CtrlK
BlogDocsLog inGet started
Tessl Logo

caching

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

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, token-efficient reference skill: prescriptive priority-tagged rules, executable code across four cache layers, and actionable anti-pattern remedies. The main gaps are a missing code example for the highest-priority invalidation rules and code examples that push the single file toward a size where splitting would help.

Suggestions

Add a short code example for event-driven invalidation (e.g., deleting/versioning cache keys on write/update), since it is the skill's P0-MUST topic but the only major area without an executable example.

Trim the code examples to their minimal instructive core (e.g., drop the Express/Hono boilerplate around the Cache-Control headers) to tighten conciseness.

Consider moving the per-layer code examples into a references/ file with the layer table remaining in SKILL.md, so the core guidance loads lean while detail stays one level deep.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive with priority-tagged bullets ([P0-MUST]/[P1-SHOULD]/[P2-MAY]) and never explains concepts Claude already knows, but the four full code examples (especially the TanStack configuration block) are slightly long and could be trimmed to reach anchor 5.

4 / 5

Actionability

Mostly executable guidance: real code for LRU-with-TTL, Redis stale-while-revalidate, Express cache headers, and TanStack Query, plus a concrete layer-selection table and key formats. It misses anchor 5 because the P0-MUST invalidation rules have no corresponding code example — a minor gap in covering the common cases.

4 / 5

Workflow Clarity

Precedence is unambiguous via priority tags, the layering order is explicit ("check memory → Redis → origin. Write-through on miss"), and each anti-pattern carries a concrete "Instead:" remedy. No destructive or batch operations, so no validation cap applies, but there is no explicit multi-step sequence or checkpoint guidance to reach anchor 5.

4 / 5

Progressive Disclosure

A single self-contained file with no bundle, organized into clearly headed sections that are easy to navigate. It fits anchor 4 (good structure, content appropriately placed for its size) rather than 5, since the body exceeds the under-50-line simple-skill exception and the code examples could conceivably live in separate reference files.

4 / 5

Total

16

/

20

Passed

Description

87%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 strong third-person description that explicitly covers both what the skill does and when to use it, with concrete subtopic enumeration. Its only weaknesses are topic-noun phrasing instead of action verbs and a few missing natural synonyms (Redis, CDN, stale data).

DimensionReasoningScore

Specificity

The description lists five specific capability areas — "invalidation, TTL guidelines, cache keys, cache layers, and when not to cache" — but these are topic nouns rather than concrete action verbs, leaving minor coverage gaps versus the comprehensive anchor-5 example.

4 / 5

Completeness

Both questions are explicitly answered: 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 trigger phrases, matching the anchor-5 example rather than the anchor-4 case where the 'when' is only weakly implied.

5 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would say — "caching", "invalidation", "TTL", "cache keys", "cache layers" — but a few common variations are missing (e.g., "Redis", "CDN", "stale data"), matching the anchor-4 example pattern.

4 / 5

Distinctiveness Conflict Risk

"Caching" is a clear, well-defined niche with distinct triggers; the description is unlikely to fire for unrelated skills, matching the anchor-5 "clear niche with distinct triggers; minimal conflict risk".

5 / 5

Total

18

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.