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

82%

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

The canonical home for this skill is skillshare-codebase-audit in runkids/skillshare

Quality

Content

65%Weight 40%Scale 1-3

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

The body is highly actionable — concrete grep commands, defined status labels, and clear output templates — but it is held back by structural problems: a duplicated Output Format section and an intro that still says '4 dimensions' while seven are defined. These issues waste tokens and blur the workflow.

Suggestions

Remove the first 'Output Format' block (lines 85-114); keep only the single complete version at lines 174-225 that already covers all dimensions.

Update 'Run all 4 dimensions in parallel' to reflect the actual seven dimensions, and group dimensions 5-7 under the same 'Audit Dimensions' heading before the single output-format section.

For a 215-line skill, consider splitting the per-dimension detail (Handler Split, Oplog, Web API) into reference files and keeping SKILL.md as an overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — it uses concrete grep commands and status tables without explaining concepts Claude already knows — but the 'Output Format' block is duplicated: lines 85-114 repeat a subset of the fuller block at 176-225, so ~30 lines do not earn their place. Not score 3 because not every token earns its place; not score 1 because the rest is lean and instruction-dense.	2 / 3
Actionability	Fully executable, copy-paste-ready commands throughout (e.g. `grep -rn 'flag\.\(String\\|Bool\\|Int\)' cmd/skillshare/`, `wc -l cmd/skillshare/*.go \| sort -rn \| head -20`), explicit per-dimension status labels, and concrete output table templates. Clear, specific guidance rather than abstract description.	3 / 3
Workflow Clarity	A sequence exists (run dimensions → per-dimension summary tables → final summary) and 'verify with grep before flagging' acts as a checkpoint, but the intro says 'Run all 4 dimensions in parallel' while seven dimensions are defined, and dimensions 5-7 are wedged between two 'Output Format' sections, muddling the flow. Not score 3 because the sequencing/organization is internally inconsistent; not score 1 because steps and a verification gate are present.	2 / 3
Progressive Disclosure	Section headers organize the content, but there are no bundle/reference files and the ~215-line body is monolithic with structural muddle (duplicate 'Output Format', stale '4 dimensions' count, dimensions split across an output block). Not score 3 because content is not cleanly split or navigable; not score 1 because it is sectioned rather than a wall of text and has no deeply nested references.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it states concrete capabilities, gives explicit 'Use when...' triggers covering both user phrasings and situational contexts, and carves out a distinct read-only niche. It is concise without fluff and matches the top reference examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Cross-validate CLI flags, docs, tests, and targets' and enumerates 'find undocumented flags, verify test coverage, validate targets.yaml, check handler split conventions, or verify oplog instrumentation'. Uses third-person/imperative voice consistent with the good reference examples, so no voice penalty applies.	3 / 3
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: ...' plus 'Use after large refactors, before releases, or whenever you suspect docs/code/tests have drifted out of sync').	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'audit the codebase', 'check for consistency issues', 'find undocumented flags', 'verify test coverage', and 'validate targets.yaml' are phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — a read-only consistency audit specific to the skillshare codebase with distinct triggers — and explicitly notes 'it reports issues but never modifies files', making conflict with editing skills unlikely.	3 / 3
	Total	12 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: JetBrains/skills
Path: codebase-audit/SKILL.md
Commit: e0f258b

Reviewed: 8 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.