CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-docs

Use when reviewing the documentation a branch changes — AGENTS.md, READMEs and pages under wiki/ — or sweeping the whole wiki with --full. Cross-checks every claim a page makes against the code, finds wikilinks and heading anchors the branch broke, checks frontmatter and page shape, and reports D-C/H/M/L findings in the four-field format.

72

Quality

91%

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

88%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 exceptionally actionable procedure skill: copy-paste commands, a verbatim deliverable skeleton, incremental-write discipline, and end-of-run validation with failure-mode interpretation. The only trimmable fat is occasional rhetorical justification prose, and the long inline body keeps progressive disclosure at good rather than exemplary.

DimensionReasoningScore

Conciseness

The body is dense with operational rules and teaches nothing Claude already knows — no concept explanations, no library tours — but a handful of rhetorical justifications ('The report is the deliverable. A run that leaves a differently-shaped file has produced nothing, however good the review inside it') could be trimmed without losing the rule. Anchor 5 ('every token earns its place') is slightly too strict for those passages; anchor 3 would require actual unnecessary explanation, which is absent.

4 / 5

Actionability

Fully executable throughout: the verbatim heredoc report skeleton, the claim-shape-to-check table with exact commands ('git grep -l '"name": "@scope/name"' -- '**/package.json"'), diff/grep pipelines per step, and a copy-paste finding block template. Fallback behavior is even specified ('On a checkout that has no scripts/check-wikilinks.ts, or no bun, record the check as not run rather than as passed').

5 / 5

Workflow Clarity

Steps 0–5 are clearly sequenced with explicit validation: the final grep checks ('Both must print 3') include interpretation of each failure mode, the wikilink script's exit code is defined, findings are written incrementally so a partial run survives, and a resumed run recovers from the file. The per-section checklist for --full sweeps is provided via references/checklist.md, matching the anchor's 'checklists for complex processes'.

5 / 5

Progressive Disclosure

The single bundle reference, references/checklist.md, exists, matches its description in the body (verified: per-section list covering currency, bloat, aids, structure, frontmatter, links, hygiene), and is one level deep and clearly signaled. Held at 4 rather than 5 because the main body is a full ~150-line procedure rather than a lean overview, and calibration detail like the Step 3 false-positive exceptions paragraph (TOML arrays, escaped-pipe aliases) is inline where a 5 would push more of it to the reference.

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 strong description: concrete action coverage, an explicit 'Use when' trigger clause naming the exact files and the --full mode, and a distinct niche sealed by the D-tier finding format. The only gap is a few natural synonyms ('docs', 'stale', 'drift') that would broaden trigger matching.

DimensionReasoningScore

Specificity

The description lists six concrete actions — 'Cross-checks every claim a page makes against the code, finds wikilinks and heading anchors the branch broke, checks frontmatter and page shape, and reports D-C/H/M/L findings in the four-field format' — comprehensively covering the skill's workflow. Anchor 4 ('minor gaps in coverage') fits worse since every phase of the review (claims, links, anchors, frontmatter, shape, reporting) is named.

5 / 5

Completeness

Explicitly answers both questions: 'Use when reviewing the documentation a branch changes — AGENTS.md, READMEs and pages under wiki/ — or sweeping the whole wiki with --full' is a concrete when-clause, and the cross-check/link/frontmatter/finding-report actions are a clear what. The 'Use when' clause is present, so the completeness cap of 3 does not apply.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'reviewing the documentation', 'AGENTS.md', 'READMEs', 'wiki', '--full', 'wikilinks', 'frontmatter', 'findings' — terms a maintainer would naturally say. Not 5 because common synonyms like 'docs', 'stale documentation', or 'documentation drift' are absent; not 3 because coverage goes well beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

A clear niche — documentation review of branch changes in a wiki-based repo — with distinct triggers (wiki/, AGENTS.md, D-C/H/M/L tiers) that no generic code-review or doc skill would share. Overlap risk with a plain 'review this branch' request is minimal because the trigger is explicitly scoped to documentation files.

5 / 5

Total

19

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

englishstreetventures/osn

Path

.claude/skills/review-docs/SKILL.md

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.