Skill Coverage Audit — Security skill for Claude Code
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs.
How to install Skill Coverage Audit
Installs to ~/.claude/skills/nyldn-claude-octopus-skill-coverage-audit/SKILL.md
mkdir -p ~/.claude/skills/nyldn-claude-octopus-skill-coverage-audit && curl -fsSL https://raw.githubusercontent.com/nyldn/claude-octopus/HEAD/.claude/skills/skill-coverage-audit.md -o ~/.claude/skills/nyldn-claude-octopus-skill-coverage-audit/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Skill Coverage Audit does
name: skill-coverage-audit paths:
- "**/.test."
- "**/.spec."
- "/coverage/" aliases:
- coverage-audit
- test-coverage description: "Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs" trigger: | AUTOMATICALLY ACTIVATE when user requests coverage analysis:
- "check test coverage" or "coverage audit"
- "what's not tested" or "find untested code"
- "generate tests for gaps"
DO NOT activate for:
- General code aud
Alternatives in Security
- Security Ownership Map — Map people-to-file ownership, compute bus factor, and identify risks 14.6k ★
- CI Audit — Stack-aware CI gap detection — audits a project's GitHub Actions workflows against its declared tech stack and 117 ★
- Engineering Fix — Applies engineering corrections from the last /engineering-audit run 48 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Vigilant Guacamole
AI Code Review Agent (with Auto-Fix) Connects to GitHub PRs, runs parallel Security / Performance / Test-cover
Review Test Quality
Audit test suite quality: coverage gaps, weak assertions, missing negative cases, over-mocking, and tests that
Audit E2e
Audit end-to-end test coverage of critical Playwright paths. Identifies missing flows, flaky tests, slow suite
07 Completeness Audit
<!-- Injected: {{CLAIM_INVENTORY_PATH}} {{COVERAGE_RUBRIC_PATH}} {{COVERED_LOCATIONS_JSON}} {{SEAT_JURISDICTIO
Closeout
Post-project audit. Diffs SCOPE.md deliverables against ground truth using tier-aware verification (code-done
Delegated Work Audit
Compare what a teammate or agent delivered in one or more PRs against what was asked in tickets, PR comments,
Related Agents
Grays
Multi-framework test runner agent. Auto-detects pytest, jest, vitest, go test. Runs tests with coverage, gener
Test Purist
The merciless enforcer of test coverage and quality. Use this agent to find untested code, meaningless asserti
Test Coverage Mapper
Reducer subagent. Reads every per-node sidecar's tests_coverage_semantic block, joins against the actual test