caching

Caching strategies — invalidation, TTL guidelines, cache keys, cache layers, and when not to cache. Use when implementing or reviewing caching logic.

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

80%

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

The body is lean and highly actionable with executable examples and clear prioritization, but it functions as an inline reference rather than an overview pointing to detailed materials, and lacks the validation/feedback checkpoints that would make caching setup read as a sequenced workflow.

Suggestions

Add a brief implementation checklist that sequences the setup (choose layer → design key → set TTL → wire invalidation → verify on write) so the guidance reads as a workflow with an explicit verification step rather than standalone rules.

Introduce a validation/feedback checkpoint for invalidation, e.g. after wiring event-driven invalidation, verify the cache is cleared on a data write by testing the write→read path before considering it done.

Move the four full code examples into a references/ file (e.g. references/examples.md) and keep SKILL.md as a lean overview that links to them, so the overview practices progressive disclosure instead of inlining all detail.

Dimension	Reasoning	Score
Conciseness	Terse priority-tagged bullets ([P0-MUST]/[P1-SHOULD]/[P2-MAY]) and executable code with no padding or explanations of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Provides fully executable TypeScript (LRU cache, Redis stale-while-revalidate, HTTP headers, TanStack Query), concrete key formats (`user:123:profile`), and a TTL-range table — copy-paste ready.	3 / 3
Workflow Clarity	Principles are prioritized and the CACHE_LAYERS "check memory → Redis → origin" order gives some sequence, but it reads as a reference of standalone rules rather than a sequenced workflow, with no explicit validation/feedback checkpoints.	2 / 3
Progressive Disclosure	Well-sectioned single file, but it is a ~160-line monolith with all four code examples and the reference table inline and no bundle/reference files, so the overview is not kept lean by offloading detail.	2 / 3
	Total	10 / 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.

The description is concise, concrete, and complete: it names specific capabilities and provides an explicit use-when trigger in third person. It does not over-claim or pad with fluff.

Dimension	Reasoning	Score
Specificity	Lists five concrete capability areas — "invalidation, TTL guidelines, cache keys, cache layers, and when not to cache" — which is more comprehensive than the score-2 anchor that names only a domain and a few actions.	3 / 3
Completeness	Explicitly answers both "what" (caching strategies and the enumerated subtopics) and "when" ("Use when implementing or reviewing caching logic"), matching the score-3 anchor with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say ("caching", "invalidation", "TTL", "cache keys", "cache layers") and an explicit trigger ("Use when implementing or reviewing caching logic"), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	"Caching strategies" with these specific triggers carves a clear niche unlikely to fire for unrelated skills, satisfying the distinct-trigger anchor.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zebbern/claude-code-guide
Path: skills/caching/SKILL.md
Commit: af7d491

Reviewed: about 9 hours 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.