skill-coverage-audit

Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-coverage-audit/SKILL.md

Quality

Content

75%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 well-structured, highly actionable workflow with explicit limits, output templates, and anti-pattern guidance. Main gaps are mild redundancy between sections, placeholder search commands, and validation of generated tests being outsourced to another skill rather than run inline.

Suggestions

Embed an inline validation feedback loop after test generation (e.g., run the suite, fix failing generated tests, re-run) instead of only deferring to skill-verification-gate, since generating up to 20 test files is a batch operation.

Remove the duplication between 'Caps and Limits', the 'Red Flags' table, and the 'Quick Reference' — the caps and phases are each stated twice, costing tokens without adding guidance.

Make the test-search commands concretely executable by showing one fully-substituted example (real file and module names) alongside the placeholder patterns.

Dimension	Reasoning	Score
Conciseness	The body is dense and instructional — concrete commands, output templates, and a caps section — with no explanations of concepts Claude already knows. Not 5 because there is redundant duplication: the 'Red Flags' table restates all three caps from 'Caps and Limits', the Quick Reference restates the four phases, and the 'Core principle' line duplicates the Overview.	4 / 5
Actionability	Mostly executable guidance: copy-paste git diff commands, explicit output templates (codepath inventory table, coverage map, ASCII diagram format), a concrete star-rating rubric, and a conventions-detection template. Not 5 because the test-search commands are placeholder templates (e.g., `grep -rl "import.from.[module_name]" tests/`) that are not executable verbatim, and no example generated test is shown.	4 / 5
Workflow Clarity	A clear four-phase sequence with numbered steps, hard caps, prioritization rules, and before/after reporting — matching the 4 anchor. Not 5 because the validate-and-fix feedback loop for the batch test-generation step is delegated to skill-verification-gate rather than embedded ('run the suite, fix failures') in the workflow, a minor validation gap for a batch operation.	4 / 5
Progressive Disclosure	As a single-file skill with no bundle files, it is well-organized with clear section headers (Overview, Caps, Phases 1-4, Integration, Red Flags, Quick Reference), fitting the 4 anchor for good structure with minor gaps. Not 5 because at ~245 lines the worked examples (inventory, coverage map, diagram) and convention templates could be split into reference files, and no references exist to signal.	4 / 5
	Total	16 / 20 Passed

Description

83%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 actions, explicit 'use before shipping PRs' trigger, third-person voice, and a clear coverage-analysis niche. Minor improvements possible by adding user-facing synonyms like 'untested code' or 'find test gaps'.

Dimension	Reasoning	Score
Specificity	The description lists three concrete actions — "Trace codepaths in diffs", "map against tests", "auto-generate missing coverage" — matching the anchor for several specific actions with minor gaps. It falls short of 5 because the body also covers scoring and diagramming coverage, which the description omits.	4 / 5
Completeness	It explicitly answers both questions: what ("Trace codepaths in diffs, map against tests, auto-generate missing coverage") and when ("use before shipping PRs") with a concrete trigger condition, matching the 5 anchor's what+when-with-concrete-trigger pattern. A 4 would require the 'when' to be less explicit, but "before shipping PRs" is a specific, actionable trigger.	5 / 5
Trigger Term Quality	Natural keywords like "codepaths", "diffs", "tests", "coverage", and "before shipping PRs" give good coverage of what a user would say, matching the 'good keyword coverage; a few natural terms missing' anchor. Not 5 because common variations users would actually say (e.g., "untested code", "test gaps", "write tests") are absent from the description.	4 / 5
Distinctiveness Conflict Risk	The coverage-audit niche (trace codepaths, map against tests, generate missing coverage) is mostly distinct with clear triggers, fitting the 4 anchor. Not 5 because it overlaps with general code-review and TDD skills on diff-based triggers, and the description itself carries no disambiguating anti-triggers (those live in the separate trigger field).	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-coverage-audit/SKILL.md
Commit: 0093dab

Reviewed: 5 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.