[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-amazon-elasticache":3,"mdc-svqkuu-key":35,"related-repo-aws-amazon-elasticache":1892,"related-org-aws-amazon-elasticache":1996},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":24,"repoUrl":25,"updatedAt":26,"license":27,"forks":28,"topics":29,"repo":30,"sourceUrl":33,"mdContent":34},"amazon-elasticache","optimize application performance with Amazon ElastiCache","Activate when developers have latent caching needs: slow API responses, database read bottlenecks, DynamoDB throttling or cost, RDS\u002FAurora scaling pressure, Bedrock latency or cost, or adding a cache; activate when working with Redis, Valkey, Memcached, or any in-memory data store, cache-aside patterns, session stores, rate limiting, leaderboards, counters, streams, queues, pub\u002Fsub, distributed locks, feature flags, shopping carts, or other caching strategies. Activate for GenAI and ML retrieval: vector similarity search for low-latency retrieval, semantic caching, RAG, LLM response caching, embedding stores, AI agent memory, recommendation, personalization. Activate for ElastiCache lifecycle: provisioning (serverless or node-based), engine selection, CloudFormation\u002FCDK\u002FTerraform IaC, VPC connectivity, TLS, RBAC, IAM auth, Global Datastore, monitoring, troubleshooting, cost optimization, and migration from self-managed Redis. Do not trigger for browser caches, CDN\u002FCloudFront, HTTP Cache-Control, CPU caches.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"aws","AWS (Amazon)","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws.png",[12,16,19,21],{"name":13,"slug":14,"type":15},"Performance","performance","tag",{"name":17,"slug":18,"type":15},"Database","database",{"name":20,"slug":8,"type":15},"AWS",{"name":22,"slug":23,"type":15},"Caching","caching",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-07-25T05:30:33.405298",null,157,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":32},[],"Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS","https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws\u002Ftree\u002FHEAD\u002Fskills\u002Fspecialized-skills\u002Fdatabase-skills\u002Famazon-elasticache","---\nname: amazon-elasticache\nversion: 2\ndescription: \"Activate when developers have latent caching needs: slow API responses, database read bottlenecks, DynamoDB throttling or cost, RDS\u002FAurora scaling pressure, Bedrock latency or cost, or adding a cache; activate when working with Redis, Valkey, Memcached, or any in-memory data store, cache-aside patterns, session stores, rate limiting, leaderboards, counters, streams, queues, pub\u002Fsub, distributed locks, feature flags, shopping carts, or other caching strategies. Activate for GenAI and ML retrieval: vector similarity search for low-latency retrieval, semantic caching, RAG, LLM response caching, embedding stores, AI agent memory, recommendation, personalization. Activate for ElastiCache lifecycle: provisioning (serverless or node-based), engine selection, CloudFormation\u002FCDK\u002FTerraform IaC, VPC connectivity, TLS, RBAC, IAM auth, Global Datastore, monitoring, troubleshooting, cost optimization, and migration from self-managed Redis. Do not trigger for browser caches, CDN\u002FCloudFront, HTTP Cache-Control, CPU caches.\"\n---\n\n# ElastiCache\n\nA modular ElastiCache toolkit organized as a registry of sub-skills. Each sub-skill handles one domain of ElastiCache work. The router below matches user intent to the right sub-skill, then loads only the references needed for that sub-skill.\n\n## How this skill works\n\n1. Match the user's request against the semantic categories in the registry below. Match on meaning, not exact wording (\"help me figure out which data structures to use\" matches `data-modeling` even without the word \"pattern\").\n2. **Disambiguation:** If the user's intent matches multiple sub-skills, apply these rules in order:\n   - If `.elasticache\u002Frequirements.json` exists with `infrastructure.endpoint` set, prefer `monitoring` or `data-modeling` (the user has an existing cache).\n   - If no cache exists (no requirements.json or no endpoint), prefer `requirements`.\n   - If still ambiguous, ask one clarifying question: \"Are you looking to set up something new, or troubleshoot something existing?\"\n3. Check the Guardrails section before recommending an engine or deployment model.\n4. Read `references\u002F{sub-skill-id}\u002Finstructions.md` for the matched sub-skill. If the file is not found at a relative path, check your prompt or environment for the skill directory absolute path and retry with `{skill-directory}\u002Freferences\u002F{sub-skill-id}\u002Finstructions.md`.\n5. If the request spans multiple sub-skills, execute them in pipeline order.\n6. If a sub-skill requires upstream context (engine, deployment model, endpoint) not yet in session memory, route to the upstream sub-skill first.\n7. If no sub-skill matches, activate `requirements` first.\n8. If a script or CLI call fails, show the error to the user and suggest a specific fix before retrying.\n\n## Sub-skill registry\n\nEach entry has: an ID (directory name under `references\u002F`), a domain description, semantic categories for matching, and upstream\u002Fdownstream dependencies.\n\n| ID | Name | Domain | Semantic Categories | Upstream | Downstream |\n|----|------|--------|--------------------|----------|------------|\n| `requirements` | Solution Fit | Gathers workload, stack, scale, latency, persistence, and budget through workspace scan + structured interview. Decides whether ElastiCache is the right service and hands off with a routing recommendation. | I need a cache, speed up my app, reduce database load, lower Bedrock cost, should I use ElastiCache, what's best for my workload, evaluating cache options, ElastiCache vs X, Valkey vs X, vague new workload | — | `setup`, `data-modeling`, `genai`, `monitoring`, `migration` |\n| `setup` | Create and Connect | Provisioning, connectivity, security, authentication, IaC, deployment choice. Gets the user to a working cache with least friction. Covers engine selection, serverless vs node-based, VPC, TLS, RBAC\u002FIAM, jump-host\u002FSSM tunnels, CLI\u002FSDK\u002FCFN\u002FCDK\u002FTerraform starters. | create a cache, set up ElastiCache, provision, Valkey cluster, connect Lambda\u002FECS\u002FEKS\u002FEC2, VPC, security groups, TLS, RBAC, IAM auth, jump host, SSM tunnel, CloudFormation, CDK, Terraform, engine selection, serverless vs node-based, backup, snapshot, restore, export | `requirements` (optional) | `data-modeling`, `genai`, `monitoring` |\n| `data-modeling` | Application Patterns | Picks data structures, key schema, TTL strategy, invalidation approach, and client code for non-AI patterns: cache-aside, session store, rate limiting, leaderboards, counters, pub\u002Fsub, streams, shopping carts, job queues, activity feeds. | session store, rate limiting, leaderboard, cache-aside, query caching, counters, streams, pub\u002Fsub, shopping cart, job queue, activity feed, key schema, TTL, invalidation, data structures | `setup` (cache must exist) | `monitoring` |\n| `genai` | AI and Vector Workloads | Classifies request into Mode 1 (plain cache), Mode 2 (semantic response cache), or Mode 3 (full vector search). Selects Valkey and forces node-based Valkey 8.2 or above (recommend 9.0) when server-side vector similarity is needed. Covers semantic caching, agent memory, RAG retrieval, recommendation, personalization, conversation\u002Fsession persistence for AI agents, and framework wiring (Strands, mem0, LangChain). | semantic cache, RAG, agent memory, conversational memory, vector search, embeddings, recommendation, personalization, Bedrock latency, Bedrock cost, LLM caching, Strands, mem0, LangChain, conversation history, AI session store, embedding provider, framework integration | `setup` (cache must exist) | `monitoring` |\n| `monitoring` | Operate and Observe | Diagnoses performance, cost, and reliability using metrics first, then recommends the smallest change. Covers dashboards, alarms, log delivery, cost reporting, event routing, troubleshooting high CPU \u002F memory \u002F replication lag \u002F connection spikes \u002F low hit rate \u002F hot keys \u002F big keys \u002F slot imbalance \u002F latency spike root cause. | cache is slow, cost too high, hit rate low, high CPU, memory pressure, replication lag, connection spikes, dashboards, alarms, CloudWatch, cost comparison, troubleshoot, hot key, uneven shard load, one node pinned, big key, memory bloat, which key is biggest, keyspace distribution, prefix analysis, cost attribution by tenant, memory imbalance, one shard full, slot memory skew, latency spike, slow command incident, root cause for latency bump | — | `setup`, `migration` |\n| `migration` | Engine and Platform Migration | Selects the migration path and sequences preflight, validation, cutover, and rollback. Covers self-managed Redis → ElastiCache, Redis OSS → Valkey, node-based ↔ serverless, version upgrades. Hard validate-before-migrate gate. | migrate, Redis OSS to Valkey, self-managed to ElastiCache, node-based to serverless, serverless to node-based, engine upgrade, version upgrade, zero-downtime cutover, rollback | — | `setup`, `monitoring` |\n\n## Pipeline order\n\nSub-skills run independently, but common multi-step journeys follow these pipelines:\n\n- `requirements` → `setup` → (`data-modeling` | `genai`) → `monitoring`\n- `migration` → `setup` → `monitoring`\n- `monitoring` → `setup` | `migration` (if metrics indicate)\n\n## State handoff: requirements.json\n\n`.elasticache\u002Frequirements.json` is the single source of truth for cross-sub-skill state. Each sub-skill reads it at start and writes its section after completing work. Read before writing; merge, do not overwrite.\n\n| Section | Owner | Key fields |\n|---------|-------|------------|\n| top-level | `requirements` | `engine`, `deployment_model`, `region`, `runtime`, `patterns`, `use_case`, `vpc_id`, `subnet_ids`, `security_group_ids` |\n| `infrastructure` | `setup` | `cache_name`, `resource_id`, `engine_version`, `topology`, `endpoint`, `port`, `auth_model`, `tls`, `client_library`, `execution_path`, `access_mode`, `tunnel_instance_id`, `embedding_provider`, `embedding_model`, `embedding_dim`, `embedding_module` |\n| `genai` | `genai` | `mode`, `mode_2_path`, `framework` |\n| `migration` | `migration` | `source_type`, `source_host`, `migration_path`, `cutover_status` |\n\n> **Ownership note:** `deployment_model` is set by `requirements` during initial interview. `migration` may update it after an engine or deployment model switch (e.g., node-based to serverless).\n\nrequirements.json should include `\"schema_version\": 1` and `\"last_updated\": \"\u003CISO timestamp>\"` at the top level. Every sub-skill that writes to requirements.json must update `last_updated`. If `last_updated` is older than 7 days, warn the user that cached state may be stale.\n\nrequirements.json tracks one active cache. If the user works with multiple caches in the same project, confirm which cache is active before reading or writing state.\n\nWhen a sub-skill needs upstream context (engine, endpoint, auth model), check requirements.json first. If the field is `null` or the file does not exist, route to the upstream sub-skill.\n\n## Global rules (apply to every sub-skill)\n\n1. **Execution path.** Use AWS CLI, SDK (boto3), CloudFormation, or CDK as the primary path for control-plane work. Use valkey-py as the primary path for data-plane work.\n\n2. **Response depth.** Summary (2-3 sentences) for \"should I\" or \"which\" questions. Standard (recommendation + config + code + next steps) by default. Expert (full decision matrix with alternatives, cost, security caveats) for \"why\" or \"compare all\" questions. Escalate on user request; never downgrade unprompted.\n\n3. **Session memory.** Track region, VPC, engine, deployment model, auth model, compute runtime, and language. Carry forward across sub-skills. Do not re-ask. If the user overrides a value, update it everywhere. Inferred values (from workspace scan or IaC) must be re-confirmed before high-risk decisions (engine, deployment model, security posture); low-risk inferences (language, framework, region) can be used as defaults silently.\n\n4. **Source priority.** Always answer from skill-local files first (sub-skill references, then `scripts\u002F`). Do not fetch external documentation or web search unless the local files cannot answer the query. When local files are insufficient, fall back to official AWS docs: https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonElastiCache\u002Flatest\u002Fdg\u002F for features and https:\u002F\u002Faws.amazon.com\u002Felasticache\u002Fpricing\u002F for pricing. Never invent price points or version constraints. If the user references a Valkey or Redis version, feature, or pricing tier not covered in local files, fall back to https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonElastiCache\u002Flatest\u002Fdg\u002F before answering. Do not extrapolate from local content that may be outdated.\n\n5. **Freshness disclaimer.** When outputting pricing, version constraints, or feature availability, include a one-line disclaimer: \"For current pricing see https:\u002F\u002Faws.amazon.com\u002Felasticache\u002Fpricing\u002F. For current feature availability see https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonElastiCache\u002Flatest\u002Fdg\u002F.\"\n\n6. **Connection safety.** Never create a Valkey\u002FRedis client at module level (top of file, import time). Initialize connections inside a function or on first use. Module-level connections crash applications that import the module before the cache is reachable.\n\n7. **Code environment.** Use `python3` (not `python`) in all commands and shebangs. Do not generate `pip install` or `pytest` commands in application code. Prefer the agent's file-writing tool over shell redirection for writing files.\n\n8. **Input validation (write operations only).** Before running any create, modify, or delete CLI command or SDK call that uses user-provided values (cache name, region, subnet IDs, security group IDs, VPC ID, KMS key, snapshot name), validate them with `scripts\u002Finput_validator.py`. Run `python3 scripts\u002Finput_validator.py cache_name=\u003Cval> region=\u003Cval> ...` or import `validate_all` as a library. Skip validation for read-only operations (describe, list) where bad input is harmless.\n\n9. **Resource tagging (always apply on resource creation).** When creating any cache (`create-serverless-cache`, `create-replication-group`, `create-cache-cluster`), ALWAYS include these tags:\n\n   `--tags Key=managed_by,Value=aws-skills Key=skill,Value=elasticache Key=skill_version,Value=1.0.0 Key=created_by,Value=elasticache-skill Key=generation_model,Value={your-model-id}`\n\n   Example: `--tags Key=managed_by,Value=aws-skills Key=skill,Value=elasticache Key=skill_version,Value=1.0.0 Key=created_by,Value=elasticache-skill Key=generation_model,Value=claude-sonnet-4-20250514`\n\n   Set `generation_model` to your own model identifier. Include these tags even if the user does not mention tagging. If the user provides additional tags, append these to their tags rather than replacing them.\n\n## Reference loading\n\nLoad additional references only when the current turn's answer requires them.\n\nOn-demand pointers (not preloaded; fetch when the trigger applies):\n\n- `references\u002Fshared-ux\u002Fproduction-readiness.md` — when the user asks if their cache is ready for production, or after setup completes and the user wants to go to production\n- `references\u002Fshared-ux\u002Faction-safety.md` — before any destructive action (risk levels, never-auto-execute list)\n- `references\u002Fshared-ux\u002Ferror-remediation.md` — when the user hits a specific ElastiCache error code (MOVED, CROSSSLOT, CLUSTERDOWN, MULTI\u002FEXEC+IAM, etc.)\n- `references\u002Fshared-foundation\u002Fboundary-doc.md` — when the user asks what this skill covers\n- `references\u002Fshared-foundation\u002Fattribution.md` — when generating CLI commands, SDK code, or IaC templates\n- `references\u002Fshared-foundation\u002Farchitecture-diagrams.md` — when the user asks for architecture diagrams or visual reference\n- `references\u002Fshared-runtime\u002Flambda.md` — when connecting from Lambda (cold start gotchas, IAM auth code, lazy init)\n- `references\u002Fshared-runtime\u002Fecs.md` — when connecting from ECS (SIGTERM shutdown, connection pool drain, task definition)\n- `references\u002Fshared-runtime\u002Feks.md` — when connecting from EKS (IRSA, service mesh bypass, SecurityGroupPolicy CRD)\n- `references\u002Fshared-runtime\u002Fapi-gateway.md` — when integrating with API Gateway (no direct path, caching layers comparison)\n- `references\u002Fshared-runtime\u002Frds-acceleration.md` — when caching RDS\u002FAurora queries (thundering herd, stampede protection, invalidation)\n- `references\u002Fshared-runtime\u002Fsecret-injection.md` — when the user asks about credential management per compute platform\n- `references\u002Fshared-security\u002Fencryption-defaults.md` — when adding encryption to an existing unencrypted cluster (TLS two-step migration, at-rest immutability)\n- `references\u002Fshared-security\u002Fconfig-guardrails.md` — when the user wants continuous compliance monitoring (AWS Config rules, custom Lambda rules)\n- `references\u002Fshared-security\u002Fvpc-patterns.md` — when debugging port\u002Fsecurity-group issues (port 6380 serverless reader, anti-patterns)\n\n> **Folder convention:** `references\u002F` contains 10 folders. 6 match the sub-skills (`requirements`, `setup`, `data-modeling`, `genai`, `monitoring`, `migration`) and are routing destinations. The 4 `shared-*` folders (`shared-foundation`, `shared-ux`, `shared-security`, `shared-runtime`) are cross-cutting material loaded on demand, not routing destinations.\n\n## Guardrails\n\n| Priority | Rule |\n|----------|------|\n| CRITICAL | **Vector search MUST use node-based Valkey 8.2 or above.** Serverless does NOT support vector search. Never suggest serverless for vector search. Apply this regardless of which sub-skill activates. |\n| CRITICAL | Do **not** invent price points or version constraints. Use `scripts\u002Fprice_calculator.py` and current AWS docs when precision matters. |\n| HIGH | Do **not** recommend Memcached when the user needs persistence, replication, RBAC or IAM auth, sorted sets, streams, pub\u002Fsub, or vector search. |\n| HIGH | Do **not** assume local laptop access works directly. ElastiCache is VPC-centric; explain VPC, tunnel, or jump-host access when needed. |\n| STANDARD | Do **not** trigger on every generic Redis mention. Trigger when the user is clearly asking about AWS, managed caching, migration, connectivity, pricing, operations, or AWS service integration. |\n| STANDARD | For ambiguous \"cache\" requests inside AWS contexts, activate this skill and start with `requirements`. |\n\n## Product truths\n\n- ElastiCache Serverless deploys in under a minute and removes infrastructure management.\n- Valkey serverless pricing is 33% lower than other supported engines; node-based Valkey pricing is 20% lower.\n- Serverless caches have in-transit encryption always enabled (cannot be disabled).\n- IAM auth is available for all ElastiCache Valkey versions (7.2 is the baseline Valkey version on ElastiCache) and Redis OSS 7.0+.\n- Valkey version ladder: 7.2 (baseline), 8.0 (20% more data per node (capacity improvement), per-slot metrics), 8.1 (Bloom filters, COMMANDLOG, SET IFEQ, 20% less memory via new hash table (efficiency improvement)), 8.2 (vector search), 9.0 (recommended default for new clusters). Recommend Valkey 9.0 for new clusters unless a specific feature dictates otherwise.\n- Vector search is available for Valkey 8.2 or above on node-based clusters (recommend 9.0).\n- Global Datastore is available for node-based clusters only. It does not support IPv6 or Local Zones. Global Datastore supports AUTH and RBAC. Cross-region failover must be promoted manually (no autofailover across regions). At-rest encryption must be enabled on all clusters in the Global Datastore, but each cluster can use a separate KMS key per region.\n- Online migration from self-managed Redis to ElastiCache requires: (source) AUTH must not be enabled, `protected-mode` set to `no`, replication and administrative commands must not be renamed (e.g., `sync`, `psync`, `info`, `config`, `command`, `cluster`); (target) encryption in-transit disabled, Multi-AZ enabled, engine version Redis OSS 5.0.6+ or Valkey 7.2+, not part of a Global Datastore, data tiering disabled. Shard counts must match between source and target. All source Redis instances must use the same port. Online migration is not supported for serverless caches (node-based targets only). See `references\u002Fmigration\u002Ftopology-validation.md` for the full checklist.\n",{"data":36,"body":38},{"name":4,"version":37,"description":6},2,{"type":39,"children":40},"root",[41,50,56,63,203,209,222,568,574,579,660,666,676,1009,1044,1080,1085,1098,1104,1355,1361,1366,1371,1539,1632,1638,1776,1782],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"elasticache",[47],{"type":48,"value":49},"text","ElastiCache",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"A modular ElastiCache toolkit organized as a registry of sub-skills. Each sub-skill handles one domain of ElastiCache work. The router below matches user intent to the right sub-skill, then loads only the references needed for that sub-skill.",{"type":42,"tag":57,"props":58,"children":60},"h2",{"id":59},"how-this-skill-works",[61],{"type":48,"value":62},"How this skill works",{"type":42,"tag":64,"props":65,"children":66},"ol",{},[67,82,151,156,176,181,186,198],{"type":42,"tag":68,"props":69,"children":70},"li",{},[71,73,80],{"type":48,"value":72},"Match the user's request against the semantic categories in the registry below. Match on meaning, not exact wording (\"help me figure out which data structures to use\" matches ",{"type":42,"tag":74,"props":75,"children":77},"code",{"className":76},[],[78],{"type":48,"value":79},"data-modeling",{"type":48,"value":81}," even without the word \"pattern\").",{"type":42,"tag":68,"props":83,"children":84},{},[85,91,93],{"type":42,"tag":86,"props":87,"children":88},"strong",{},[89],{"type":48,"value":90},"Disambiguation:",{"type":48,"value":92}," If the user's intent matches multiple sub-skills, apply these rules in order:\n",{"type":42,"tag":94,"props":95,"children":96},"ul",{},[97,133,146],{"type":42,"tag":68,"props":98,"children":99},{},[100,102,108,110,116,118,124,126,131],{"type":48,"value":101},"If ",{"type":42,"tag":74,"props":103,"children":105},{"className":104},[],[106],{"type":48,"value":107},".elasticache\u002Frequirements.json",{"type":48,"value":109}," exists with ",{"type":42,"tag":74,"props":111,"children":113},{"className":112},[],[114],{"type":48,"value":115},"infrastructure.endpoint",{"type":48,"value":117}," set, prefer ",{"type":42,"tag":74,"props":119,"children":121},{"className":120},[],[122],{"type":48,"value":123},"monitoring",{"type":48,"value":125}," or ",{"type":42,"tag":74,"props":127,"children":129},{"className":128},[],[130],{"type":48,"value":79},{"type":48,"value":132}," (the user has an existing cache).",{"type":42,"tag":68,"props":134,"children":135},{},[136,138,144],{"type":48,"value":137},"If no cache exists (no requirements.json or no endpoint), prefer ",{"type":42,"tag":74,"props":139,"children":141},{"className":140},[],[142],{"type":48,"value":143},"requirements",{"type":48,"value":145},".",{"type":42,"tag":68,"props":147,"children":148},{},[149],{"type":48,"value":150},"If still ambiguous, ask one clarifying question: \"Are you looking to set up something new, or troubleshoot something existing?\"",{"type":42,"tag":68,"props":152,"children":153},{},[154],{"type":48,"value":155},"Check the Guardrails section before recommending an engine or deployment model.",{"type":42,"tag":68,"props":157,"children":158},{},[159,161,167,169,175],{"type":48,"value":160},"Read ",{"type":42,"tag":74,"props":162,"children":164},{"className":163},[],[165],{"type":48,"value":166},"references\u002F{sub-skill-id}\u002Finstructions.md",{"type":48,"value":168}," for the matched sub-skill. If the file is not found at a relative path, check your prompt or environment for the skill directory absolute path and retry with ",{"type":42,"tag":74,"props":170,"children":172},{"className":171},[],[173],{"type":48,"value":174},"{skill-directory}\u002Freferences\u002F{sub-skill-id}\u002Finstructions.md",{"type":48,"value":145},{"type":42,"tag":68,"props":177,"children":178},{},[179],{"type":48,"value":180},"If the request spans multiple sub-skills, execute them in pipeline order.",{"type":42,"tag":68,"props":182,"children":183},{},[184],{"type":48,"value":185},"If a sub-skill requires upstream context (engine, deployment model, endpoint) not yet in session memory, route to the upstream sub-skill first.",{"type":42,"tag":68,"props":187,"children":188},{},[189,191,196],{"type":48,"value":190},"If no sub-skill matches, activate ",{"type":42,"tag":74,"props":192,"children":194},{"className":193},[],[195],{"type":48,"value":143},{"type":48,"value":197}," first.",{"type":42,"tag":68,"props":199,"children":200},{},[201],{"type":48,"value":202},"If a script or CLI call fails, show the error to the user and suggest a specific fix before retrying.",{"type":42,"tag":57,"props":204,"children":206},{"id":205},"sub-skill-registry",[207],{"type":48,"value":208},"Sub-skill registry",{"type":42,"tag":51,"props":210,"children":211},{},[212,214,220],{"type":48,"value":213},"Each entry has: an ID (directory name under ",{"type":42,"tag":74,"props":215,"children":217},{"className":216},[],[218],{"type":48,"value":219},"references\u002F",{"type":48,"value":221},"), a domain description, semantic categories for matching, and upstream\u002Fdownstream dependencies.",{"type":42,"tag":223,"props":224,"children":225},"table",{},[226,265],{"type":42,"tag":227,"props":228,"children":229},"thead",{},[230],{"type":42,"tag":231,"props":232,"children":233},"tr",{},[234,240,245,250,255,260],{"type":42,"tag":235,"props":236,"children":237},"th",{},[238],{"type":48,"value":239},"ID",{"type":42,"tag":235,"props":241,"children":242},{},[243],{"type":48,"value":244},"Name",{"type":42,"tag":235,"props":246,"children":247},{},[248],{"type":48,"value":249},"Domain",{"type":42,"tag":235,"props":251,"children":252},{},[253],{"type":48,"value":254},"Semantic Categories",{"type":42,"tag":235,"props":256,"children":257},{},[258],{"type":48,"value":259},"Upstream",{"type":42,"tag":235,"props":261,"children":262},{},[263],{"type":48,"value":264},"Downstream",{"type":42,"tag":266,"props":267,"children":268},"tbody",{},[269,337,393,437,480,524],{"type":42,"tag":231,"props":270,"children":271},{},[272,281,286,291,296,301],{"type":42,"tag":273,"props":274,"children":275},"td",{},[276],{"type":42,"tag":74,"props":277,"children":279},{"className":278},[],[280],{"type":48,"value":143},{"type":42,"tag":273,"props":282,"children":283},{},[284],{"type":48,"value":285},"Solution Fit",{"type":42,"tag":273,"props":287,"children":288},{},[289],{"type":48,"value":290},"Gathers workload, stack, scale, latency, persistence, and budget through workspace scan + structured interview. Decides whether ElastiCache is the right service and hands off with a routing recommendation.",{"type":42,"tag":273,"props":292,"children":293},{},[294],{"type":48,"value":295},"I need a cache, speed up my app, reduce database load, lower Bedrock cost, should I use ElastiCache, what's best for my workload, evaluating cache options, ElastiCache vs X, Valkey vs X, vague new workload",{"type":42,"tag":273,"props":297,"children":298},{},[299],{"type":48,"value":300},"—",{"type":42,"tag":273,"props":302,"children":303},{},[304,310,312,317,318,324,325,330,331],{"type":42,"tag":74,"props":305,"children":307},{"className":306},[],[308],{"type":48,"value":309},"setup",{"type":48,"value":311},", ",{"type":42,"tag":74,"props":313,"children":315},{"className":314},[],[316],{"type":48,"value":79},{"type":48,"value":311},{"type":42,"tag":74,"props":319,"children":321},{"className":320},[],[322],{"type":48,"value":323},"genai",{"type":48,"value":311},{"type":42,"tag":74,"props":326,"children":328},{"className":327},[],[329],{"type":48,"value":123},{"type":48,"value":311},{"type":42,"tag":74,"props":332,"children":334},{"className":333},[],[335],{"type":48,"value":336},"migration",{"type":42,"tag":231,"props":338,"children":339},{},[340,348,353,358,363,373],{"type":42,"tag":273,"props":341,"children":342},{},[343],{"type":42,"tag":74,"props":344,"children":346},{"className":345},[],[347],{"type":48,"value":309},{"type":42,"tag":273,"props":349,"children":350},{},[351],{"type":48,"value":352},"Create and Connect",{"type":42,"tag":273,"props":354,"children":355},{},[356],{"type":48,"value":357},"Provisioning, connectivity, security, authentication, IaC, deployment choice. Gets the user to a working cache with least friction. Covers engine selection, serverless vs node-based, VPC, TLS, RBAC\u002FIAM, jump-host\u002FSSM tunnels, CLI\u002FSDK\u002FCFN\u002FCDK\u002FTerraform starters.",{"type":42,"tag":273,"props":359,"children":360},{},[361],{"type":48,"value":362},"create a cache, set up ElastiCache, provision, Valkey cluster, connect Lambda\u002FECS\u002FEKS\u002FEC2, VPC, security groups, TLS, RBAC, IAM auth, jump host, SSM tunnel, CloudFormation, CDK, Terraform, engine selection, serverless vs node-based, backup, snapshot, restore, export",{"type":42,"tag":273,"props":364,"children":365},{},[366,371],{"type":42,"tag":74,"props":367,"children":369},{"className":368},[],[370],{"type":48,"value":143},{"type":48,"value":372}," (optional)",{"type":42,"tag":273,"props":374,"children":375},{},[376,381,382,387,388],{"type":42,"tag":74,"props":377,"children":379},{"className":378},[],[380],{"type":48,"value":79},{"type":48,"value":311},{"type":42,"tag":74,"props":383,"children":385},{"className":384},[],[386],{"type":48,"value":323},{"type":48,"value":311},{"type":42,"tag":74,"props":389,"children":391},{"className":390},[],[392],{"type":48,"value":123},{"type":42,"tag":231,"props":394,"children":395},{},[396,404,409,414,419,429],{"type":42,"tag":273,"props":397,"children":398},{},[399],{"type":42,"tag":74,"props":400,"children":402},{"className":401},[],[403],{"type":48,"value":79},{"type":42,"tag":273,"props":405,"children":406},{},[407],{"type":48,"value":408},"Application Patterns",{"type":42,"tag":273,"props":410,"children":411},{},[412],{"type":48,"value":413},"Picks data structures, key schema, TTL strategy, invalidation approach, and client code for non-AI patterns: cache-aside, session store, rate limiting, leaderboards, counters, pub\u002Fsub, streams, shopping carts, job queues, activity feeds.",{"type":42,"tag":273,"props":415,"children":416},{},[417],{"type":48,"value":418},"session store, rate limiting, leaderboard, cache-aside, query caching, counters, streams, pub\u002Fsub, shopping cart, job queue, activity feed, key schema, TTL, invalidation, data structures",{"type":42,"tag":273,"props":420,"children":421},{},[422,427],{"type":42,"tag":74,"props":423,"children":425},{"className":424},[],[426],{"type":48,"value":309},{"type":48,"value":428}," (cache must exist)",{"type":42,"tag":273,"props":430,"children":431},{},[432],{"type":42,"tag":74,"props":433,"children":435},{"className":434},[],[436],{"type":48,"value":123},{"type":42,"tag":231,"props":438,"children":439},{},[440,448,453,458,463,472],{"type":42,"tag":273,"props":441,"children":442},{},[443],{"type":42,"tag":74,"props":444,"children":446},{"className":445},[],[447],{"type":48,"value":323},{"type":42,"tag":273,"props":449,"children":450},{},[451],{"type":48,"value":452},"AI and Vector Workloads",{"type":42,"tag":273,"props":454,"children":455},{},[456],{"type":48,"value":457},"Classifies request into Mode 1 (plain cache), Mode 2 (semantic response cache), or Mode 3 (full vector search). Selects Valkey and forces node-based Valkey 8.2 or above (recommend 9.0) when server-side vector similarity is needed. Covers semantic caching, agent memory, RAG retrieval, recommendation, personalization, conversation\u002Fsession persistence for AI agents, and framework wiring (Strands, mem0, LangChain).",{"type":42,"tag":273,"props":459,"children":460},{},[461],{"type":48,"value":462},"semantic cache, RAG, agent memory, conversational memory, vector search, embeddings, recommendation, personalization, Bedrock latency, Bedrock cost, LLM caching, Strands, mem0, LangChain, conversation history, AI session store, embedding provider, framework integration",{"type":42,"tag":273,"props":464,"children":465},{},[466,471],{"type":42,"tag":74,"props":467,"children":469},{"className":468},[],[470],{"type":48,"value":309},{"type":48,"value":428},{"type":42,"tag":273,"props":473,"children":474},{},[475],{"type":42,"tag":74,"props":476,"children":478},{"className":477},[],[479],{"type":48,"value":123},{"type":42,"tag":231,"props":481,"children":482},{},[483,491,496,501,506,510],{"type":42,"tag":273,"props":484,"children":485},{},[486],{"type":42,"tag":74,"props":487,"children":489},{"className":488},[],[490],{"type":48,"value":123},{"type":42,"tag":273,"props":492,"children":493},{},[494],{"type":48,"value":495},"Operate and Observe",{"type":42,"tag":273,"props":497,"children":498},{},[499],{"type":48,"value":500},"Diagnoses performance, cost, and reliability using metrics first, then recommends the smallest change. Covers dashboards, alarms, log delivery, cost reporting, event routing, troubleshooting high CPU \u002F memory \u002F replication lag \u002F connection spikes \u002F low hit rate \u002F hot keys \u002F big keys \u002F slot imbalance \u002F latency spike root cause.",{"type":42,"tag":273,"props":502,"children":503},{},[504],{"type":48,"value":505},"cache is slow, cost too high, hit rate low, high CPU, memory pressure, replication lag, connection spikes, dashboards, alarms, CloudWatch, cost comparison, troubleshoot, hot key, uneven shard load, one node pinned, big key, memory bloat, which key is biggest, keyspace distribution, prefix analysis, cost attribution by tenant, memory imbalance, one shard full, slot memory skew, latency spike, slow command incident, root cause for latency bump",{"type":42,"tag":273,"props":507,"children":508},{},[509],{"type":48,"value":300},{"type":42,"tag":273,"props":511,"children":512},{},[513,518,519],{"type":42,"tag":74,"props":514,"children":516},{"className":515},[],[517],{"type":48,"value":309},{"type":48,"value":311},{"type":42,"tag":74,"props":520,"children":522},{"className":521},[],[523],{"type":48,"value":336},{"type":42,"tag":231,"props":525,"children":526},{},[527,535,540,545,550,554],{"type":42,"tag":273,"props":528,"children":529},{},[530],{"type":42,"tag":74,"props":531,"children":533},{"className":532},[],[534],{"type":48,"value":336},{"type":42,"tag":273,"props":536,"children":537},{},[538],{"type":48,"value":539},"Engine and Platform Migration",{"type":42,"tag":273,"props":541,"children":542},{},[543],{"type":48,"value":544},"Selects the migration path and sequences preflight, validation, cutover, and rollback. Covers self-managed Redis → ElastiCache, Redis OSS → Valkey, node-based ↔ serverless, version upgrades. Hard validate-before-migrate gate.",{"type":42,"tag":273,"props":546,"children":547},{},[548],{"type":48,"value":549},"migrate, Redis OSS to Valkey, self-managed to ElastiCache, node-based to serverless, serverless to node-based, engine upgrade, version upgrade, zero-downtime cutover, rollback",{"type":42,"tag":273,"props":551,"children":552},{},[553],{"type":48,"value":300},{"type":42,"tag":273,"props":555,"children":556},{},[557,562,563],{"type":42,"tag":74,"props":558,"children":560},{"className":559},[],[561],{"type":48,"value":309},{"type":48,"value":311},{"type":42,"tag":74,"props":564,"children":566},{"className":565},[],[567],{"type":48,"value":123},{"type":42,"tag":57,"props":569,"children":571},{"id":570},"pipeline-order",[572],{"type":48,"value":573},"Pipeline order",{"type":42,"tag":51,"props":575,"children":576},{},[577],{"type":48,"value":578},"Sub-skills run independently, but common multi-step journeys follow these pipelines:",{"type":42,"tag":94,"props":580,"children":581},{},[582,618,638],{"type":42,"tag":68,"props":583,"children":584},{},[585,590,592,597,599,604,606,611,613],{"type":42,"tag":74,"props":586,"children":588},{"className":587},[],[589],{"type":48,"value":143},{"type":48,"value":591}," → ",{"type":42,"tag":74,"props":593,"children":595},{"className":594},[],[596],{"type":48,"value":309},{"type":48,"value":598}," → (",{"type":42,"tag":74,"props":600,"children":602},{"className":601},[],[603],{"type":48,"value":79},{"type":48,"value":605}," | ",{"type":42,"tag":74,"props":607,"children":609},{"className":608},[],[610],{"type":48,"value":323},{"type":48,"value":612},") → ",{"type":42,"tag":74,"props":614,"children":616},{"className":615},[],[617],{"type":48,"value":123},{"type":42,"tag":68,"props":619,"children":620},{},[621,626,627,632,633],{"type":42,"tag":74,"props":622,"children":624},{"className":623},[],[625],{"type":48,"value":336},{"type":48,"value":591},{"type":42,"tag":74,"props":628,"children":630},{"className":629},[],[631],{"type":48,"value":309},{"type":48,"value":591},{"type":42,"tag":74,"props":634,"children":636},{"className":635},[],[637],{"type":48,"value":123},{"type":42,"tag":68,"props":639,"children":640},{},[641,646,647,652,653,658],{"type":42,"tag":74,"props":642,"children":644},{"className":643},[],[645],{"type":48,"value":123},{"type":48,"value":591},{"type":42,"tag":74,"props":648,"children":650},{"className":649},[],[651],{"type":48,"value":309},{"type":48,"value":605},{"type":42,"tag":74,"props":654,"children":656},{"className":655},[],[657],{"type":48,"value":336},{"type":48,"value":659}," (if metrics indicate)",{"type":42,"tag":57,"props":661,"children":663},{"id":662},"state-handoff-requirementsjson",[664],{"type":48,"value":665},"State handoff: requirements.json",{"type":42,"tag":51,"props":667,"children":668},{},[669,674],{"type":42,"tag":74,"props":670,"children":672},{"className":671},[],[673],{"type":48,"value":107},{"type":48,"value":675}," is the single source of truth for cross-sub-skill state. Each sub-skill reads it at start and writes its section after completing work. Read before writing; merge, do not overwrite.",{"type":42,"tag":223,"props":677,"children":678},{},[679,700],{"type":42,"tag":227,"props":680,"children":681},{},[682],{"type":42,"tag":231,"props":683,"children":684},{},[685,690,695],{"type":42,"tag":235,"props":686,"children":687},{},[688],{"type":48,"value":689},"Section",{"type":42,"tag":235,"props":691,"children":692},{},[693],{"type":48,"value":694},"Owner",{"type":42,"tag":235,"props":696,"children":697},{},[698],{"type":48,"value":699},"Key fields",{"type":42,"tag":266,"props":701,"children":702},{},[703,784,918,960],{"type":42,"tag":231,"props":704,"children":705},{},[706,711,719],{"type":42,"tag":273,"props":707,"children":708},{},[709],{"type":48,"value":710},"top-level",{"type":42,"tag":273,"props":712,"children":713},{},[714],{"type":42,"tag":74,"props":715,"children":717},{"className":716},[],[718],{"type":48,"value":143},{"type":42,"tag":273,"props":720,"children":721},{},[722,728,729,735,736,742,743,749,750,756,757,763,764,770,771,777,778],{"type":42,"tag":74,"props":723,"children":725},{"className":724},[],[726],{"type":48,"value":727},"engine",{"type":48,"value":311},{"type":42,"tag":74,"props":730,"children":732},{"className":731},[],[733],{"type":48,"value":734},"deployment_model",{"type":48,"value":311},{"type":42,"tag":74,"props":737,"children":739},{"className":738},[],[740],{"type":48,"value":741},"region",{"type":48,"value":311},{"type":42,"tag":74,"props":744,"children":746},{"className":745},[],[747],{"type":48,"value":748},"runtime",{"type":48,"value":311},{"type":42,"tag":74,"props":751,"children":753},{"className":752},[],[754],{"type":48,"value":755},"patterns",{"type":48,"value":311},{"type":42,"tag":74,"props":758,"children":760},{"className":759},[],[761],{"type":48,"value":762},"use_case",{"type":48,"value":311},{"type":42,"tag":74,"props":765,"children":767},{"className":766},[],[768],{"type":48,"value":769},"vpc_id",{"type":48,"value":311},{"type":42,"tag":74,"props":772,"children":774},{"className":773},[],[775],{"type":48,"value":776},"subnet_ids",{"type":48,"value":311},{"type":42,"tag":74,"props":779,"children":781},{"className":780},[],[782],{"type":48,"value":783},"security_group_ids",{"type":42,"tag":231,"props":785,"children":786},{},[787,796,804],{"type":42,"tag":273,"props":788,"children":789},{},[790],{"type":42,"tag":74,"props":791,"children":793},{"className":792},[],[794],{"type":48,"value":795},"infrastructure",{"type":42,"tag":273,"props":797,"children":798},{},[799],{"type":42,"tag":74,"props":800,"children":802},{"className":801},[],[803],{"type":48,"value":309},{"type":42,"tag":273,"props":805,"children":806},{},[807,813,814,820,821,827,828,834,835,841,842,848,849,855,856,862,863,869,870,876,877,883,884,890,891,897,898,904,905,911,912],{"type":42,"tag":74,"props":808,"children":810},{"className":809},[],[811],{"type":48,"value":812},"cache_name",{"type":48,"value":311},{"type":42,"tag":74,"props":815,"children":817},{"className":816},[],[818],{"type":48,"value":819},"resource_id",{"type":48,"value":311},{"type":42,"tag":74,"props":822,"children":824},{"className":823},[],[825],{"type":48,"value":826},"engine_version",{"type":48,"value":311},{"type":42,"tag":74,"props":829,"children":831},{"className":830},[],[832],{"type":48,"value":833},"topology",{"type":48,"value":311},{"type":42,"tag":74,"props":836,"children":838},{"className":837},[],[839],{"type":48,"value":840},"endpoint",{"type":48,"value":311},{"type":42,"tag":74,"props":843,"children":845},{"className":844},[],[846],{"type":48,"value":847},"port",{"type":48,"value":311},{"type":42,"tag":74,"props":850,"children":852},{"className":851},[],[853],{"type":48,"value":854},"auth_model",{"type":48,"value":311},{"type":42,"tag":74,"props":857,"children":859},{"className":858},[],[860],{"type":48,"value":861},"tls",{"type":48,"value":311},{"type":42,"tag":74,"props":864,"children":866},{"className":865},[],[867],{"type":48,"value":868},"client_library",{"type":48,"value":311},{"type":42,"tag":74,"props":871,"children":873},{"className":872},[],[874],{"type":48,"value":875},"execution_path",{"type":48,"value":311},{"type":42,"tag":74,"props":878,"children":880},{"className":879},[],[881],{"type":48,"value":882},"access_mode",{"type":48,"value":311},{"type":42,"tag":74,"props":885,"children":887},{"className":886},[],[888],{"type":48,"value":889},"tunnel_instance_id",{"type":48,"value":311},{"type":42,"tag":74,"props":892,"children":894},{"className":893},[],[895],{"type":48,"value":896},"embedding_provider",{"type":48,"value":311},{"type":42,"tag":74,"props":899,"children":901},{"className":900},[],[902],{"type":48,"value":903},"embedding_model",{"type":48,"value":311},{"type":42,"tag":74,"props":906,"children":908},{"className":907},[],[909],{"type":48,"value":910},"embedding_dim",{"type":48,"value":311},{"type":42,"tag":74,"props":913,"children":915},{"className":914},[],[916],{"type":48,"value":917},"embedding_module",{"type":42,"tag":231,"props":919,"children":920},{},[921,929,937],{"type":42,"tag":273,"props":922,"children":923},{},[924],{"type":42,"tag":74,"props":925,"children":927},{"className":926},[],[928],{"type":48,"value":323},{"type":42,"tag":273,"props":930,"children":931},{},[932],{"type":42,"tag":74,"props":933,"children":935},{"className":934},[],[936],{"type":48,"value":323},{"type":42,"tag":273,"props":938,"children":939},{},[940,946,947,953,954],{"type":42,"tag":74,"props":941,"children":943},{"className":942},[],[944],{"type":48,"value":945},"mode",{"type":48,"value":311},{"type":42,"tag":74,"props":948,"children":950},{"className":949},[],[951],{"type":48,"value":952},"mode_2_path",{"type":48,"value":311},{"type":42,"tag":74,"props":955,"children":957},{"className":956},[],[958],{"type":48,"value":959},"framework",{"type":42,"tag":231,"props":961,"children":962},{},[963,971,979],{"type":42,"tag":273,"props":964,"children":965},{},[966],{"type":42,"tag":74,"props":967,"children":969},{"className":968},[],[970],{"type":48,"value":336},{"type":42,"tag":273,"props":972,"children":973},{},[974],{"type":42,"tag":74,"props":975,"children":977},{"className":976},[],[978],{"type":48,"value":336},{"type":42,"tag":273,"props":980,"children":981},{},[982,988,989,995,996,1002,1003],{"type":42,"tag":74,"props":983,"children":985},{"className":984},[],[986],{"type":48,"value":987},"source_type",{"type":48,"value":311},{"type":42,"tag":74,"props":990,"children":992},{"className":991},[],[993],{"type":48,"value":994},"source_host",{"type":48,"value":311},{"type":42,"tag":74,"props":997,"children":999},{"className":998},[],[1000],{"type":48,"value":1001},"migration_path",{"type":48,"value":311},{"type":42,"tag":74,"props":1004,"children":1006},{"className":1005},[],[1007],{"type":48,"value":1008},"cutover_status",{"type":42,"tag":1010,"props":1011,"children":1012},"blockquote",{},[1013],{"type":42,"tag":51,"props":1014,"children":1015},{},[1016,1021,1023,1028,1030,1035,1037,1042],{"type":42,"tag":86,"props":1017,"children":1018},{},[1019],{"type":48,"value":1020},"Ownership note:",{"type":48,"value":1022}," ",{"type":42,"tag":74,"props":1024,"children":1026},{"className":1025},[],[1027],{"type":48,"value":734},{"type":48,"value":1029}," is set by ",{"type":42,"tag":74,"props":1031,"children":1033},{"className":1032},[],[1034],{"type":48,"value":143},{"type":48,"value":1036}," during initial interview. ",{"type":42,"tag":74,"props":1038,"children":1040},{"className":1039},[],[1041],{"type":48,"value":336},{"type":48,"value":1043}," may update it after an engine or deployment model switch (e.g., node-based to serverless).",{"type":42,"tag":51,"props":1045,"children":1046},{},[1047,1049,1055,1057,1063,1065,1071,1073,1078],{"type":48,"value":1048},"requirements.json should include ",{"type":42,"tag":74,"props":1050,"children":1052},{"className":1051},[],[1053],{"type":48,"value":1054},"\"schema_version\": 1",{"type":48,"value":1056}," and ",{"type":42,"tag":74,"props":1058,"children":1060},{"className":1059},[],[1061],{"type":48,"value":1062},"\"last_updated\": \"\u003CISO timestamp>\"",{"type":48,"value":1064}," at the top level. Every sub-skill that writes to requirements.json must update ",{"type":42,"tag":74,"props":1066,"children":1068},{"className":1067},[],[1069],{"type":48,"value":1070},"last_updated",{"type":48,"value":1072},". If ",{"type":42,"tag":74,"props":1074,"children":1076},{"className":1075},[],[1077],{"type":48,"value":1070},{"type":48,"value":1079}," is older than 7 days, warn the user that cached state may be stale.",{"type":42,"tag":51,"props":1081,"children":1082},{},[1083],{"type":48,"value":1084},"requirements.json tracks one active cache. If the user works with multiple caches in the same project, confirm which cache is active before reading or writing state.",{"type":42,"tag":51,"props":1086,"children":1087},{},[1088,1090,1096],{"type":48,"value":1089},"When a sub-skill needs upstream context (engine, endpoint, auth model), check requirements.json first. If the field is ",{"type":42,"tag":74,"props":1091,"children":1093},{"className":1092},[],[1094],{"type":48,"value":1095},"null",{"type":48,"value":1097}," or the file does not exist, route to the upstream sub-skill.",{"type":42,"tag":57,"props":1099,"children":1101},{"id":1100},"global-rules-apply-to-every-sub-skill",[1102],{"type":48,"value":1103},"Global rules (apply to every sub-skill)",{"type":42,"tag":64,"props":1105,"children":1106},{},[1107,1117,1127,1137,1180,1204,1214,1255,1289],{"type":42,"tag":68,"props":1108,"children":1109},{},[1110,1115],{"type":42,"tag":86,"props":1111,"children":1112},{},[1113],{"type":48,"value":1114},"Execution path.",{"type":48,"value":1116}," Use AWS CLI, SDK (boto3), CloudFormation, or CDK as the primary path for control-plane work. Use valkey-py as the primary path for data-plane work.",{"type":42,"tag":68,"props":1118,"children":1119},{},[1120,1125],{"type":42,"tag":86,"props":1121,"children":1122},{},[1123],{"type":48,"value":1124},"Response depth.",{"type":48,"value":1126}," Summary (2-3 sentences) for \"should I\" or \"which\" questions. Standard (recommendation + config + code + next steps) by default. Expert (full decision matrix with alternatives, cost, security caveats) for \"why\" or \"compare all\" questions. Escalate on user request; never downgrade unprompted.",{"type":42,"tag":68,"props":1128,"children":1129},{},[1130,1135],{"type":42,"tag":86,"props":1131,"children":1132},{},[1133],{"type":48,"value":1134},"Session memory.",{"type":48,"value":1136}," Track region, VPC, engine, deployment model, auth model, compute runtime, and language. Carry forward across sub-skills. Do not re-ask. If the user overrides a value, update it everywhere. Inferred values (from workspace scan or IaC) must be re-confirmed before high-risk decisions (engine, deployment model, security posture); low-risk inferences (language, framework, region) can be used as defaults silently.",{"type":42,"tag":68,"props":1138,"children":1139},{},[1140,1145,1147,1153,1155,1163,1165,1171,1173,1178],{"type":42,"tag":86,"props":1141,"children":1142},{},[1143],{"type":48,"value":1144},"Source priority.",{"type":48,"value":1146}," Always answer from skill-local files first (sub-skill references, then ",{"type":42,"tag":74,"props":1148,"children":1150},{"className":1149},[],[1151],{"type":48,"value":1152},"scripts\u002F",{"type":48,"value":1154},"). Do not fetch external documentation or web search unless the local files cannot answer the query. When local files are insufficient, fall back to official AWS docs: ",{"type":42,"tag":1156,"props":1157,"children":1161},"a",{"href":1158,"rel":1159},"https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonElastiCache\u002Flatest\u002Fdg\u002F",[1160],"nofollow",[1162],{"type":48,"value":1158},{"type":48,"value":1164}," for features and ",{"type":42,"tag":1156,"props":1166,"children":1169},{"href":1167,"rel":1168},"https:\u002F\u002Faws.amazon.com\u002Felasticache\u002Fpricing\u002F",[1160],[1170],{"type":48,"value":1167},{"type":48,"value":1172}," for pricing. Never invent price points or version constraints. If the user references a Valkey or Redis version, feature, or pricing tier not covered in local files, fall back to ",{"type":42,"tag":1156,"props":1174,"children":1176},{"href":1158,"rel":1175},[1160],[1177],{"type":48,"value":1158},{"type":48,"value":1179}," before answering. Do not extrapolate from local content that may be outdated.",{"type":42,"tag":68,"props":1181,"children":1182},{},[1183,1188,1190,1195,1197,1202],{"type":42,"tag":86,"props":1184,"children":1185},{},[1186],{"type":48,"value":1187},"Freshness disclaimer.",{"type":48,"value":1189}," When outputting pricing, version constraints, or feature availability, include a one-line disclaimer: \"For current pricing see ",{"type":42,"tag":1156,"props":1191,"children":1193},{"href":1167,"rel":1192},[1160],[1194],{"type":48,"value":1167},{"type":48,"value":1196},". For current feature availability see ",{"type":42,"tag":1156,"props":1198,"children":1200},{"href":1158,"rel":1199},[1160],[1201],{"type":48,"value":1158},{"type":48,"value":1203},".\"",{"type":42,"tag":68,"props":1205,"children":1206},{},[1207,1212],{"type":42,"tag":86,"props":1208,"children":1209},{},[1210],{"type":48,"value":1211},"Connection safety.",{"type":48,"value":1213}," Never create a Valkey\u002FRedis client at module level (top of file, import time). Initialize connections inside a function or on first use. Module-level connections crash applications that import the module before the cache is reachable.",{"type":42,"tag":68,"props":1215,"children":1216},{},[1217,1222,1224,1230,1232,1238,1240,1246,1247,1253],{"type":42,"tag":86,"props":1218,"children":1219},{},[1220],{"type":48,"value":1221},"Code environment.",{"type":48,"value":1223}," Use ",{"type":42,"tag":74,"props":1225,"children":1227},{"className":1226},[],[1228],{"type":48,"value":1229},"python3",{"type":48,"value":1231}," (not ",{"type":42,"tag":74,"props":1233,"children":1235},{"className":1234},[],[1236],{"type":48,"value":1237},"python",{"type":48,"value":1239},") in all commands and shebangs. Do not generate ",{"type":42,"tag":74,"props":1241,"children":1243},{"className":1242},[],[1244],{"type":48,"value":1245},"pip install",{"type":48,"value":125},{"type":42,"tag":74,"props":1248,"children":1250},{"className":1249},[],[1251],{"type":48,"value":1252},"pytest",{"type":48,"value":1254}," commands in application code. Prefer the agent's file-writing tool over shell redirection for writing files.",{"type":42,"tag":68,"props":1256,"children":1257},{},[1258,1263,1265,1271,1273,1279,1281,1287],{"type":42,"tag":86,"props":1259,"children":1260},{},[1261],{"type":48,"value":1262},"Input validation (write operations only).",{"type":48,"value":1264}," Before running any create, modify, or delete CLI command or SDK call that uses user-provided values (cache name, region, subnet IDs, security group IDs, VPC ID, KMS key, snapshot name), validate them with ",{"type":42,"tag":74,"props":1266,"children":1268},{"className":1267},[],[1269],{"type":48,"value":1270},"scripts\u002Finput_validator.py",{"type":48,"value":1272},". Run ",{"type":42,"tag":74,"props":1274,"children":1276},{"className":1275},[],[1277],{"type":48,"value":1278},"python3 scripts\u002Finput_validator.py cache_name=\u003Cval> region=\u003Cval> ...",{"type":48,"value":1280}," or import ",{"type":42,"tag":74,"props":1282,"children":1284},{"className":1283},[],[1285],{"type":48,"value":1286},"validate_all",{"type":48,"value":1288}," as a library. Skip validation for read-only operations (describe, list) where bad input is harmless.",{"type":42,"tag":68,"props":1290,"children":1291},{},[1292,1297,1299,1305,1306,1312,1313,1319,1321,1325,1331,1334,1336,1342,1345,1347,1353],{"type":42,"tag":86,"props":1293,"children":1294},{},[1295],{"type":48,"value":1296},"Resource tagging (always apply on resource creation).",{"type":48,"value":1298}," When creating any cache (",{"type":42,"tag":74,"props":1300,"children":1302},{"className":1301},[],[1303],{"type":48,"value":1304},"create-serverless-cache",{"type":48,"value":311},{"type":42,"tag":74,"props":1307,"children":1309},{"className":1308},[],[1310],{"type":48,"value":1311},"create-replication-group",{"type":48,"value":311},{"type":42,"tag":74,"props":1314,"children":1316},{"className":1315},[],[1317],{"type":48,"value":1318},"create-cache-cluster",{"type":48,"value":1320},"), ALWAYS include these tags:",{"type":42,"tag":1322,"props":1323,"children":1324},"br",{},[],{"type":42,"tag":74,"props":1326,"children":1328},{"className":1327},[],[1329],{"type":48,"value":1330},"--tags Key=managed_by,Value=aws-skills Key=skill,Value=elasticache Key=skill_version,Value=1.0.0 Key=created_by,Value=elasticache-skill Key=generation_model,Value={your-model-id}",{"type":42,"tag":1322,"props":1332,"children":1333},{},[],{"type":48,"value":1335},"Example: ",{"type":42,"tag":74,"props":1337,"children":1339},{"className":1338},[],[1340],{"type":48,"value":1341},"--tags Key=managed_by,Value=aws-skills Key=skill,Value=elasticache Key=skill_version,Value=1.0.0 Key=created_by,Value=elasticache-skill Key=generation_model,Value=claude-sonnet-4-20250514",{"type":42,"tag":1322,"props":1343,"children":1344},{},[],{"type":48,"value":1346},"Set ",{"type":42,"tag":74,"props":1348,"children":1350},{"className":1349},[],[1351],{"type":48,"value":1352},"generation_model",{"type":48,"value":1354}," to your own model identifier. Include these tags even if the user does not mention tagging. If the user provides additional tags, append these to their tags rather than replacing them.",{"type":42,"tag":57,"props":1356,"children":1358},{"id":1357},"reference-loading",[1359],{"type":48,"value":1360},"Reference loading",{"type":42,"tag":51,"props":1362,"children":1363},{},[1364],{"type":48,"value":1365},"Load additional references only when the current turn's answer requires them.",{"type":42,"tag":51,"props":1367,"children":1368},{},[1369],{"type":48,"value":1370},"On-demand pointers (not preloaded; fetch when the trigger applies):",{"type":42,"tag":94,"props":1372,"children":1373},{},[1374,1385,1396,1407,1418,1429,1440,1451,1462,1473,1484,1495,1506,1517,1528],{"type":42,"tag":68,"props":1375,"children":1376},{},[1377,1383],{"type":42,"tag":74,"props":1378,"children":1380},{"className":1379},[],[1381],{"type":48,"value":1382},"references\u002Fshared-ux\u002Fproduction-readiness.md",{"type":48,"value":1384}," — when the user asks if their cache is ready for production, or after setup completes and the user wants to go to production",{"type":42,"tag":68,"props":1386,"children":1387},{},[1388,1394],{"type":42,"tag":74,"props":1389,"children":1391},{"className":1390},[],[1392],{"type":48,"value":1393},"references\u002Fshared-ux\u002Faction-safety.md",{"type":48,"value":1395}," — before any destructive action (risk levels, never-auto-execute list)",{"type":42,"tag":68,"props":1397,"children":1398},{},[1399,1405],{"type":42,"tag":74,"props":1400,"children":1402},{"className":1401},[],[1403],{"type":48,"value":1404},"references\u002Fshared-ux\u002Ferror-remediation.md",{"type":48,"value":1406}," — when the user hits a specific ElastiCache error code (MOVED, CROSSSLOT, CLUSTERDOWN, MULTI\u002FEXEC+IAM, etc.)",{"type":42,"tag":68,"props":1408,"children":1409},{},[1410,1416],{"type":42,"tag":74,"props":1411,"children":1413},{"className":1412},[],[1414],{"type":48,"value":1415},"references\u002Fshared-foundation\u002Fboundary-doc.md",{"type":48,"value":1417}," — when the user asks what this skill covers",{"type":42,"tag":68,"props":1419,"children":1420},{},[1421,1427],{"type":42,"tag":74,"props":1422,"children":1424},{"className":1423},[],[1425],{"type":48,"value":1426},"references\u002Fshared-foundation\u002Fattribution.md",{"type":48,"value":1428}," — when generating CLI commands, SDK code, or IaC templates",{"type":42,"tag":68,"props":1430,"children":1431},{},[1432,1438],{"type":42,"tag":74,"props":1433,"children":1435},{"className":1434},[],[1436],{"type":48,"value":1437},"references\u002Fshared-foundation\u002Farchitecture-diagrams.md",{"type":48,"value":1439}," — when the user asks for architecture diagrams or visual reference",{"type":42,"tag":68,"props":1441,"children":1442},{},[1443,1449],{"type":42,"tag":74,"props":1444,"children":1446},{"className":1445},[],[1447],{"type":48,"value":1448},"references\u002Fshared-runtime\u002Flambda.md",{"type":48,"value":1450}," — when connecting from Lambda (cold start gotchas, IAM auth code, lazy init)",{"type":42,"tag":68,"props":1452,"children":1453},{},[1454,1460],{"type":42,"tag":74,"props":1455,"children":1457},{"className":1456},[],[1458],{"type":48,"value":1459},"references\u002Fshared-runtime\u002Fecs.md",{"type":48,"value":1461}," — when connecting from ECS (SIGTERM shutdown, connection pool drain, task definition)",{"type":42,"tag":68,"props":1463,"children":1464},{},[1465,1471],{"type":42,"tag":74,"props":1466,"children":1468},{"className":1467},[],[1469],{"type":48,"value":1470},"references\u002Fshared-runtime\u002Feks.md",{"type":48,"value":1472}," — when connecting from EKS (IRSA, service mesh bypass, SecurityGroupPolicy CRD)",{"type":42,"tag":68,"props":1474,"children":1475},{},[1476,1482],{"type":42,"tag":74,"props":1477,"children":1479},{"className":1478},[],[1480],{"type":48,"value":1481},"references\u002Fshared-runtime\u002Fapi-gateway.md",{"type":48,"value":1483}," — when integrating with API Gateway (no direct path, caching layers comparison)",{"type":42,"tag":68,"props":1485,"children":1486},{},[1487,1493],{"type":42,"tag":74,"props":1488,"children":1490},{"className":1489},[],[1491],{"type":48,"value":1492},"references\u002Fshared-runtime\u002Frds-acceleration.md",{"type":48,"value":1494}," — when caching RDS\u002FAurora queries (thundering herd, stampede protection, invalidation)",{"type":42,"tag":68,"props":1496,"children":1497},{},[1498,1504],{"type":42,"tag":74,"props":1499,"children":1501},{"className":1500},[],[1502],{"type":48,"value":1503},"references\u002Fshared-runtime\u002Fsecret-injection.md",{"type":48,"value":1505}," — when the user asks about credential management per compute platform",{"type":42,"tag":68,"props":1507,"children":1508},{},[1509,1515],{"type":42,"tag":74,"props":1510,"children":1512},{"className":1511},[],[1513],{"type":48,"value":1514},"references\u002Fshared-security\u002Fencryption-defaults.md",{"type":48,"value":1516}," — when adding encryption to an existing unencrypted cluster (TLS two-step migration, at-rest immutability)",{"type":42,"tag":68,"props":1518,"children":1519},{},[1520,1526],{"type":42,"tag":74,"props":1521,"children":1523},{"className":1522},[],[1524],{"type":48,"value":1525},"references\u002Fshared-security\u002Fconfig-guardrails.md",{"type":48,"value":1527}," — when the user wants continuous compliance monitoring (AWS Config rules, custom Lambda rules)",{"type":42,"tag":68,"props":1529,"children":1530},{},[1531,1537],{"type":42,"tag":74,"props":1532,"children":1534},{"className":1533},[],[1535],{"type":48,"value":1536},"references\u002Fshared-security\u002Fvpc-patterns.md",{"type":48,"value":1538}," — when debugging port\u002Fsecurity-group issues (port 6380 serverless reader, anti-patterns)",{"type":42,"tag":1010,"props":1540,"children":1541},{},[1542],{"type":42,"tag":51,"props":1543,"children":1544},{},[1545,1550,1551,1556,1558,1563,1564,1569,1570,1575,1576,1581,1582,1587,1588,1593,1595,1601,1603,1609,1610,1616,1617,1623,1624,1630],{"type":42,"tag":86,"props":1546,"children":1547},{},[1548],{"type":48,"value":1549},"Folder convention:",{"type":48,"value":1022},{"type":42,"tag":74,"props":1552,"children":1554},{"className":1553},[],[1555],{"type":48,"value":219},{"type":48,"value":1557}," contains 10 folders. 6 match the sub-skills (",{"type":42,"tag":74,"props":1559,"children":1561},{"className":1560},[],[1562],{"type":48,"value":143},{"type":48,"value":311},{"type":42,"tag":74,"props":1565,"children":1567},{"className":1566},[],[1568],{"type":48,"value":309},{"type":48,"value":311},{"type":42,"tag":74,"props":1571,"children":1573},{"className":1572},[],[1574],{"type":48,"value":79},{"type":48,"value":311},{"type":42,"tag":74,"props":1577,"children":1579},{"className":1578},[],[1580],{"type":48,"value":323},{"type":48,"value":311},{"type":42,"tag":74,"props":1583,"children":1585},{"className":1584},[],[1586],{"type":48,"value":123},{"type":48,"value":311},{"type":42,"tag":74,"props":1589,"children":1591},{"className":1590},[],[1592],{"type":48,"value":336},{"type":48,"value":1594},") and are routing destinations. The 4 ",{"type":42,"tag":74,"props":1596,"children":1598},{"className":1597},[],[1599],{"type":48,"value":1600},"shared-*",{"type":48,"value":1602}," folders (",{"type":42,"tag":74,"props":1604,"children":1606},{"className":1605},[],[1607],{"type":48,"value":1608},"shared-foundation",{"type":48,"value":311},{"type":42,"tag":74,"props":1611,"children":1613},{"className":1612},[],[1614],{"type":48,"value":1615},"shared-ux",{"type":48,"value":311},{"type":42,"tag":74,"props":1618,"children":1620},{"className":1619},[],[1621],{"type":48,"value":1622},"shared-security",{"type":48,"value":311},{"type":42,"tag":74,"props":1625,"children":1627},{"className":1626},[],[1628],{"type":48,"value":1629},"shared-runtime",{"type":48,"value":1631},") are cross-cutting material loaded on demand, not routing destinations.",{"type":42,"tag":57,"props":1633,"children":1635},{"id":1634},"guardrails",[1636],{"type":48,"value":1637},"Guardrails",{"type":42,"tag":223,"props":1639,"children":1640},{},[1641,1657],{"type":42,"tag":227,"props":1642,"children":1643},{},[1644],{"type":42,"tag":231,"props":1645,"children":1646},{},[1647,1652],{"type":42,"tag":235,"props":1648,"children":1649},{},[1650],{"type":48,"value":1651},"Priority",{"type":42,"tag":235,"props":1653,"children":1654},{},[1655],{"type":48,"value":1656},"Rule",{"type":42,"tag":266,"props":1658,"children":1659},{},[1660,1678,1705,1723,1740,1758],{"type":42,"tag":231,"props":1661,"children":1662},{},[1663,1668],{"type":42,"tag":273,"props":1664,"children":1665},{},[1666],{"type":48,"value":1667},"CRITICAL",{"type":42,"tag":273,"props":1669,"children":1670},{},[1671,1676],{"type":42,"tag":86,"props":1672,"children":1673},{},[1674],{"type":48,"value":1675},"Vector search MUST use node-based Valkey 8.2 or above.",{"type":48,"value":1677}," Serverless does NOT support vector search. Never suggest serverless for vector search. Apply this regardless of which sub-skill activates.",{"type":42,"tag":231,"props":1679,"children":1680},{},[1681,1685],{"type":42,"tag":273,"props":1682,"children":1683},{},[1684],{"type":48,"value":1667},{"type":42,"tag":273,"props":1686,"children":1687},{},[1688,1690,1695,1697,1703],{"type":48,"value":1689},"Do ",{"type":42,"tag":86,"props":1691,"children":1692},{},[1693],{"type":48,"value":1694},"not",{"type":48,"value":1696}," invent price points or version constraints. Use ",{"type":42,"tag":74,"props":1698,"children":1700},{"className":1699},[],[1701],{"type":48,"value":1702},"scripts\u002Fprice_calculator.py",{"type":48,"value":1704}," and current AWS docs when precision matters.",{"type":42,"tag":231,"props":1706,"children":1707},{},[1708,1713],{"type":42,"tag":273,"props":1709,"children":1710},{},[1711],{"type":48,"value":1712},"HIGH",{"type":42,"tag":273,"props":1714,"children":1715},{},[1716,1717,1721],{"type":48,"value":1689},{"type":42,"tag":86,"props":1718,"children":1719},{},[1720],{"type":48,"value":1694},{"type":48,"value":1722}," recommend Memcached when the user needs persistence, replication, RBAC or IAM auth, sorted sets, streams, pub\u002Fsub, or vector search.",{"type":42,"tag":231,"props":1724,"children":1725},{},[1726,1730],{"type":42,"tag":273,"props":1727,"children":1728},{},[1729],{"type":48,"value":1712},{"type":42,"tag":273,"props":1731,"children":1732},{},[1733,1734,1738],{"type":48,"value":1689},{"type":42,"tag":86,"props":1735,"children":1736},{},[1737],{"type":48,"value":1694},{"type":48,"value":1739}," assume local laptop access works directly. ElastiCache is VPC-centric; explain VPC, tunnel, or jump-host access when needed.",{"type":42,"tag":231,"props":1741,"children":1742},{},[1743,1748],{"type":42,"tag":273,"props":1744,"children":1745},{},[1746],{"type":48,"value":1747},"STANDARD",{"type":42,"tag":273,"props":1749,"children":1750},{},[1751,1752,1756],{"type":48,"value":1689},{"type":42,"tag":86,"props":1753,"children":1754},{},[1755],{"type":48,"value":1694},{"type":48,"value":1757}," trigger on every generic Redis mention. Trigger when the user is clearly asking about AWS, managed caching, migration, connectivity, pricing, operations, or AWS service integration.",{"type":42,"tag":231,"props":1759,"children":1760},{},[1761,1765],{"type":42,"tag":273,"props":1762,"children":1763},{},[1764],{"type":48,"value":1747},{"type":42,"tag":273,"props":1766,"children":1767},{},[1768,1770,1775],{"type":48,"value":1769},"For ambiguous \"cache\" requests inside AWS contexts, activate this skill and start with ",{"type":42,"tag":74,"props":1771,"children":1773},{"className":1772},[],[1774],{"type":48,"value":143},{"type":48,"value":145},{"type":42,"tag":57,"props":1777,"children":1779},{"id":1778},"product-truths",[1780],{"type":48,"value":1781},"Product truths",{"type":42,"tag":94,"props":1783,"children":1784},{},[1785,1790,1795,1800,1805,1810,1815,1820],{"type":42,"tag":68,"props":1786,"children":1787},{},[1788],{"type":48,"value":1789},"ElastiCache Serverless deploys in under a minute and removes infrastructure management.",{"type":42,"tag":68,"props":1791,"children":1792},{},[1793],{"type":48,"value":1794},"Valkey serverless pricing is 33% lower than other supported engines; node-based Valkey pricing is 20% lower.",{"type":42,"tag":68,"props":1796,"children":1797},{},[1798],{"type":48,"value":1799},"Serverless caches have in-transit encryption always enabled (cannot be disabled).",{"type":42,"tag":68,"props":1801,"children":1802},{},[1803],{"type":48,"value":1804},"IAM auth is available for all ElastiCache Valkey versions (7.2 is the baseline Valkey version on ElastiCache) and Redis OSS 7.0+.",{"type":42,"tag":68,"props":1806,"children":1807},{},[1808],{"type":48,"value":1809},"Valkey version ladder: 7.2 (baseline), 8.0 (20% more data per node (capacity improvement), per-slot metrics), 8.1 (Bloom filters, COMMANDLOG, SET IFEQ, 20% less memory via new hash table (efficiency improvement)), 8.2 (vector search), 9.0 (recommended default for new clusters). Recommend Valkey 9.0 for new clusters unless a specific feature dictates otherwise.",{"type":42,"tag":68,"props":1811,"children":1812},{},[1813],{"type":48,"value":1814},"Vector search is available for Valkey 8.2 or above on node-based clusters (recommend 9.0).",{"type":42,"tag":68,"props":1816,"children":1817},{},[1818],{"type":48,"value":1819},"Global Datastore is available for node-based clusters only. It does not support IPv6 or Local Zones. Global Datastore supports AUTH and RBAC. Cross-region failover must be promoted manually (no autofailover across regions). At-rest encryption must be enabled on all clusters in the Global Datastore, but each cluster can use a separate KMS key per region.",{"type":42,"tag":68,"props":1821,"children":1822},{},[1823,1825,1831,1833,1839,1841,1847,1848,1854,1855,1861,1862,1868,1869,1875,1876,1882,1884,1890],{"type":48,"value":1824},"Online migration from self-managed Redis to ElastiCache requires: (source) AUTH must not be enabled, ",{"type":42,"tag":74,"props":1826,"children":1828},{"className":1827},[],[1829],{"type":48,"value":1830},"protected-mode",{"type":48,"value":1832}," set to ",{"type":42,"tag":74,"props":1834,"children":1836},{"className":1835},[],[1837],{"type":48,"value":1838},"no",{"type":48,"value":1840},", replication and administrative commands must not be renamed (e.g., ",{"type":42,"tag":74,"props":1842,"children":1844},{"className":1843},[],[1845],{"type":48,"value":1846},"sync",{"type":48,"value":311},{"type":42,"tag":74,"props":1849,"children":1851},{"className":1850},[],[1852],{"type":48,"value":1853},"psync",{"type":48,"value":311},{"type":42,"tag":74,"props":1856,"children":1858},{"className":1857},[],[1859],{"type":48,"value":1860},"info",{"type":48,"value":311},{"type":42,"tag":74,"props":1863,"children":1865},{"className":1864},[],[1866],{"type":48,"value":1867},"config",{"type":48,"value":311},{"type":42,"tag":74,"props":1870,"children":1872},{"className":1871},[],[1873],{"type":48,"value":1874},"command",{"type":48,"value":311},{"type":42,"tag":74,"props":1877,"children":1879},{"className":1878},[],[1880],{"type":48,"value":1881},"cluster",{"type":48,"value":1883},"); (target) encryption in-transit disabled, Multi-AZ enabled, engine version Redis OSS 5.0.6+ or Valkey 7.2+, not part of a Global Datastore, data tiering disabled. Shard counts must match between source and target. All source Redis instances must use the same port. Online migration is not supported for serverless caches (node-based targets only). See ",{"type":42,"tag":74,"props":1885,"children":1887},{"className":1886},[],[1888],{"type":48,"value":1889},"references\u002Fmigration\u002Ftopology-validation.md",{"type":48,"value":1891}," for the full checklist.",{"items":1893,"total":1995},[1894,1911,1926,1941,1956,1966,1981],{"slug":1895,"name":1895,"fn":1896,"description":1897,"org":1898,"tags":1899,"stars":24,"repoUrl":25,"updatedAt":1910},"agents-build","add capabilities to existing agent projects","Use when adding capabilities to an existing agent project — memory, app integration, VPC, multi-agent, migration, model changes, browser, code interpreter, or resource removal. Triggers on: \"add memory\", \"remember across sessions\", \"call agent from app\", \"invoke agent from code\", \"auth to call agent\", \"streaming responses\", \"VPC\", \"VPC connectivity\", \"VPC error\", \"can't reach from VPC\", \"multi-agent\", \"A2A\", \"A2A auth\", \"orchestrator not delegating\", \"specialist not called\", \"migrate Bedrock Agent\", \"after import\", \"migration issue\", \"framework for migration\", \"change model\", \"browser tool\", \"code interpreter\", \"delete agent\", \"tear down\", \"agentcore remove\", \"cross-account memory\", \"resource-based policy on memory\", \"pay for x402 content\", \"402 Payment Required\", \"microtransactions\", \"paid API or tool\". Not for connecting to external APIs via Gateway — use agents-connect. Not for scaffolding a new project — use agents-get-started. Not for CLI\u002Fdev server errors — use agents-debug. Strands vs LangGraph in a migration context routes here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1900,1903,1906,1907],{"name":1901,"slug":1902,"type":15},"Agents","agents",{"name":1904,"slug":1905,"type":15},"Automation","automation",{"name":20,"slug":8,"type":15},{"name":1908,"slug":1909,"type":15},"Engineering","engineering","2026-07-12T08:42:53.812877",{"slug":1912,"name":1912,"fn":1913,"description":1914,"org":1915,"tags":1916,"stars":24,"repoUrl":25,"updatedAt":1925},"agents-connect","connect agents to external services","Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies. Handles gateway setup, target types, outbound auth (OAuth, API key, IAM), credentials, and Cedar policy authoring. Triggers on: \"connect to API\", \"add gateway\", \"connect to MCP server\", \"Lambda tools\", \"OpenAPI\", \"gateway target\", \"Cedar policy\", \"restrict tools\", \"policy engine\", \"gateway auth error\", \"store API key\", \"outbound credential\", \"env var API key\", \"API key None after deploy\", \"credential not available after deploy\", \"should this be a gateway target\", \"give my agent tools\", \"add tools to agent\". Not for inbound auth (who can call your agent) — use agents-harden. Not for debugging agent behavior — use agents-debug. Not for VPC networking errors (agent can't reach APIs due to VPC) — use agents-build. Not for creating or hosting a new MCP server project — use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1917,1918,1921,1924],{"name":1901,"slug":1902,"type":15},{"name":1919,"slug":1920,"type":15},"API Development","api-development",{"name":1922,"slug":1923,"type":15},"Authentication","authentication",{"name":20,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":1927,"name":1927,"fn":1928,"description":1929,"org":1930,"tags":1931,"stars":24,"repoUrl":25,"updatedAt":1940},"agents-debug","debug agent and environment issues","Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisites when the CLI itself isn't working. Triggers on: \"agent not working\", \"wrong answer\", \"agent error\", \"tool call failing\", \"debug agent\", \"check logs\", \"read traces\", \"broken\", \"500 error\", \"424 error\", \"model access denied\", \"command not found\", \"stuck in DELETING\", \"maxVms exceeded\", \"cold start diagnosis\", \"cold start slow\", \"agentcore create error\", \"create failed\", \"exit code 7\", \"connection refused local dev\". Not for deploy failures — use agents-deploy. Not for performance tuning without errors — use agents-optimize. Not for VPC configuration — use agents-build. Not for observability setup or missing logs — use agents-optimize.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1932,1933,1934,1937],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":1935,"slug":1936,"type":15},"Debugging","debugging",{"name":1938,"slug":1939,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":1942,"name":1942,"fn":1943,"description":1944,"org":1945,"tags":1946,"stars":24,"repoUrl":25,"updatedAt":1955},"agents-deploy","deploy AI agents to AWS","Use when deploying your agent to AWS, or when a deploy has failed. Handles pre-flight validation, CDK\u002FIAM\u002Fquota error diagnosis, version management, rollback, and canary deployments. Triggers on: \"deploy my agent\", \"agentcore deploy\", \"deploy failed\", \"CDK error\", \"rollback\", \"canary deploy\", \"pin version\", \"redeploy\", \"deploy stuck\". Not for production hardening — use agents-harden. Not for adding capabilities before deploy — use agents-build or agents-connect. Not for VPC configuration errors — use agents-build.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1947,1948,1949,1952],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":1950,"slug":1951,"type":15},"CI\u002FCD","ci-cd",{"name":1953,"slug":1954,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":1957,"name":1957,"fn":1958,"description":1959,"org":1960,"tags":1961,"stars":24,"repoUrl":25,"updatedAt":1965},"agents-get-started","scaffold and deploy new agent projects","Use when a developer wants to create a new agent project or get started with AgentCore. Handles framework selection, project scaffolding, first deploy, and first invocation. Triggers on: \"build an agent\", \"create an agent\", \"get started\", \"new project\", \"agentcore create\", \"which framework\", \"Strands vs LangGraph\", \"hello world agent\", \"first agent\", \"create MCP server\", \"host MCP server\", \"agentcore dev\", \"dev server\", \"what port\", \"local development\". Not for adding capabilities to existing projects — use agents-build or agents-connect. Strands vs LangGraph in a migration context routes to agents-build, not here. Connecting to an existing MCP server routes to agents-connect, not here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1962,1963,1964],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":1953,"slug":1954,"type":15},"2026-07-12T08:42:51.963247",{"slug":1967,"name":1967,"fn":1968,"description":1969,"org":1970,"tags":1971,"stars":24,"repoUrl":25,"updatedAt":1980},"agents-harden","harden agents for production","Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: \"production checklist\", \"harden agent\", \"production ready\", \"secure agent\", \"inbound auth\", \"going live\", \"cold start optimization\", \"session lifecycle\", \"StopRuntimeSession\", \"quota\", \"throttling\", \"maxVms\", \"rate limit\", \"security audit of outbound API calls\", \"gateway target audit for production\", \"restrict who can call\", \"lock down endpoint\", \"only our app can call\". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1972,1973,1974,1977],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":1975,"slug":1976,"type":15},"Best Practices","best-practices",{"name":1978,"slug":1979,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":1982,"name":1982,"fn":1983,"description":1984,"org":1985,"tags":1986,"stars":24,"repoUrl":25,"updatedAt":1994},"agents-optimize","optimize agent quality and performance","Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI\u002FCD quality gates, observability, or cost optimization. Triggers on: \"evaluate my agent\", \"add evaluator\", \"measure quality\", \"quality gate\", \"run evals\", \"agent too slow\", \"why is it slow\", \"reduce latency\", \"set up observability\", \"CloudWatch dashboard\", \"how much does my agent cost\", \"cost optimization\", \"logs not showing up\", \"logs missing\", \"spans not found\", \"eval failing\", \"eval error\", \"dev traces\", \"local traces\", \"agentcore dev traces\", \"traces to CloudWatch\". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1987,1988,1989,1992,1993],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":1990,"slug":1991,"type":15},"Evals","evals",{"name":1938,"slug":1939,"type":15},{"name":13,"slug":14,"type":15},"2026-07-12T08:42:56.488105",114,{"items":1997,"total":2112},[1998,2005,2012,2019,2026,2032,2039,2047,2062,2075,2087,2102],{"slug":1895,"name":1895,"fn":1896,"description":1897,"org":1999,"tags":2000,"stars":24,"repoUrl":25,"updatedAt":1910},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2001,2002,2003,2004],{"name":1901,"slug":1902,"type":15},{"name":1904,"slug":1905,"type":15},{"name":20,"slug":8,"type":15},{"name":1908,"slug":1909,"type":15},{"slug":1912,"name":1912,"fn":1913,"description":1914,"org":2006,"tags":2007,"stars":24,"repoUrl":25,"updatedAt":1925},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2008,2009,2010,2011],{"name":1901,"slug":1902,"type":15},{"name":1919,"slug":1920,"type":15},{"name":1922,"slug":1923,"type":15},{"name":20,"slug":8,"type":15},{"slug":1927,"name":1927,"fn":1928,"description":1929,"org":2013,"tags":2014,"stars":24,"repoUrl":25,"updatedAt":1940},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2015,2016,2017,2018],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":1935,"slug":1936,"type":15},{"name":1938,"slug":1939,"type":15},{"slug":1942,"name":1942,"fn":1943,"description":1944,"org":2020,"tags":2021,"stars":24,"repoUrl":25,"updatedAt":1955},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2022,2023,2024,2025],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":1950,"slug":1951,"type":15},{"name":1953,"slug":1954,"type":15},{"slug":1957,"name":1957,"fn":1958,"description":1959,"org":2027,"tags":2028,"stars":24,"repoUrl":25,"updatedAt":1965},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2029,2030,2031],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":1953,"slug":1954,"type":15},{"slug":1967,"name":1967,"fn":1968,"description":1969,"org":2033,"tags":2034,"stars":24,"repoUrl":25,"updatedAt":1980},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2035,2036,2037,2038],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":1975,"slug":1976,"type":15},{"name":1978,"slug":1979,"type":15},{"slug":1982,"name":1982,"fn":1983,"description":1984,"org":2040,"tags":2041,"stars":24,"repoUrl":25,"updatedAt":1994},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2042,2043,2044,2045,2046],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":1990,"slug":1991,"type":15},{"name":1938,"slug":1939,"type":15},{"name":13,"slug":14,"type":15},{"slug":2048,"name":2048,"fn":2049,"description":2050,"org":2051,"tags":2052,"stars":24,"repoUrl":25,"updatedAt":2061},"amazon-aurora-mysql","manage Amazon Aurora MySQL clusters","Amazon Aurora MySQL — creates, modifies, and advises on Aurora MySQL clusters specifically (MySQL-compatible engine, Aurora serverless, parallel query). Trigger for Aurora MySQL cluster operations, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or MySQL upgrade planning. Aurora MySQL uses full (VPC-based) configuration — express configuration is PostgreSQL-only. For Aurora PostgreSQL, use amazon-aurora-postgresql instead. Contains safety guardrails and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2053,2054,2055,2058],{"name":20,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":2056,"slug":2057,"type":15},"MySQL","mysql",{"name":2059,"slug":2060,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":2063,"name":2063,"fn":2064,"description":2065,"org":2066,"tags":2067,"stars":24,"repoUrl":25,"updatedAt":2074},"amazon-aurora-postgresql","configure Amazon Aurora PostgreSQL clusters","Amazon Aurora PostgreSQL — creates, modifies, and advises on Aurora PostgreSQL clusters specifically (PostgreSQL-compatible engine, Aurora serverless, express configuration, pgvector, Babelfish). Trigger for Aurora PostgreSQL cluster operations, express-configuration quick-start, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or PostgreSQL upgrade planning. For Aurora MySQL, use amazon-aurora-mysql instead. Contains safety guardrails, express-first routing, and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2068,2069,2070,2073],{"name":20,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":2071,"slug":2072,"type":15},"PostgreSQL","postgresql",{"name":2059,"slug":2060,"type":15},"2026-07-16T06:00:34.789624",{"slug":2076,"name":2076,"fn":2077,"description":2078,"org":2079,"tags":2080,"stars":24,"repoUrl":25,"updatedAt":2086},"amazon-bedrock","build generative AI apps with Amazon Bedrock","Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore. Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating\u002Fporting\u002Fconverting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching setup and debugging, quota health checks and throttling diagnosis, cost attribution and tracking, migrating between Claude model generations (4.5 to 4.6 to 4.7), chunking strategies, API selection (Converse vs InvokeModel), guardrail capabilities, and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, 402 Payment Required, pay for content, paid endpoint, agent payments). NOT for custom model training, Rekognition, or Comprehend.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2081,2082,2083],{"name":1901,"slug":1902,"type":15},{"name":20,"slug":8,"type":15},{"name":2084,"slug":2085,"type":15},"LLM","llm","2026-07-25T05:30:35.20899",{"slug":2088,"name":2088,"fn":2089,"description":2090,"org":2091,"tags":2092,"stars":24,"repoUrl":25,"updatedAt":2101},"amazon-documentdb","manage Amazon DocumentDB clusters","Manages Amazon DocumentDB end-to-end — serverless-on-8.0 cluster setup, TLS\u002FVPC\u002Fdriver config, flexible-schema and vector-search data modeling, MongoDB compatibility assessment, DMS-based migration, slow-query diagnosis, major version upgrades (4.0→5.0→8.0), Well-Architected reviews (41-check wa_review.py), cost estimation, and security hardening. Retrieve for every DocumentDB question and when the user asks to set up or migrate MongoDB to AWS — DocumentDB is AWS's MongoDB-compatible managed database. Triggers: JSON document store, document database, MongoDB on AWS, Nested fields, Lambda cannot connect, TLS handshake, VPC port 27017, IAM auth, Secrets Manager, encryption at rest, $graphLookup, flexible schema, COLLSCAN, compound index, DMS migration, CDC cutover, $vectorSearch, RAG, Global Clusters, DR replication, cost sizing, audit, health check, production-readiness.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2093,2094,2095,2098],{"name":20,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":2096,"slug":2097,"type":15},"MongoDB","mongodb",{"name":2099,"slug":2100,"type":15},"NoSQL","nosql","2026-07-12T08:43:00.455878",{"slug":2103,"name":2103,"fn":2104,"description":2105,"org":2106,"tags":2107,"stars":24,"repoUrl":25,"updatedAt":2111},"amazon-dynamodb","design and debug DynamoDB data layers","Designs, reviews, and debugs DynamoDB data layers from design axioms — enumerates access patterns, chooses partition\u002Fsort keys and GSIs, decides single-table vs. multi-table, configures Streams, Global Tables, TTL, and zero-ETL integrations to OpenSearch\u002FRedshift\u002FSageMaker Lakehouse, and produces a defensible data-layer design with a monthly cost estimate and optional live validation. Applies whenever a user is designing, reviewing, or refactoring anything backed by DynamoDB — schemas, access patterns, GSIs, single- vs. multi-table choices, Streams consumers, transactional outboxes, Global Tables, zero-ETL pipelines — even when they don't say \"axioms\" or \"design review.\" Also applies when debugging hot partitions, throttling, unbounded Scans, LWW conflicts, or surprise bills on DynamoDB workloads.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2108,2109,2110],{"name":20,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":2099,"slug":2100,"type":15},"2026-07-16T06:00:37.690386",115]