Stats
Actions
Tags
From skills
Audit a codebase for high-risk untested paths and surface them as findings. Static-first, no instrumented coverage run required. Use when the user wants to find test gaps, audit coverage, find untested critical paths, or asks "what's not tested?".
How this skill is triggered — by the user, by Claude, or both
Slash command
/skills:audit-coverage [path or area to focus on, or leave blank for the whole codebase][path or area to focus on, or leave blank for the whole codebase]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Find where the test suite leaves **high-risk paths unexercised**, and surface each as a finding. Run the shared audit method in [../AUDIT-METHOD.md](../AUDIT-METHOD.md) with the lens and dimension below.
Find where the test suite leaves high-risk paths unexercised, and surface each as a finding. Run the shared audit method in ../AUDIT-METHOD.md with the lens and dimension below.
The aim is risk-weighted gaps, not raw uncovered-line count — target paths where being untested matters.
Rank code by:
git log) breaks more often.For the high-risk code, find what the tests exercise. A test file existing for a module is not coverage — trace which branches and error paths are hit. Consume a coverage report here if one exists.
test-gapenhancement ("add coverage for X"); a gap that already masks a likely defect is a bugPer ../AUDIT-METHOD.md → Handover.
capture — dedups against open issues, culls, files survivors as needs-triageGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub krixon/skills --plugin skills