skillshare-codebase-audit

Cross-validate CLI flags, docs, tests, and targets for consistency across the codebase. Use this skill whenever the user asks to: audit the codebase, check for consistency issues, find undocumented flags, verify test coverage, validate targets.yaml, check handler split conventions, or verify oplog instrumentation. This is a read-only audit — it reports issues but never modifies files. Use after large refactors, before releases, or whenever you suspect docs/code/tests have drifted out of sync.

Quality

81%

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

63%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 highly actionable audit skill with concrete commands and strong evidence-based rules, undermined by a verbatim-duplicated Output Format section and an internal inconsistency (4 vs 7 dimensions). Tightening the redundancy would lift conciseness and structure together.

Suggestions

Remove the duplicated '## Output Format' block (keep a single section that includes the Handler Split, Oplog, and Web API tables) to recover ~50 lines and remove navigation ambiguity.

Reconcile the instruction 'Run all 4 dimensions in parallel' with the 7 dimensions actually documented, or split into 'core dimensions 1-4' and 'extended dimensions 5-7' explicitly.

For dimensions 2, 4, 5, and 7 that lack a grep probe, add a concrete example command matching the style of the others to keep actionability uniform.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with grep snippets and compact status tables, but the '## Output Format' section is duplicated verbatim (lines 82-111 and 173-222), a sizable padded block that should be consolidated.	3 / 5
Actionability	Provides concrete executable grep commands, exact file paths (cmd/skillshare/*.go, internal/config/targets.yaml), and explicit status labels (UNDOCUMENTED, STALE, MISMATCH) per dimension; minor gaps where some dimensions lack a grep probe.	4 / 5
Workflow Clarity	Clear per-dimension structure with verification rules ('verify with grep before flagging', 'Evidence-based — every finding must include file path and line number', 'No false positives') acting as checkpoints; the 'Run all 4 dimensions' instruction contradicts the 7 dimensions actually listed, a minor gap.	4 / 5
Progressive Disclosure	Well-sectioned but entirely monolithic with no bundle/reference files, and the duplicate '## Output Format' headers create navigation ambiguity; content is reasonably organized yet could be split or de-duplicated.	3 / 5
	Total	14 / 20 Passed

Description

100%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.

An exemplary description: concrete actions, explicit 'Use when' triggers in the user's own vocabulary, third-person voice, and a clear read-only boundary that distinguishes it from fix/modify skills. It hits the top anchor on every dimension without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete audit actions — 'Cross-validate CLI flags, docs, tests, and targets', 'find undocumented flags', 'verify test coverage', 'validate targets.yaml', 'check handler split conventions', 'verify oplog instrumentation' — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both what ('Cross-validate CLI flags, docs, tests, and targets for consistency') and when ('Use this skill whenever the user asks to: ... Use after large refactors, before releases, or whenever you suspect docs/code/tests have drifted out of sync').	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases a user would actually say — 'audit the codebase', 'check for consistency issues', 'verify test coverage', plus situational cues like 'after large refactors', 'before releases', 'drifted out of sync' — with synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Clear niche as a read-only consistency audit with the explicit boundary 'it reports issues but never modifies files', and distinct triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: runkids/skillshare
Path: .skillshare/skills/skillshare-codebase-audit/SKILL.md
Commit: e535e8f

Reviewed: 2 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.