caching

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

Quality

91%

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

90%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.

A concise, highly actionable caching skill with executable examples across layers and a useful anti-patterns section. It lacks an explicit validation/feedback loop and is slightly long for a single-file skill, which keep workflow clarity and progressive disclosure at 4 rather than 5.

Suggestions

Add an explicit validate→fix→retry feedback loop for cache-related changes (e.g., after writing a cache key, verify a read returns fresh data on update) to push workflow clarity toward 5.

Consider extracting the longer CODE_EXAMPLES into a references/ file (e.g., examples.md) with one-level-deep links from SKILL.md to improve progressive disclosure given the body length.

Dimension	Reasoning	Score
Conciseness	Lean guidance with no basic-concept padding ('Stale data is worse than no cache.') and tight code with only purposeful comments; assumes Claude's competence throughout, matching the top anchor.	5 / 5
Actionability	Fully executable, copy-paste-ready TypeScript covering the common cases (in-memory LRU+TTL, Redis stale-while-revalidate, HTTP Cache-Control headers, TanStack Query config), matching the top anchor.	5 / 5
Workflow Clarity	Clear organization with a layered lookup sequence ('check memory → Redis → origin') and decision-style checklists, but no explicit validate→fix→retry feedback loop, keeping it just below the top anchor.	4 / 5
Progressive Disclosure	Well-organized sections, table, and code blocks with no unnecessary external references and no nested navigation, but the body exceeds the ~50-line simple-skill threshold so it sits just below the top anchor.	4 / 5
	Total	18 / 20 Passed

Description

92%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 highly specific, well-structured description that clearly states both capabilities and trigger conditions with minimal conflict risk. The only gap is slightly limited trigger-term synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities ('invalidation, TTL guidelines, cache keys, cache layers, and when not to cache'), matching the comprehensive anchor rather than the minor-gaps anchor at 4.	5 / 5
Completeness	Explicitly answers both what ('Caching strategies — invalidation, TTL guidelines, cache keys, cache layers, and when not to cache') and when ('Use when implementing or reviewing caching logic') with concrete triggers, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases ('implementing or reviewing caching logic', 'caching') with good keyword coverage, but is missing common variations and library names a user might say, placing it just below the comprehensive anchor at 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear caching niche with specific sub-domain triggers, giving minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 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: 59c5fc4

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.