`. On a\nwarm start, `current_phase` in `.phase-status.json` is authoritative **except**\nwhen deferred-advance sidebar resume applies (`INTERPRETER.md` § The\ninterpreter loop step 2 — Estimate completed + `workshop` pending\u002Fin_progress\nmust not re-run Estimate).\n\n**Clarify is mandatory (heroku policy).** Do not skip Clarify or jump straight to\nDesign, Estimate, or Generate even if the user asks — there is no exception for\n\"quick\" or \"obvious\" migrations. A `preferences.json` that was not produced by an\nactual Clarify run does not count. If asked to skip, refuse briefly and run\nClarify.\n\n---\n\n## State Management\n\nMigration state lives in `$MIGRATION_DIR` (`.migration\u002F[MMDD-HHMM]\u002F`), created on\nthe first phase and persisted across invocations. The state file is\n`.phase-status.json`; its shape is defined by\n`references\u002Fvendored\u002Fstate\u002Fphase-status.schema.json`, and how it is created, validated, and\nupdated across the lifecycle is defined in `INTERPRETER.md` § The interpreter loop.\nThe `.migration\u002F` directory is protected by a `.gitignore` created at init.\n\n---\n\n## MCP Servers\n\n**awspricing** (for cost estimation):\n\n- Provides `get_pricing`, `get_pricing_service_codes`, `get_pricing_service_attributes` tools\n- Only needed during Estimate phase. Discover and Design do not require it.\n- Primary pricing source: `references\u002Fvendored\u002Fpricing\u002Faws-infra-pricing.json` (cached AWS infrastructure rates, ±5-10% for infrastructure). MCP is secondary — used only for services not found in the pricing file.\n\n---\n\n## Files in This Skill\n\n```\nheroku-to-aws\u002F\n├── SKILL.md ← You are here (skill entry point)\n│\n├── references\u002F\n│ ├── phases\u002F\n│ │ ├── discover\u002F\n│ │ │ ├── discover.md # Phase 1: Discover orchestrator\n│ │ │ ├── discover-terraform.md # Terraform discovery\n│ │ │ ├── discover-live-capture.md # Live CLI capture (main-window pre-work, consent-gated)\n│ │ │ ├── discover-live.md # Live discovery fragment (parses live-capture\u002F)\n│ │ │ └── discover-billing.md # Billing data parsing\n│ │ ├── clarify\u002F\n│ │ │ └── clarify.md # Phase 2: Adaptive questions (12–15, batched ≤5)\n│ │ ├── design\u002F\n│ │ │ └── design.md # Phase 3: Design orchestrator (flat single-pass mapping)\n│ │ ├── estimate\u002F\n│ │ │ └── estimate.md # Phase 4: Cost projection\n│ │ ├── workshop\u002F\n│ │ │ ├── workshop.md # Sidebar: optional post-Estimate what-if\n│ │ │ ├── workshop-sheet.md # Assumption sheet knobs\n│ │ │ ├── workshop-refresh.md # Patch prefs → Design → Estimate → snapshot\n│ │ │ ├── workshop-compare.md # Side-by-side scenarios\n│ │ │ └── workshop-assemble.md # Resolve sidebar → return to Generate\n│ │ ├── generate\u002F\n│ │ │ ├── generate.md # Phase 5: Generate orchestrator\n│ │ │ ├── generate-terraform.md # Terraform configurations\n│ │ │ ├── generate-docs.md # MIGRATION_GUIDE.md + README.md\n│ │ │ ├── generate-report.md # migration-report.html (stakeholder + scenarios)\n│ │ │ └── generate-eks.md # EKS manifests when design has EKS\n│ │ └── feedback\u002F\n│ │ └── feedback.md # Phase 6: Feedback collection (reuses shared)\n│ │\n│ └── shared\u002F # heroku-to-aws's own shared references\n│ ├── README.md # what lives here + pointers to plugin-neutral shared data\n│ ├── heroku-pricing-cache.md # Heroku plan pricing (source-side baseline)\n│ ├── schema-discover-heroku.md # heroku-resource-inventory.json schema\n│ └── schema-workshop-scenarios.md # scenarios\u002F + preferences.workshop contract\n│\n├── knowledge\u002Fdesign\u002F # design lookup DATA (pure data, referenced by\n│ │ # design.md _knowledge, gated per _when)\n│ ├── dyno-eb-sizing.json # Dyno type → Elastic Beanstalk EC2 instance type\n│ ├── dyno-fargate-sizing.json # Dyno type → Fargate CPU\u002Fmemory\n│ ├── eks-pod-sizing.json # Dyno type → EKS pod sizing + node selection\n│ ├── postgres-rds-sizing.json # Postgres plan → RDS\u002FAurora sizing\n│ ├── redis-elasticache-sizing.json # Redis plan → ElastiCache sizing\n│ ├── kafka-msk-sizing.json # Kafka plan → MSK sizing\n│ └── fast-path-addons.json # Add-on → AWS deterministic mappings (13+ entries)\n```\n\n| Condition | Action |\n| -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `.phase-status.json` missing phase gate | Stop. Output: \"Cannot enter Phase X: Phase Y-1 not completed. Start from Phase Y or resume Phase Y-1.\" |\n| awspricing unavailable after 3 attempts | Display user warning about ±5-10% accuracy. Use `references\u002Fvendored\u002Fpricing\u002Faws-infra-pricing.json`. Add `pricing_source: \"cached_fallback\"` to `estimation-infra.json`. |\n| User skips questions or says \"use defaults for the rest\" | Apply documented defaults for remaining questions. Phase 2 completes either way. |\n| Dyno type not in selected compute sizing table | Reject mapping for that formation. Output: \"Unsupported dyno type: {type}. Cannot map to target compute service.\" |\n| Add-on not in Fast-Path Table | Mark as \"Deferred — specialist engagement\". No automated mapping produced. |\n\n## Defaults\n\n- **IaC output**: Terraform configurations, migration scripts, and documentation\n- **Region**: `us-east-1` (unless user specifies otherwise)\n- **Sizing**: Development tier (e.g., `db.t4g.micro` for databases, 0.5 CPU for Fargate)\n- **Migration mode**: Adapts based on available inputs (live CLI discovery recommended, Terraform supported, Procfile\u002Fapp.json supplementary, billing optional)\n- **Cost currency**: USD\n- **Timeline assumption**: 2-16 weeks depending on migration complexity — small (2-6 weeks), medium (6-12 weeks), large (12-18 weeks). Complexity tiers are classified per `references\u002Fvendored\u002Festimate\u002Fcomplexity-tiers.json`.\n\n## Feedback & Sharing Sidebars\n\nThe interpreter loop (`INTERPRETER.md` § The interpreter loop) drives phase\nsequencing, gates, and state. This section defines only the heroku-specific\nsidebar orchestration: WHERE the optional `workshop` and `feedback`\nsidebars are offered (placement is orchestration prose, not part of the phase\ncontract). Both are `_kind: sidebar` — off-backbone, trigger-entered, never\n`current_phase`.\n\n> **Plan-share links are GATED OFF.** The share landing page\n> (`https:\u002F\u002Faws.amazon.com\u002Fstartups\u002Fmigrate\u002Fconnect`) is not yet live (404). Do\n> NOT offer, generate, or present a share link at any sidebar. The share-link\n> spec is preserved in `references\u002Fphases\u002Ffeedback\u002Ffeedback-collect.md` Step 3\n> (itself gated) for when the page ships; restoring the share prompts here is the\n> un-gating change.\n\n- **After Discover**: No prompt. Proceed directly to Clarify.\n\n- **After Estimate**: First offer the what-if workshop sidebar per\n `estimate-assemble.md` (Enter workshop \u002F Proceed toward Generate). Outer\n Estimate keeps `current_phase: estimate` until workshop is resolved (entered\n then exited via `workshop-assemble.md`, or declined). If the user enters\n workshop, follow `references\u002Fphases\u002Fworkshop\u002Fworkshop.md`. Then, if\n `phases.feedback` is `\"pending\"`:\n\n ```\n Would you like to share quick feedback? (5 optional questions +\n anonymized usage data — never resource names, file paths, or\n account IDs)\n\n [A] Yes, share feedback\n [B] No thanks, continue to Generate\n ```\n\n - If user picks **A** → Load `references\u002Fphases\u002Ffeedback\u002Ffeedback.md`, execute it. Set `phases.feedback` to `\"completed\"`. Continue to Generate.\n - If user picks **B** → Set `phases.feedback` to `\"completed\"`. Continue to Generate.\n\n- **Workshop resume (mandatory):** If `current_phase == \"estimate\"` AND\n `phases.estimate == \"completed\"` AND `phases.workshop` is `\"pending\"` or\n `\"in_progress\"`, **do not recompute Estimate**. If `\"pending\"`, re-present the\n post-Estimate workshop offer from `estimate-assemble.md`. If `\"in_progress\"`,\n load `references\u002Fphases\u002Fworkshop\u002Fworkshop.md`. Generate must wait until\n `phases.workshop == \"completed\"` (entered+exited or declined).\n\n- **Warm start \u002F explicit what-if**: If the user says \"what if\", \"reprice\",\n \"workshop mode\", or \"compare scenarios\" and Estimate artifacts already exist,\n load `references\u002Fphases\u002Fworkshop\u002Fworkshop.md` directly (respect Generate\n `_re_entry_guard` when Terraform was already produced). Knobs on the pilot\n sheet: region, HA, compute target, cost optimization, CPU architecture\n (x86 vs Graviton). There is no traffic-multiplier knob in v1.\n\n- **After Generate**: No prompt. If `phases.feedback` is still `\"pending\"`, set it to `\"completed\"` and mark the migration complete.\n\n**Critical constraint**: Follow each phase reference file's workflow exactly. If unable to complete a step, stop and report the specific issue. Do not fabricate or infer data.\n",{"data":38,"body":39},{"name":4,"description":6},{"type":40,"children":41},"root",[42,51,58,213,217,223,266,269,275,304,309,312,318,323,382,411,416,419,425,492,576,594,597,603,660,663,669,679,727,730,736,748,869,875,961,967,1008,1038,1322],{"type":43,"tag":44,"props":45,"children":47},"element","h1",{"id":46},"heroku-to-aws-migration-skill",[48],{"type":49,"value":50},"text","Heroku-to-AWS Migration Skill",{"type":43,"tag":52,"props":53,"children":55},"h2",{"id":54},"philosophy",[56],{"type":49,"value":57},"Philosophy",{"type":43,"tag":59,"props":60,"children":61},"ul",{},[62,74,84,94,104,114,124,158,168,178,188],{"type":43,"tag":63,"props":64,"children":65},"li",{},[66,72],{"type":43,"tag":67,"props":68,"children":69},"strong",{},[70],{"type":49,"value":71},"Full platform exit by default",{"type":49,"value":73},": Heroku is in sustaining engineering (KTLO) — stability and support only, no new investment. Enterprise contracts are no longer sold to new customers. This skill assumes complete departure from Heroku (compute, data, and add-ons) within a user-defined window. Do not recommend indefinite continued use of Heroku.",{"type":43,"tag":63,"props":75,"children":76},{},[77,82],{"type":43,"tag":67,"props":78,"children":79},{},[80],{"type":49,"value":81},"PaaS-to-PaaS by default, recommendation-shaped",{"type":49,"value":83},": Elastic Beanstalk (Docker platform, AL2023) is the default compute target because it preserves Heroku's managed platform model (source deployment, platform-managed environments, and lower operational burden than direct container orchestration). Clarify presents a per-formation compute recommendation before asking for confirmation. Fargate remains the override for direct container control and is used automatically for horizontally scaled non-web processes that EB SingleInstance cannot preserve; EKS remains the override for teams with Kubernetes expertise. ECS Express Mode may be mentioned only as a forward-look for the Fargate override path, not as a replacement for the EB default. Do not recommend AWS App Runner (no longer accepting new customers as of April 2026).",{"type":43,"tag":63,"props":85,"children":86},{},[87,92],{"type":43,"tag":67,"props":88,"children":89},{},[90],{"type":49,"value":91},"Interim cutover is bounded",{"type":49,"value":93},": If a user chooses data-first migration (database on AWS, app temporarily on Heroku), treat this as a bounded phase (weeks, not quarters). Require a target exit date and surface KTLO platform risk warnings.",{"type":43,"tag":63,"props":95,"children":96},{},[97,102],{"type":43,"tag":67,"props":98,"children":99},{},[100],{"type":49,"value":101},"Re-platform by default",{"type":49,"value":103},": Select AWS services that match Heroku workload types (e.g., Dynos → Elastic Beanstalk, Heroku Postgres → RDS\u002FAurora, Heroku Redis → ElastiCache, Kafka → MSK).",{"type":43,"tag":63,"props":105,"children":106},{},[107,112],{"type":43,"tag":67,"props":108,"children":109},{},[110],{"type":49,"value":111},"Dev sizing unless specified",{"type":49,"value":113},": Default to development-tier capacity (e.g., db.t4g.micro, single AZ). Upgrade only on user direction.",{"type":43,"tag":63,"props":115,"children":116},{},[117,122],{"type":43,"tag":67,"props":118,"children":119},{},[120],{"type":49,"value":121},"No human one-time migration costs",{"type":49,"value":123},": Do not present human labor, professional services, or people-time work as dollar estimates or \"one-time migration cost\" budget categories. Vendor charges grounded in data (for example Heroku invoice line items in the infra estimate when billing exists) are allowed.",{"type":43,"tag":63,"props":125,"children":126},{},[127,132,134,141,143,149,151,156],{"type":43,"tag":67,"props":128,"children":129},{},[130],{"type":49,"value":131},"Live-first discovery, read-only and consent-gated",{"type":49,"value":133},": The user's authenticated Heroku CLI is a first-class discovery source — most startups have no ",{"type":43,"tag":135,"props":136,"children":138},"code",{"className":137},[],[139],{"type":49,"value":140},"heroku_*",{"type":49,"value":142}," Terraform, and the account is authoritative for what actually runs. Live capture is strictly read-only (an exact-command whitelist of list\u002Finfo commands), requires explicit consent, never captures config var values (key names only), and never extracts the API token. Terraform files (",{"type":43,"tag":135,"props":144,"children":146},{"className":145},[],[147],{"type":49,"value":148},".tf",{"type":49,"value":150}," with ",{"type":43,"tag":135,"props":152,"children":154},{"className":153},[],[155],{"type":49,"value":140},{"type":49,"value":157}," resources) and repo artifacts (Procfile, app.json) remain fully supported; when both live and Terraform data exist, live wins for current state, Terraform supplements structure and provenance, and disagreements are surfaced as drift — never silently resolved.",{"type":43,"tag":63,"props":159,"children":160},{},[161,166],{"type":43,"tag":67,"props":162,"children":163},{},[164],{"type":49,"value":165},"Flat resource model",{"type":49,"value":167},": Heroku resources are organized per-app without dependency graphs or clustering. No topological sorting, typed edges, or cluster formation logic. Resources are processed as a flat list in input order.",{"type":43,"tag":63,"props":169,"children":170},{},[171,176],{"type":43,"tag":67,"props":172,"children":173},{},[174],{"type":49,"value":175},"Deterministic mappings",{"type":49,"value":177},": Core services use fixed lookup tables (Dyno Type Table, Postgres Plan Table, Redis Plan Table, Kafka Plan Table). Common add-ons use the Fast-Path Table. Unknown add-ons hit the specialist gate.",{"type":43,"tag":63,"props":179,"children":180},{},[181,186],{"type":43,"tag":67,"props":182,"children":183},{},[184],{"type":49,"value":185},"DMS has Heroku constraints",{"type":49,"value":187},": AWS DMS cannot perform continuous replication (CDC) with Heroku Postgres because Heroku does not grant the REPLICATION role. DMS is for one-time bulk migration with a cutover window only. The skill must surface this constraint when DMS is selected.",{"type":43,"tag":63,"props":189,"children":190},{},[191,196,198,204,206,211],{"type":43,"tag":67,"props":192,"children":193},{},[194],{"type":49,"value":195},"What-if after Estimate",{"type":49,"value":197},": After costs are computed, SAs can enter an optional what-if workshop sidebar (",{"type":43,"tag":135,"props":199,"children":201},{"className":200},[],[202],{"type":49,"value":203},"references\u002Fphases\u002Fworkshop\u002Fworkshop.md",{"type":49,"value":205},") to change region, HA, compute target, or CPU architecture (x86 vs Graviton), refresh Design + Estimate, and compare up to 5 priced scenarios — without re-running Discover. Region dollar deltas need awspricing MCP; without it, rates stay us-east-1-cache-based. Workshop arch defaults to ",{"type":43,"tag":67,"props":207,"children":208},{},[209],{"type":49,"value":210},"x86_64",{"type":49,"value":212}," here (EB tables historically x86-first).",{"type":43,"tag":214,"props":215,"children":216},"hr",{},[],{"type":43,"tag":52,"props":218,"children":220},{"id":219},"definitions",[221],{"type":49,"value":222},"Definitions",{"type":43,"tag":59,"props":224,"children":225},{},[226,236],{"type":43,"tag":63,"props":227,"children":228},{},[229,234],{"type":43,"tag":67,"props":230,"children":231},{},[232],{"type":49,"value":233},"\"Load\"",{"type":49,"value":235}," = Read the file using the Read tool and follow its instructions. Do not summarize or skip sections.",{"type":43,"tag":63,"props":237,"children":238},{},[239,248,250,256,258,264],{"type":43,"tag":67,"props":240,"children":241},{},[242],{"type":43,"tag":135,"props":243,"children":245},{"className":244},[],[246],{"type":49,"value":247},"$MIGRATION_DIR",{"type":49,"value":249}," = The run-specific directory under ",{"type":43,"tag":135,"props":251,"children":253},{"className":252},[],[254],{"type":49,"value":255},".migration\u002F",{"type":49,"value":257}," (e.g., ",{"type":43,"tag":135,"props":259,"children":261},{"className":260},[],[262],{"type":49,"value":263},".migration\u002F0315-1030\u002F",{"type":49,"value":265},"). Set during Phase 1 (Discover).",{"type":43,"tag":214,"props":267,"children":268},{},[],{"type":43,"tag":52,"props":270,"children":272},{"id":271},"phase-structure-frontmatter",[273],{"type":49,"value":274},"Phase Structure (frontmatter)",{"type":43,"tag":276,"props":277,"children":278},"p",{},[279,281,287,289,294,296,302],{"type":49,"value":280},"Phase and unit files carry a YAML frontmatter block that declares how the phase is\ncomposed — its inputs, the fragments it runs, the assembler that combines them,\nwhat it produces, its gates, and what it requires\u002Fadvances-to. The DSL interpreter\ncontract is the vendored ",{"type":43,"tag":135,"props":282,"children":284},{"className":283},[],[285],{"type":49,"value":286},"references\u002Fvendored\u002Fdsl\u002FINTERPRETER.md",{"type":49,"value":288},": it defines every\nfrontmatter key, the fragment\u002Fassembler model, and the interpreter loop. ",{"type":43,"tag":67,"props":290,"children":291},{},[292],{"type":49,"value":293},"Load it\nfirst",{"type":49,"value":295}," (once, at the start of a migration), then execute a phase file's prose\nbody. Elsewhere in this skill, ",{"type":43,"tag":135,"props":297,"children":299},{"className":298},[],[300],{"type":49,"value":301},"INTERPRETER.md",{"type":49,"value":303}," (without a path) refers to this\nsame loaded contract.",{"type":43,"tag":276,"props":305,"children":306},{},[307],{"type":49,"value":308},"Frontmatter is being introduced phase-by-phase; a phase file without it runs from\nits prose as before.",{"type":43,"tag":214,"props":310,"children":311},{},[],{"type":43,"tag":52,"props":313,"children":315},{"id":314},"context-loading-rules",[316],{"type":49,"value":317},"Context Loading Rules",{"type":43,"tag":276,"props":319,"children":320},{},[321],{"type":49,"value":322},"Each phase loads reference files on demand. To keep per-turn context manageable and prevent instruction-following degradation:",{"type":43,"tag":59,"props":324,"children":325},{},[326,336,346,356],{"type":43,"tag":63,"props":327,"children":328},{},[329,334],{"type":43,"tag":67,"props":330,"children":331},{},[332],{"type":49,"value":333},"Budget:",{"type":49,"value":335}," Each phase should load no more than ~800 lines of instructions (excluding user artifacts like JSON profiles and MCP tool results).",{"type":43,"tag":63,"props":337,"children":338},{},[339,344],{"type":43,"tag":67,"props":340,"children":341},{},[342],{"type":49,"value":343},"Conditional loading:",{"type":49,"value":345}," Reference files with trigger conditions MUST NOT be loaded unless the condition is met. Do not speculatively load files.",{"type":43,"tag":63,"props":347,"children":348},{},[349,354],{"type":43,"tag":67,"props":350,"children":351},{},[352],{"type":49,"value":353},"No duplication:",{"type":49,"value":355}," Mapping tables, pricing data, and shared warnings exist in one canonical file. Other files reference them; they do not copy them inline.",{"type":43,"tag":63,"props":357,"children":358},{},[359,364,366,372,374,380],{"type":43,"tag":67,"props":360,"children":361},{},[362],{"type":49,"value":363},"Progressive depth:",{"type":49,"value":365}," Phase orchestrators (",{"type":43,"tag":135,"props":367,"children":369},{"className":368},[],[370],{"type":49,"value":371},"design.md",{"type":49,"value":373},", ",{"type":43,"tag":135,"props":375,"children":377},{"className":376},[],[378],{"type":49,"value":379},"generate.md",{"type":49,"value":381},") contain short routing logic that points to detailed sub-files. Load the sub-file only when its path is selected.",{"type":43,"tag":276,"props":383,"children":384},{},[385,387,393,395,401,403,409],{"type":49,"value":386},"Each phase declares its own conditional reference\u002Fknowledge loads in frontmatter (a fragment ",{"type":43,"tag":135,"props":388,"children":390},{"className":389},[],[391],{"type":49,"value":392},"_trigger",{"type":49,"value":394}," or a ",{"type":43,"tag":135,"props":396,"children":398},{"className":397},[],[399],{"type":49,"value":400},"_knowledge",{"type":49,"value":402}," entry's ",{"type":43,"tag":135,"props":404,"children":406},{"className":405},[],[407],{"type":49,"value":408},"_when",{"type":49,"value":410},"); do not maintain a separate load-condition table here.",{"type":43,"tag":276,"props":412,"children":413},{},[414],{"type":49,"value":415},"When adding new reference files, verify the phase's total loaded instructions remain under budget. If a new file would exceed ~800 lines when combined with other loaded refs, split it or make it conditional.",{"type":43,"tag":214,"props":417,"children":418},{},[],{"type":43,"tag":52,"props":420,"children":422},{"id":421},"execution",[423],{"type":49,"value":424},"Execution",{"type":43,"tag":276,"props":426,"children":427},{},[428,430,435,437,443,445,451,453,459,461,467,469,475,477,483,485,490],{"type":49,"value":429},"This skill is driven by the interpreter loop in ",{"type":43,"tag":135,"props":431,"children":433},{"className":432},[],[434],{"type":49,"value":301},{"type":49,"value":436}," (§ The interpreter\nloop): it reads ",{"type":43,"tag":135,"props":438,"children":440},{"className":439},[],[441],{"type":49,"value":442},".phase-status.json",{"type":49,"value":444},", determines the current phase, runs each\nphase's ",{"type":43,"tag":135,"props":446,"children":448},{"className":447},[],[449],{"type":49,"value":450},"_preconditions",{"type":49,"value":452}," \u002F fragments \u002F ",{"type":43,"tag":135,"props":454,"children":456},{"className":455},[],[457],{"type":49,"value":458},"_assemble",{"type":49,"value":460}," \u002F ",{"type":43,"tag":135,"props":462,"children":464},{"className":463},[],[465],{"type":49,"value":466},"_postconditions",{"type":49,"value":468},", advances on\n",{"type":43,"tag":135,"props":470,"children":472},{"className":471},[],[473],{"type":49,"value":474},"HANDOFF_OK",{"type":49,"value":476}," via ",{"type":43,"tag":135,"props":478,"children":480},{"className":479},[],[481],{"type":49,"value":482},"_advances_to",{"type":49,"value":484},", and validates state. The phase set, ordering, and\ngates are all derived from the phase files' frontmatter and ",{"type":43,"tag":135,"props":486,"children":488},{"className":487},[],[489],{"type":49,"value":301},{"type":49,"value":491}," — they\nare not restated here.",{"type":43,"tag":276,"props":493,"children":494},{},[495,500,502,507,509,514,516,522,524,530,532,537,539,545,547,552,554,559,561,566,568,574],{"type":43,"tag":67,"props":496,"children":497},{},[498],{"type":49,"value":499},"Cold start (entry phase).",{"type":49,"value":501}," On a cold start — no ",{"type":43,"tag":135,"props":503,"children":505},{"className":504},[],[506],{"type":49,"value":255},{"type":49,"value":508}," run with a\n",{"type":43,"tag":135,"props":510,"children":512},{"className":511},[],[513],{"type":49,"value":442},{"type":49,"value":515}," yet — begin at ",{"type":43,"tag":135,"props":517,"children":519},{"className":518},[],[520],{"type":49,"value":521},"references\u002Fphases\u002Fdiscover\u002Fdiscover.md",{"type":49,"value":523},", this\nskill's entry phase (the one carrying ",{"type":43,"tag":135,"props":525,"children":527},{"className":526},[],[528],{"type":49,"value":529},"_init: true",{"type":49,"value":531},"). The interpreter loads THIS\nphase directly; it does not scan every phase's frontmatter to discover the root.\nAll subsequent phases are reached by following each phase's ",{"type":43,"tag":135,"props":533,"children":535},{"className":534},[],[536],{"type":49,"value":482},{"type":49,"value":538},". On a\nwarm start, ",{"type":43,"tag":135,"props":540,"children":542},{"className":541},[],[543],{"type":49,"value":544},"current_phase",{"type":49,"value":546}," in ",{"type":43,"tag":135,"props":548,"children":550},{"className":549},[],[551],{"type":49,"value":442},{"type":49,"value":553}," is authoritative ",{"type":43,"tag":67,"props":555,"children":556},{},[557],{"type":49,"value":558},"except",{"type":49,"value":560},"\nwhen deferred-advance sidebar resume applies (",{"type":43,"tag":135,"props":562,"children":564},{"className":563},[],[565],{"type":49,"value":301},{"type":49,"value":567}," § The\ninterpreter loop step 2 — Estimate completed + ",{"type":43,"tag":135,"props":569,"children":571},{"className":570},[],[572],{"type":49,"value":573},"workshop",{"type":49,"value":575}," pending\u002Fin_progress\nmust not re-run Estimate).",{"type":43,"tag":276,"props":577,"children":578},{},[579,584,586,592],{"type":43,"tag":67,"props":580,"children":581},{},[582],{"type":49,"value":583},"Clarify is mandatory (heroku policy).",{"type":49,"value":585}," Do not skip Clarify or jump straight to\nDesign, Estimate, or Generate even if the user asks — there is no exception for\n\"quick\" or \"obvious\" migrations. A ",{"type":43,"tag":135,"props":587,"children":589},{"className":588},[],[590],{"type":49,"value":591},"preferences.json",{"type":49,"value":593}," that was not produced by an\nactual Clarify run does not count. If asked to skip, refuse briefly and run\nClarify.",{"type":43,"tag":214,"props":595,"children":596},{},[],{"type":43,"tag":52,"props":598,"children":600},{"id":599},"state-management",[601],{"type":49,"value":602},"State Management",{"type":43,"tag":276,"props":604,"children":605},{},[606,608,613,615,621,623,628,630,636,638,643,645,650,652,658],{"type":49,"value":607},"Migration state lives in ",{"type":43,"tag":135,"props":609,"children":611},{"className":610},[],[612],{"type":49,"value":247},{"type":49,"value":614}," (",{"type":43,"tag":135,"props":616,"children":618},{"className":617},[],[619],{"type":49,"value":620},".migration\u002F[MMDD-HHMM]\u002F",{"type":49,"value":622},"), created on\nthe first phase and persisted across invocations. The state file is\n",{"type":43,"tag":135,"props":624,"children":626},{"className":625},[],[627],{"type":49,"value":442},{"type":49,"value":629},"; its shape is defined by\n",{"type":43,"tag":135,"props":631,"children":633},{"className":632},[],[634],{"type":49,"value":635},"references\u002Fvendored\u002Fstate\u002Fphase-status.schema.json",{"type":49,"value":637},", and how it is created, validated, and\nupdated across the lifecycle is defined in ",{"type":43,"tag":135,"props":639,"children":641},{"className":640},[],[642],{"type":49,"value":301},{"type":49,"value":644}," § The interpreter loop.\nThe ",{"type":43,"tag":135,"props":646,"children":648},{"className":647},[],[649],{"type":49,"value":255},{"type":49,"value":651}," directory is protected by a ",{"type":43,"tag":135,"props":653,"children":655},{"className":654},[],[656],{"type":49,"value":657},".gitignore",{"type":49,"value":659}," created at init.",{"type":43,"tag":214,"props":661,"children":662},{},[],{"type":43,"tag":52,"props":664,"children":666},{"id":665},"mcp-servers",[667],{"type":49,"value":668},"MCP Servers",{"type":43,"tag":276,"props":670,"children":671},{},[672,677],{"type":43,"tag":67,"props":673,"children":674},{},[675],{"type":49,"value":676},"awspricing",{"type":49,"value":678}," (for cost estimation):",{"type":43,"tag":59,"props":680,"children":681},{},[682,709,714],{"type":43,"tag":63,"props":683,"children":684},{},[685,687,693,694,700,701,707],{"type":49,"value":686},"Provides ",{"type":43,"tag":135,"props":688,"children":690},{"className":689},[],[691],{"type":49,"value":692},"get_pricing",{"type":49,"value":373},{"type":43,"tag":135,"props":695,"children":697},{"className":696},[],[698],{"type":49,"value":699},"get_pricing_service_codes",{"type":49,"value":373},{"type":43,"tag":135,"props":702,"children":704},{"className":703},[],[705],{"type":49,"value":706},"get_pricing_service_attributes",{"type":49,"value":708}," tools",{"type":43,"tag":63,"props":710,"children":711},{},[712],{"type":49,"value":713},"Only needed during Estimate phase. Discover and Design do not require it.",{"type":43,"tag":63,"props":715,"children":716},{},[717,719,725],{"type":49,"value":718},"Primary pricing source: ",{"type":43,"tag":135,"props":720,"children":722},{"className":721},[],[723],{"type":49,"value":724},"references\u002Fvendored\u002Fpricing\u002Faws-infra-pricing.json",{"type":49,"value":726}," (cached AWS infrastructure rates, ±5-10% for infrastructure). MCP is secondary — used only for services not found in the pricing file.",{"type":43,"tag":214,"props":728,"children":729},{},[],{"type":43,"tag":52,"props":731,"children":733},{"id":732},"files-in-this-skill",[734],{"type":49,"value":735},"Files in This Skill",{"type":43,"tag":737,"props":738,"children":742},"pre",{"className":739,"code":741,"language":49},[740],"language-text","heroku-to-aws\u002F\n├── SKILL.md ← You are here (skill entry point)\n│\n├── references\u002F\n│ ├── phases\u002F\n│ │ ├── discover\u002F\n│ │ │ ├── discover.md # Phase 1: Discover orchestrator\n│ │ │ ├── discover-terraform.md # Terraform discovery\n│ │ │ ├── discover-live-capture.md # Live CLI capture (main-window pre-work, consent-gated)\n│ │ │ ├── discover-live.md # Live discovery fragment (parses live-capture\u002F)\n│ │ │ └── discover-billing.md # Billing data parsing\n│ │ ├── clarify\u002F\n│ │ │ └── clarify.md # Phase 2: Adaptive questions (12–15, batched ≤5)\n│ │ ├── design\u002F\n│ │ │ └── design.md # Phase 3: Design orchestrator (flat single-pass mapping)\n│ │ ├── estimate\u002F\n│ │ │ └── estimate.md # Phase 4: Cost projection\n│ │ ├── workshop\u002F\n│ │ │ ├── workshop.md # Sidebar: optional post-Estimate what-if\n│ │ │ ├── workshop-sheet.md # Assumption sheet knobs\n│ │ │ ├── workshop-refresh.md # Patch prefs → Design → Estimate → snapshot\n│ │ │ ├── workshop-compare.md # Side-by-side scenarios\n│ │ │ └── workshop-assemble.md # Resolve sidebar → return to Generate\n│ │ ├── generate\u002F\n│ │ │ ├── generate.md # Phase 5: Generate orchestrator\n│ │ │ ├── generate-terraform.md # Terraform configurations\n│ │ │ ├── generate-docs.md # MIGRATION_GUIDE.md + README.md\n│ │ │ ├── generate-report.md # migration-report.html (stakeholder + scenarios)\n│ │ │ └── generate-eks.md # EKS manifests when design has EKS\n│ │ └── feedback\u002F\n│ │ └── feedback.md # Phase 6: Feedback collection (reuses shared)\n│ │\n│ └── shared\u002F # heroku-to-aws's own shared references\n│ ├── README.md # what lives here + pointers to plugin-neutral shared data\n│ ├── heroku-pricing-cache.md # Heroku plan pricing (source-side baseline)\n│ ├── schema-discover-heroku.md # heroku-resource-inventory.json schema\n│ └── schema-workshop-scenarios.md # scenarios\u002F + preferences.workshop contract\n│\n├── knowledge\u002Fdesign\u002F # design lookup DATA (pure data, referenced by\n│ │ # design.md _knowledge, gated per _when)\n│ ├── dyno-eb-sizing.json # Dyno type → Elastic Beanstalk EC2 instance type\n│ ├── dyno-fargate-sizing.json # Dyno type → Fargate CPU\u002Fmemory\n│ ├── eks-pod-sizing.json # Dyno type → EKS pod sizing + node selection\n│ ├── postgres-rds-sizing.json # Postgres plan → RDS\u002FAurora sizing\n│ ├── redis-elasticache-sizing.json # Redis plan → ElastiCache sizing\n│ ├── kafka-msk-sizing.json # Kafka plan → MSK sizing\n│ └── fast-path-addons.json # Add-on → AWS deterministic mappings (13+ entries)\n",[743],{"type":43,"tag":135,"props":744,"children":746},{"__ignoreMap":745},"",[747],{"type":49,"value":741},{"type":43,"tag":749,"props":750,"children":751},"table",{},[752,771],{"type":43,"tag":753,"props":754,"children":755},"thead",{},[756],{"type":43,"tag":757,"props":758,"children":759},"tr",{},[760,766],{"type":43,"tag":761,"props":762,"children":763},"th",{},[764],{"type":49,"value":765},"Condition",{"type":43,"tag":761,"props":767,"children":768},{},[769],{"type":49,"value":770},"Action",{"type":43,"tag":772,"props":773,"children":774},"tbody",{},[775,794,830,843,856],{"type":43,"tag":757,"props":776,"children":777},{},[778,789],{"type":43,"tag":779,"props":780,"children":781},"td",{},[782,787],{"type":43,"tag":135,"props":783,"children":785},{"className":784},[],[786],{"type":49,"value":442},{"type":49,"value":788}," missing phase gate",{"type":43,"tag":779,"props":790,"children":791},{},[792],{"type":49,"value":793},"Stop. Output: \"Cannot enter Phase X: Phase Y-1 not completed. Start from Phase Y or resume Phase Y-1.\"",{"type":43,"tag":757,"props":795,"children":796},{},[797,802],{"type":43,"tag":779,"props":798,"children":799},{},[800],{"type":49,"value":801},"awspricing unavailable after 3 attempts",{"type":43,"tag":779,"props":803,"children":804},{},[805,807,812,814,820,822,828],{"type":49,"value":806},"Display user warning about ±5-10% accuracy. Use ",{"type":43,"tag":135,"props":808,"children":810},{"className":809},[],[811],{"type":49,"value":724},{"type":49,"value":813},". Add ",{"type":43,"tag":135,"props":815,"children":817},{"className":816},[],[818],{"type":49,"value":819},"pricing_source: \"cached_fallback\"",{"type":49,"value":821}," to ",{"type":43,"tag":135,"props":823,"children":825},{"className":824},[],[826],{"type":49,"value":827},"estimation-infra.json",{"type":49,"value":829},".",{"type":43,"tag":757,"props":831,"children":832},{},[833,838],{"type":43,"tag":779,"props":834,"children":835},{},[836],{"type":49,"value":837},"User skips questions or says \"use defaults for the rest\"",{"type":43,"tag":779,"props":839,"children":840},{},[841],{"type":49,"value":842},"Apply documented defaults for remaining questions. Phase 2 completes either way.",{"type":43,"tag":757,"props":844,"children":845},{},[846,851],{"type":43,"tag":779,"props":847,"children":848},{},[849],{"type":49,"value":850},"Dyno type not in selected compute sizing table",{"type":43,"tag":779,"props":852,"children":853},{},[854],{"type":49,"value":855},"Reject mapping for that formation. Output: \"Unsupported dyno type: {type}. Cannot map to target compute service.\"",{"type":43,"tag":757,"props":857,"children":858},{},[859,864],{"type":43,"tag":779,"props":860,"children":861},{},[862],{"type":49,"value":863},"Add-on not in Fast-Path Table",{"type":43,"tag":779,"props":865,"children":866},{},[867],{"type":49,"value":868},"Mark as \"Deferred — specialist engagement\". No automated mapping produced.",{"type":43,"tag":52,"props":870,"children":872},{"id":871},"defaults",[873],{"type":49,"value":874},"Defaults",{"type":43,"tag":59,"props":876,"children":877},{},[878,888,906,924,934,944],{"type":43,"tag":63,"props":879,"children":880},{},[881,886],{"type":43,"tag":67,"props":882,"children":883},{},[884],{"type":49,"value":885},"IaC output",{"type":49,"value":887},": Terraform configurations, migration scripts, and documentation",{"type":43,"tag":63,"props":889,"children":890},{},[891,896,898,904],{"type":43,"tag":67,"props":892,"children":893},{},[894],{"type":49,"value":895},"Region",{"type":49,"value":897},": ",{"type":43,"tag":135,"props":899,"children":901},{"className":900},[],[902],{"type":49,"value":903},"us-east-1",{"type":49,"value":905}," (unless user specifies otherwise)",{"type":43,"tag":63,"props":907,"children":908},{},[909,914,916,922],{"type":43,"tag":67,"props":910,"children":911},{},[912],{"type":49,"value":913},"Sizing",{"type":49,"value":915},": Development tier (e.g., ",{"type":43,"tag":135,"props":917,"children":919},{"className":918},[],[920],{"type":49,"value":921},"db.t4g.micro",{"type":49,"value":923}," for databases, 0.5 CPU for Fargate)",{"type":43,"tag":63,"props":925,"children":926},{},[927,932],{"type":43,"tag":67,"props":928,"children":929},{},[930],{"type":49,"value":931},"Migration mode",{"type":49,"value":933},": Adapts based on available inputs (live CLI discovery recommended, Terraform supported, Procfile\u002Fapp.json supplementary, billing optional)",{"type":43,"tag":63,"props":935,"children":936},{},[937,942],{"type":43,"tag":67,"props":938,"children":939},{},[940],{"type":49,"value":941},"Cost currency",{"type":49,"value":943},": USD",{"type":43,"tag":63,"props":945,"children":946},{},[947,952,954,960],{"type":43,"tag":67,"props":948,"children":949},{},[950],{"type":49,"value":951},"Timeline assumption",{"type":49,"value":953},": 2-16 weeks depending on migration complexity — small (2-6 weeks), medium (6-12 weeks), large (12-18 weeks). Complexity tiers are classified per ",{"type":43,"tag":135,"props":955,"children":957},{"className":956},[],[958],{"type":49,"value":959},"references\u002Fvendored\u002Festimate\u002Fcomplexity-tiers.json",{"type":49,"value":829},{"type":43,"tag":52,"props":962,"children":964},{"id":963},"feedback-sharing-sidebars",[965],{"type":49,"value":966},"Feedback & Sharing Sidebars",{"type":43,"tag":276,"props":968,"children":969},{},[970,972,977,979,984,986,992,994,1000,1002,1007],{"type":49,"value":971},"The interpreter loop (",{"type":43,"tag":135,"props":973,"children":975},{"className":974},[],[976],{"type":49,"value":301},{"type":49,"value":978}," § The interpreter loop) drives phase\nsequencing, gates, and state. This section defines only the heroku-specific\nsidebar orchestration: WHERE the optional ",{"type":43,"tag":135,"props":980,"children":982},{"className":981},[],[983],{"type":49,"value":573},{"type":49,"value":985}," and ",{"type":43,"tag":135,"props":987,"children":989},{"className":988},[],[990],{"type":49,"value":991},"feedback",{"type":49,"value":993},"\nsidebars are offered (placement is orchestration prose, not part of the phase\ncontract). Both are ",{"type":43,"tag":135,"props":995,"children":997},{"className":996},[],[998],{"type":49,"value":999},"_kind: sidebar",{"type":49,"value":1001}," — off-backbone, trigger-entered, never\n",{"type":43,"tag":135,"props":1003,"children":1005},{"className":1004},[],[1006],{"type":49,"value":544},{"type":49,"value":829},{"type":43,"tag":1009,"props":1010,"children":1011},"blockquote",{},[1012],{"type":43,"tag":276,"props":1013,"children":1014},{},[1015,1020,1022,1028,1030,1036],{"type":43,"tag":67,"props":1016,"children":1017},{},[1018],{"type":49,"value":1019},"Plan-share links are GATED OFF.",{"type":49,"value":1021}," The share landing page\n(",{"type":43,"tag":135,"props":1023,"children":1025},{"className":1024},[],[1026],{"type":49,"value":1027},"https:\u002F\u002Faws.amazon.com\u002Fstartups\u002Fmigrate\u002Fconnect",{"type":49,"value":1029},") is not yet live (404). Do\nNOT offer, generate, or present a share link at any sidebar. The share-link\nspec is preserved in ",{"type":43,"tag":135,"props":1031,"children":1033},{"className":1032},[],[1034],{"type":49,"value":1035},"references\u002Fphases\u002Ffeedback\u002Ffeedback-collect.md",{"type":49,"value":1037}," Step 3\n(itself gated) for when the page ships; restoring the share prompts here is the\nun-gating change.",{"type":43,"tag":59,"props":1039,"children":1040},{},[1041,1051,1177,1266,1291],{"type":43,"tag":63,"props":1042,"children":1043},{},[1044,1049],{"type":43,"tag":67,"props":1045,"children":1046},{},[1047],{"type":49,"value":1048},"After Discover",{"type":49,"value":1050},": No prompt. Proceed directly to Clarify.",{"type":43,"tag":63,"props":1052,"children":1053},{},[1054,1059,1061,1067,1069,1075,1077,1083,1085,1090,1092,1098,1100,1106,1108,1117],{"type":43,"tag":67,"props":1055,"children":1056},{},[1057],{"type":49,"value":1058},"After Estimate",{"type":49,"value":1060},": First offer the what-if workshop sidebar per\n",{"type":43,"tag":135,"props":1062,"children":1064},{"className":1063},[],[1065],{"type":49,"value":1066},"estimate-assemble.md",{"type":49,"value":1068}," (Enter workshop \u002F Proceed toward Generate). Outer\nEstimate keeps ",{"type":43,"tag":135,"props":1070,"children":1072},{"className":1071},[],[1073],{"type":49,"value":1074},"current_phase: estimate",{"type":49,"value":1076}," until workshop is resolved (entered\nthen exited via ",{"type":43,"tag":135,"props":1078,"children":1080},{"className":1079},[],[1081],{"type":49,"value":1082},"workshop-assemble.md",{"type":49,"value":1084},", or declined). If the user enters\nworkshop, follow ",{"type":43,"tag":135,"props":1086,"children":1088},{"className":1087},[],[1089],{"type":49,"value":203},{"type":49,"value":1091},". Then, if\n",{"type":43,"tag":135,"props":1093,"children":1095},{"className":1094},[],[1096],{"type":49,"value":1097},"phases.feedback",{"type":49,"value":1099}," is ",{"type":43,"tag":135,"props":1101,"children":1103},{"className":1102},[],[1104],{"type":49,"value":1105},"\"pending\"",{"type":49,"value":1107},":",{"type":43,"tag":737,"props":1109,"children":1112},{"className":1110,"code":1111,"language":49},[740],"Would you like to share quick feedback? (5 optional questions +\nanonymized usage data — never resource names, file paths, or\naccount IDs)\n\n[A] Yes, share feedback\n[B] No thanks, continue to Generate\n",[1113],{"type":43,"tag":135,"props":1114,"children":1115},{"__ignoreMap":745},[1116],{"type":49,"value":1111},{"type":43,"tag":59,"props":1118,"children":1119},{},[1120,1154],{"type":43,"tag":63,"props":1121,"children":1122},{},[1123,1125,1130,1132,1138,1140,1145,1146,1152],{"type":49,"value":1124},"If user picks ",{"type":43,"tag":67,"props":1126,"children":1127},{},[1128],{"type":49,"value":1129},"A",{"type":49,"value":1131}," → Load ",{"type":43,"tag":135,"props":1133,"children":1135},{"className":1134},[],[1136],{"type":49,"value":1137},"references\u002Fphases\u002Ffeedback\u002Ffeedback.md",{"type":49,"value":1139},", execute it. Set ",{"type":43,"tag":135,"props":1141,"children":1143},{"className":1142},[],[1144],{"type":49,"value":1097},{"type":49,"value":821},{"type":43,"tag":135,"props":1147,"children":1149},{"className":1148},[],[1150],{"type":49,"value":1151},"\"completed\"",{"type":49,"value":1153},". Continue to Generate.",{"type":43,"tag":63,"props":1155,"children":1156},{},[1157,1158,1163,1165,1170,1171,1176],{"type":49,"value":1124},{"type":43,"tag":67,"props":1159,"children":1160},{},[1161],{"type":49,"value":1162},"B",{"type":49,"value":1164}," → Set ",{"type":43,"tag":135,"props":1166,"children":1168},{"className":1167},[],[1169],{"type":49,"value":1097},{"type":49,"value":821},{"type":43,"tag":135,"props":1172,"children":1174},{"className":1173},[],[1175],{"type":49,"value":1151},{"type":49,"value":1153},{"type":43,"tag":63,"props":1178,"children":1179},{},[1180,1185,1187,1193,1195,1201,1203,1209,1210,1215,1217,1223,1224,1229,1231,1236,1238,1243,1244,1249,1251,1256,1258,1264],{"type":43,"tag":67,"props":1181,"children":1182},{},[1183],{"type":49,"value":1184},"Workshop resume (mandatory):",{"type":49,"value":1186}," If ",{"type":43,"tag":135,"props":1188,"children":1190},{"className":1189},[],[1191],{"type":49,"value":1192},"current_phase == \"estimate\"",{"type":49,"value":1194}," AND\n",{"type":43,"tag":135,"props":1196,"children":1198},{"className":1197},[],[1199],{"type":49,"value":1200},"phases.estimate == \"completed\"",{"type":49,"value":1202}," AND ",{"type":43,"tag":135,"props":1204,"children":1206},{"className":1205},[],[1207],{"type":49,"value":1208},"phases.workshop",{"type":49,"value":1099},{"type":43,"tag":135,"props":1211,"children":1213},{"className":1212},[],[1214],{"type":49,"value":1105},{"type":49,"value":1216}," or\n",{"type":43,"tag":135,"props":1218,"children":1220},{"className":1219},[],[1221],{"type":49,"value":1222},"\"in_progress\"",{"type":49,"value":373},{"type":43,"tag":67,"props":1225,"children":1226},{},[1227],{"type":49,"value":1228},"do not recompute Estimate",{"type":49,"value":1230},". If ",{"type":43,"tag":135,"props":1232,"children":1234},{"className":1233},[],[1235],{"type":49,"value":1105},{"type":49,"value":1237},", re-present the\npost-Estimate workshop offer from ",{"type":43,"tag":135,"props":1239,"children":1241},{"className":1240},[],[1242],{"type":49,"value":1066},{"type":49,"value":1230},{"type":43,"tag":135,"props":1245,"children":1247},{"className":1246},[],[1248],{"type":49,"value":1222},{"type":49,"value":1250},",\nload ",{"type":43,"tag":135,"props":1252,"children":1254},{"className":1253},[],[1255],{"type":49,"value":203},{"type":49,"value":1257},". Generate must wait until\n",{"type":43,"tag":135,"props":1259,"children":1261},{"className":1260},[],[1262],{"type":49,"value":1263},"phases.workshop == \"completed\"",{"type":49,"value":1265}," (entered+exited or declined).",{"type":43,"tag":63,"props":1267,"children":1268},{},[1269,1274,1276,1281,1283,1289],{"type":43,"tag":67,"props":1270,"children":1271},{},[1272],{"type":49,"value":1273},"Warm start \u002F explicit what-if",{"type":49,"value":1275},": If the user says \"what if\", \"reprice\",\n\"workshop mode\", or \"compare scenarios\" and Estimate artifacts already exist,\nload ",{"type":43,"tag":135,"props":1277,"children":1279},{"className":1278},[],[1280],{"type":49,"value":203},{"type":49,"value":1282}," directly (respect Generate\n",{"type":43,"tag":135,"props":1284,"children":1286},{"className":1285},[],[1287],{"type":49,"value":1288},"_re_entry_guard",{"type":49,"value":1290}," when Terraform was already produced). Knobs on the pilot\nsheet: region, HA, compute target, cost optimization, CPU architecture\n(x86 vs Graviton). There is no traffic-multiplier knob in v1.",{"type":43,"tag":63,"props":1292,"children":1293},{},[1294,1299,1301,1306,1308,1313,1315,1320],{"type":43,"tag":67,"props":1295,"children":1296},{},[1297],{"type":49,"value":1298},"After Generate",{"type":49,"value":1300},": No prompt. If ",{"type":43,"tag":135,"props":1302,"children":1304},{"className":1303},[],[1305],{"type":49,"value":1097},{"type":49,"value":1307}," is still ",{"type":43,"tag":135,"props":1309,"children":1311},{"className":1310},[],[1312],{"type":49,"value":1105},{"type":49,"value":1314},", set it to ",{"type":43,"tag":135,"props":1316,"children":1318},{"className":1317},[],[1319],{"type":49,"value":1151},{"type":49,"value":1321}," and mark the migration complete.",{"type":43,"tag":276,"props":1323,"children":1324},{},[1325,1330],{"type":43,"tag":67,"props":1326,"children":1327},{},[1328],{"type":49,"value":1329},"Critical constraint",{"type":49,"value":1331},": Follow each phase reference file's workflow exactly. If unable to complete a step, stop and report the specific issue. Do not fabricate or infer data.",{"items":1333,"total":1509},[1334,1353,1374,1384,1395,1408,1418,1428,1449,1464,1479,1494],{"slug":1335,"name":1335,"fn":1336,"description":1337,"org":1338,"tags":1339,"stars":1350,"repoUrl":1351,"updatedAt":1352},"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},[1340,1341,1344,1347],{"name":21,"slug":22,"type":16},{"name":1342,"slug":1343,"type":16},"Debugging","debugging",{"name":1345,"slug":1346,"type":16},"Logs","logs",{"name":1348,"slug":1349,"type":16},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":1354,"name":1355,"fn":1356,"description":1357,"org":1358,"tags":1359,"stars":1350,"repoUrl":1351,"updatedAt":1373},"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},[1360,1363,1364,1367,1370],{"name":1361,"slug":1362,"type":16},"Aurora","aurora",{"name":21,"slug":22,"type":16},{"name":1365,"slug":1366,"type":16},"Database","database",{"name":1368,"slug":1369,"type":16},"Serverless","serverless",{"name":1371,"slug":1372,"type":16},"SQL","sql","2026-08-04T05:35:10.770847",{"slug":1375,"name":1376,"fn":1356,"description":1357,"org":1377,"tags":1378,"stars":1350,"repoUrl":1351,"updatedAt":1383},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1379,1380,1381,1382],{"name":21,"slug":22,"type":16},{"name":1365,"slug":1366,"type":16},{"name":1368,"slug":1369,"type":16},{"name":1371,"slug":1372,"type":16},"2026-08-04T05:35:05.694395",{"slug":1385,"name":1386,"fn":1356,"description":1357,"org":1387,"tags":1388,"stars":1350,"repoUrl":1351,"updatedAt":1394},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1389,1390,1391,1392,1393],{"name":21,"slug":22,"type":16},{"name":1365,"slug":1366,"type":16},{"name":14,"slug":15,"type":16},{"name":1368,"slug":1369,"type":16},{"name":1371,"slug":1372,"type":16},"2026-08-04T05:35:08.749669",{"slug":1396,"name":1397,"fn":1356,"description":1357,"org":1398,"tags":1399,"stars":1350,"repoUrl":1351,"updatedAt":1407},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1400,1401,1402,1405,1406],{"name":21,"slug":22,"type":16},{"name":1365,"slug":1366,"type":16},{"name":1403,"slug":1404,"type":16},"PostgreSQL","postgresql",{"name":1368,"slug":1369,"type":16},{"name":1371,"slug":1372,"type":16},"2026-08-04T05:35:06.713102",{"slug":1409,"name":1410,"fn":1356,"description":1357,"org":1411,"tags":1412,"stars":1350,"repoUrl":1351,"updatedAt":1417},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1413,1414,1415,1416],{"name":21,"slug":22,"type":16},{"name":1365,"slug":1366,"type":16},{"name":1368,"slug":1369,"type":16},{"name":1371,"slug":1372,"type":16},"2026-08-04T05:35:10.086942",{"slug":1419,"name":1419,"fn":1356,"description":1357,"org":1420,"tags":1421,"stars":1350,"repoUrl":1351,"updatedAt":1427},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1422,1423,1424,1425,1426],{"name":21,"slug":22,"type":16},{"name":1365,"slug":1366,"type":16},{"name":14,"slug":15,"type":16},{"name":1368,"slug":1369,"type":16},{"name":1371,"slug":1372,"type":16},"2026-08-04T05:35:07.751779",{"slug":1429,"name":1429,"fn":1430,"description":1431,"org":1432,"tags":1433,"stars":1446,"repoUrl":1447,"updatedAt":1448},"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},[1434,1437,1440,1443],{"name":1435,"slug":1436,"type":16},"Accounting","accounting",{"name":1438,"slug":1439,"type":16},"Analytics","analytics",{"name":1441,"slug":1442,"type":16},"Cost Optimization","cost-optimization",{"name":1444,"slug":1445,"type":16},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":1450,"name":1450,"fn":1451,"description":1452,"org":1453,"tags":1454,"stars":1446,"repoUrl":1447,"updatedAt":1463},"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},[1455,1456,1457,1460],{"name":21,"slug":22,"type":16},{"name":1444,"slug":1445,"type":16},{"name":1458,"slug":1459,"type":16},"Management","management",{"name":1461,"slug":1462,"type":16},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":1465,"name":1465,"fn":1466,"description":1467,"org":1468,"tags":1469,"stars":1446,"repoUrl":1447,"updatedAt":1478},"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},[1470,1471,1472,1475],{"name":1438,"slug":1439,"type":16},{"name":1444,"slug":1445,"type":16},{"name":1473,"slug":1474,"type":16},"Financial Statements","financial-statements",{"name":1476,"slug":1477,"type":16},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":1480,"name":1480,"fn":1481,"description":1482,"org":1483,"tags":1484,"stars":1446,"repoUrl":1447,"updatedAt":1493},"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},[1485,1488,1491],{"name":1486,"slug":1487,"type":16},"Automation","automation",{"name":1489,"slug":1490,"type":16},"Documents","documents",{"name":1492,"slug":1480,"type":16},"PDF","2026-07-12T08:41:44.135656",{"slug":1495,"name":1495,"fn":1496,"description":1497,"org":1498,"tags":1499,"stars":1446,"repoUrl":1447,"updatedAt":1508},"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},[1500,1501,1504,1505],{"name":1435,"slug":1436,"type":16},{"name":1502,"slug":1503,"type":16},"Data Analysis","data-analysis",{"name":1444,"slug":1445,"type":16},{"name":1506,"slug":1507,"type":16},"KPI","kpi","2026-07-12T08:39:59.54971",125,{"items":1511,"total":1611},[1512,1529,1543,1556,1563,1580,1598],{"slug":1513,"name":1513,"fn":1514,"description":1515,"org":1516,"tags":1517,"stars":26,"repoUrl":27,"updatedAt":1528},"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},[1518,1521,1524,1525],{"name":1519,"slug":1520,"type":16},"Agents","agents",{"name":1522,"slug":1523,"type":16},"AI Infrastructure","ai-infrastructure",{"name":21,"slug":22,"type":16},{"name":1526,"slug":1527,"type":16},"Engineering","engineering","2026-08-14T04:51:57.95352",{"slug":1530,"name":1530,"fn":1531,"description":1532,"org":1533,"tags":1534,"stars":26,"repoUrl":27,"updatedAt":1542},"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},[1535,1538,1539],{"name":1536,"slug":1537,"type":16},"Architecture","architecture",{"name":21,"slug":22,"type":16},{"name":1540,"slug":1541,"type":16},"Strategy","strategy","2026-08-14T04:27:18.122372",{"slug":1544,"name":1544,"fn":1545,"description":1546,"org":1547,"tags":1548,"stars":26,"repoUrl":27,"updatedAt":1555},"gcp-to-aws","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},[1549,1550,1553,1554],{"name":21,"slug":22,"type":16},{"name":1551,"slug":1552,"type":16},"Google Cloud","google-cloud",{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},"2026-08-14T04:52:07.358543",{"slug":4,"name":4,"fn":5,"description":6,"org":1557,"tags":1558,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1559,1560,1561,1562],{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"slug":1564,"name":1564,"fn":1565,"description":1566,"org":1567,"tags":1568,"stars":26,"repoUrl":27,"updatedAt":1579},"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},[1569,1570,1573,1576],{"name":21,"slug":22,"type":16},{"name":1571,"slug":1572,"type":16},"Cloud","cloud",{"name":1574,"slug":1575,"type":16},"Documentation","documentation",{"name":1577,"slug":1578,"type":16},"Research","research","2026-07-25T05:32:19.312255",{"slug":1581,"name":1581,"fn":1582,"description":1583,"org":1584,"tags":1585,"stars":26,"repoUrl":27,"updatedAt":1597},"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},[1586,1587,1590,1593,1594],{"name":21,"slug":22,"type":16},{"name":1588,"slug":1589,"type":16},"Gemini","gemini",{"name":1591,"slug":1592,"type":16},"LLM","llm",{"name":14,"slug":15,"type":16},{"name":1595,"slug":1596,"type":16},"OpenAI","openai","2026-08-14T04:51:58.393797",{"slug":1599,"name":1599,"fn":1600,"description":1601,"org":1602,"tags":1603,"stars":26,"repoUrl":27,"updatedAt":1610},"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},[1604,1605,1608,1609],{"name":21,"slug":22,"type":16},{"name":1606,"slug":1607,"type":16},"Coding","coding",{"name":1526,"slug":1527,"type":16},{"name":1591,"slug":1592,"type":16},"2026-08-14T04:27:16.118669",8]