CtrlK
BlogDocsLog inGet started
Tessl Logo

doc-freshness-review

Use when auditing repository documentation for drift, stale statements, broken references, or README mismatches, especially across published docs under `doc/` and key entry surfaces such as `README.md` (English default), `README.zh-CN.md`, `mcp/README.md`, and `mcp/README.zh-CN.md` during periodic maintenance or before preparing corrective PRs.

74

Quality

92%

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

85%

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

A well-structured instruction-only skill with concrete guidance, a clearly sequenced workflow, and clean one-level-deep reference use. Its only weakness is mild verbosity from a description-duplicating "When to use" section and the evaluation-prompts block.

Suggestions

Trim or remove the "When to use this skill" list, since the frontmatter description already covers triggers; keep only the "Do NOT use for" negative triggers which add new information.

Consider condensing the six evaluation prompts into 2–3 representative should-trigger/should-not-trigger examples, or move them to a separate test reference, to reduce non-execution scaffolding in the main body.

De-duplicate the routing table against Phase 3–4 handoffs so each routing decision appears in only one place.

DimensionReasoningScore

Conciseness

The body avoids concept-explanation padding, but the "When to use this skill" section largely restates the description and the six-item evaluation-prompts block is testing scaffolding rather than execution guidance, so it could be tightened.

2 / 3

Actionability

Although code-free, the guidance is concrete and executable: exact surfaces (doc/, README.md, mcp/README.md), a five-category mismatch taxonomy, specific routing destinations, and a self-check — all specific rather than abstract.

3 / 3

Workflow Clarity

Four sequenced phases with numbered steps, explicit decision branches (mechanical fix → PR; product unclear → report/issue; CloudBase contract → hand off), and a terminal minimum-self-check checklist provide clear checkpoints and an ambiguity guardrail.

3 / 3

Progressive Disclosure

The body is a focused overview that delegates scope detail to one clearly-signaled, one-level-deep reference (references/review-scope.md, verified to exist and not chain further), with navigation reinforced by the routing table.

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, well-crafted description: it states concrete capabilities, includes an explicit trigger clause, and is clearly distinguished from sibling review skills. No changes needed.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete audit targets — "drift, stale statements, broken references, or README mismatches" — rather than vague language, matching the multiple-specific-actions anchor.

3 / 3

Completeness

It explicitly answers both what ("auditing repository documentation for drift, stale statements, broken references, or README mismatches") and when via an explicit "Use when…" clause tied to periodic maintenance and corrective PRs.

3 / 3

Trigger Term Quality

It uses natural terms a user would actually say — "documentation", "drift", "stale", "README", "broken references", "corrective PRs" — giving good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

It carves a clear docs-freshness niche scoped to specific surfaces (doc/, README.md, README.zh-CN.md, mcp/README*) with handoffs to sibling skills, making wrong-skill conflicts unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
TencentCloudBase/CloudBase-AI-Toolkit
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.