amazon-elasticache

Activate when developers have latent caching needs: slow API responses, database read bottlenecks, DynamoDB throttling or cost, RDS/Aurora 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/sub, 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/CDK/Terraform 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/CloudFront, HTTP Cache-Control, CPU caches.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-architected registry skill with a sequenced router, explicit validation gates, and clean progressive disclosure into verified references. The only weakness is mild verbosity from time-sensitive version/pricing specifics and a partial inline migration checklist that duplicate dedicated reference files.

Suggestions

Move the Valkey version ladder (7.2/8.0/8.1/8.2/9.0 feature notes) and the inline online-migration preflight requirements into their respective reference files (e.g. references/setup and references/migration/topology-validation.md), keeping SKILL.md to the rule 'node-based Valkey 8.2+ for vector search' and a pointer.

Tighten the 'Product truths' section to non-obvious, stable facts only; defer 33%/20% pricing differentials to scripts/price_calculator.py and the pricing URL to avoid stale numeric claims in the always-loaded overview.

The sub-skill registry table cells are long; consider shortening the 'Semantic Categories' column to the highest-signal trigger terms and relying on each sub-skill's instructions.md for the full list.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (no concept-explanation fluff), but the 'Product truths' version ladder (Valkey 7.2/8.0/8.1/8.2/9.0) and the inline online-migration preflight list are time-sensitive specifics that partially duplicate `references/migration/topology-validation.md` and could be tightened/moved. This matches the 'mostly efficient but includes some…that could be tightened' anchor rather than the lean score-3 anchor.	2 / 3
Actionability	Concrete, executable guidance throughout: `python3 scripts/input_validator.py cache_name=<val> region=<val> …`, the full `--tags Key=managed_by,Value=aws-skills …` CLI syntax, exact reference paths, and explicit tool choices (AWS CLI/SDK/CFN/CDK, valkey-py, python3). As an instruction/routing skill the guidance is copy-paste-ready and specific, satisfying the actionable-anchor even without a full code block.	3 / 3
Workflow Clarity	The 8-step 'How this skill works' router is clearly sequenced with disambiguation rules, pipeline order, an input-validation gate before write operations, a hard validate-before-migrate gate, and an explicit retry-on-error feedback loop ('show the error…suggest a specific fix before retrying'). This matches the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points to one-level-deep references via an 'On-demand pointers' list with explicit per-file triggers, a stated folder convention, and verified bundle paths (6 sub-skill `instructions.md` files + 4 `shared-*` folders). Content is appropriately split and easy to navigate, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, densely packed description that pairs concrete capabilities with explicit natural-language triggers and clear negative triggers. It is long but every clause earns its place with actionable trigger terms rather than fluff.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions across caching and data-store work — 'provisioning (serverless or node-based), engine selection, CloudFormation/CDK/Terraform IaC, VPC connectivity, TLS, RBAC, IAM auth, Global Datastore, monitoring, troubleshooting, cost optimization, and migration' plus GenAI actions like 'vector similarity search', 'semantic caching', 'RAG', 'embedding stores'. These are specific verbs/capabilities, not vague language, matching the 'lists multiple specific concrete actions' anchor rather than the score-2 partial coverage.	3 / 3
Completeness	Explicitly answers what (caching/data-store/GenAI/lifecycle capabilities) and when, via repeated 'Activate when…' trigger clauses plus a 'Do not trigger for…' exclusion list. Meets the 'clearly answers both what AND when with explicit triggers' anchor; the 'Activate when' construction is an explicit trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Natural phrasing users actually say is well covered: 'slow API responses', 'database read bottlenecks', 'DynamoDB throttling or cost', 'session stores', 'rate limiting', 'leaderboards', 'semantic caching', 'RAG', 'migration from self-managed Redis'. Matches the 'good coverage of natural terms' anchor and is not jargon-only like the score-1 example.	3 / 3
Distinctiveness Conflict Risk	A clearly bounded AWS ElastiCache niche with sharp negative triggers ('Do not trigger for browser caches, CDN/CloudFront, HTTP Cache-Control, CPU caches') that prevent overlap with generic caching skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 16 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: aws/agent-toolkit-for-aws
Path: skills/specialized-skills/database-skills/amazon-elasticache/SKILL.md
Commit: 222ce56

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.