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

90%

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%Weight 40%Scale 1-5

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

An unusually well-structured router skill: crisp routing logic with disambiguation and error-recovery loops, a clearly documented state-handoff contract, and exemplary progressive disclosure where every referenced bundle file exists one level deep. The only costs are minor token redundancy (duplicated tag example) and time-sensitive version/pricing data inlined in 'Product truths' rather than delegated to a reference with freshness handling.

Suggestions

Collapse the resource-tagging rule to a single template line (drop the near-duplicate example) and trim rationale sentences like 'Module-level connections crash applications...' to save tokens without losing the rule.

Move the Valkey version ladder and pricing percentages out of 'Product truths' into a versioned reference file (or a clearly freshness-stamped section), keeping only the decision rules inline, since time-sensitive data in the body will age and violates the freshness-disclaimer pattern the skill itself defines.

Dimension	Reasoning	Score
Conciseness	The body is dense and functional — tables, routing rules, and guardrails with no explanation of concepts Claude already knows — but the resource-tagging template is duplicated verbatim (template plus a near-identical example), and the 'Product truths' section inlines time-sensitive version numbers and pricing percentages ('Valkey serverless pricing is 33% lower', the 7.2→9.0 version ladder) outside any freshness/deprecated section. Fits the 4 anchor (efficient with minor trim opportunities); not 5 because of these specific redundancies and inline time-sensitive data.	4 / 5
Actionability	Contains exact copy-paste commands ('python3 scripts/input_validator.py cache_name=<val> region=<val> ...' and the full '--tags Key=managed_by,Value=aws-skills ...' CLI string) and routing steps that name exact file paths with fallback resolution. Fits the 4 anchor (mostly executable guidance with minor gaps); not 5 because most executable code and CLI detail is deliberately deferred to the per-sub-skill instructions.md files rather than covering common cases inline, and not 3 because nothing is pseudocode or vague.	4 / 5
Workflow Clarity	The 8-step 'How this skill works' sequence includes ordered disambiguation rules, a path-fallback retry (step 4), and an explicit error-recovery feedback loop ('If a script or CLI call fails, show the error to the user and suggest a specific fix before retrying'), reinforced by write-operation input validation, the migration 'validate-before-migrate gate', and the destructive-action safety reference. This matches the 5 anchor (clear sequence, explicit validation steps, feedback loops, checklists for complex processes).	5 / 5
Progressive Disclosure	The body is purely a router/overview; every on-demand pointer ('references/shared-ux/action-safety.md', 'references/shared-runtime/lambda.md', 'references/migration/topology-validation.md', etc.) was verified to be a real one-level-deep file with an explicit fetch trigger, and all six sub-skill instructions.md files exist. The folder convention (6 routing destinations + 4 shared cross-cutting folders) is documented. Matches the 5 anchor (clear overview, well-signaled one-level-deep references, easy navigation).	5 / 5
	Total	18 / 20 Passed

Description

96%Weight 40%Scale 1-5

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 dense, well-engineered trigger description: it enumerates concrete capabilities, includes extensive natural trigger vocabulary with symptom-based phrasing, explicitly states both what and when, and adds negative triggers to avoid misfires. The only weakness is a deliberately broad latent-need surface that overlaps with general Redis/Valkey skills and other AWS service skills.

Dimension	Reasoning	Score
Specificity	Lists many concrete capabilities across domains — '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' plus 'vector similarity search... semantic caching, RAG, LLM response caching'. This matches the 5 anchor (multiple specific concrete actions, comprehensive); it exceeds 4 because coverage spans symptoms, patterns, GenAI, and lifecycle with no notable gaps.	5 / 5
Completeness	Explicitly answers both: what ('ElastiCache lifecycle: provisioning... monitoring, troubleshooting, cost optimization, and migration from self-managed Redis') and when (three explicit 'Activate when/for' clauses with concrete trigger phrases, plus negative triggers 'Do not trigger for browser caches, CDN/CloudFront...'). Matches the 5 anchor; not 4 because the 'when' is maximally explicit, not merely present.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say: 'slow API responses', 'database read bottlenecks', 'DynamoDB throttling or cost', 'session stores, rate limiting, leaderboards', plus engine synonyms (Redis, Valkey, Memcached) and framework terms (RAG, Strands-adjacent GenAI vocabulary). Matches the 5 anchor (synonyms and natural phrasing included); a 4 would require missing natural terms, which is not the case.	5 / 5
Distinctiveness Conflict Risk	Clear AWS ElastiCache anchoring with explicit exclusions ('Do not trigger for browser caches, CDN/CloudFront, HTTP Cache-Control, CPU caches') minimizes conflict with unrelated skills. However, 'activate when working with Redis, Valkey, Memcached, or any in-memory data store' and other-service symptoms ('DynamoDB throttling', 'Bedrock latency or cost') create more than minimal overlap with generic Redis/Valkey and other AWS-service skills, so the 4 anchor (mostly distinct, minor overlap risk with closely related skills) fits better than 5.	4 / 5
	Total	19 / 20 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: b8171ad

Reviewed: 5 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.