CtrlK
BlogDocsLog inGet started
Tessl Logo

good-docs-audit

Audit a doc, guide, README, or block of prose against the good-docs-writing style guide and report violations. Use when the user asks to review, critique, lint, or check the voice and tone of documentation or text. Produces a structured findings report (file:line, rule violated, offending text, suggested rewrite) and does NOT edit files unless explicitly asked.

73

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

86%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 tight, well-structured instruction-only skill that assumes Claude's competence and delegates detail cleanly to one verified reference. Actionability and workflow clarity sit at 4 because the executable procedure lives in the reference rather than the body, which is correct progressive disclosure but leaves the body itself slightly less self-contained.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or explanation of concepts Claude already knows — every line ('Default behavior is report only', the four non-negotiables, the single pointer to the reference) earns its place.

5 / 5

Actionability

Concrete, specific directives ('Cite file:line for every finding and quote the exact offending text', 'Give a real rewrite in the target voice, not consider revising'), but the bulk of the executable procedure (checklist, report format) is deferred one level deep to the reference rather than shown inline.

4 / 5

Workflow Clarity

The body frames the workflow and establishes an explicit validation gate ('report only ... do not edit ... Only modify files if the user explicitly says to fix, rewrite, or apply'), with the full sequenced procedure living in the referenced file; the delegation is appropriate but leaves the body's own step sequence implicit.

4 / 5

Progressive Disclosure

Clear overview that points to a single well-signaled one-level-deep reference ('Read references/audit-process.md for the procedure, the prioritized violation checklist, the report format, and the reporting rules'), with content appropriately split and the referenced file verified to exist and contain the real procedure.

5 / 5

Total

18

/

20

Passed

Description

96%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 concretely states capabilities, gives an explicit 'Use when' trigger with natural synonyms, and stakes out a clear documentation-voice niche. Only slightly broad trigger terms keep it from a perfect distinctiveness score.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Audit a doc, guide, README, or block of prose', 'report violations', 'Produces a structured findings report (file:line, rule violated, offending text, suggested rewrite)', 'does NOT edit files unless explicitly asked' — giving comprehensive coverage of what it does.

5 / 5

Completeness

Explicitly answers both 'what' (audit against the good-docs-writing style guide and produce a structured findings report) and 'when' ('Use when the user asks to review, critique, lint, or check the voice and tone of documentation or text') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural synonyms users would say — 'review, critique, lint, or check the voice and tone' plus 'doc, guide, README, ... documentation or text' — with broad synonym coverage matching the top anchor.

5 / 5

Distinctiveness Conflict Risk

The 'good-docs-writing style guide' / 'voice and tone of documentation' niche is distinct, but the leading trigger terms 'review' and 'critique' are broad enough to risk minor overlap with general code-review or doc-review skills, so it sits just below the top anchor.

4 / 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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
ComposioHQ/composio
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.