Skills for Real Engineers. Straight from my .agents directory.
skill-coverage-audit
Agent skill fromnyldn/claude-octopus
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs
How to install skill-coverage-audit
npx skills add nyldn/claude-octopus# or add only this skill to Claude Code: copy the folder
skills/skill-coverage-audit/
# into
~/.claude/skills/skill-coverage-audit/ (all projects)
.claude/skills/skill-coverage-audit/ (one project)
1> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.2> Cross-reference commands use installed skill names in Codex rather than `/octo:*` slash commands.3> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.4> For host tool equivalents, see `skills/blocks/codex-host-adapter.md`.567# Test Coverage Audit89## Artifact consistency before implementation1011When invoked at a spec/plan/tasks boundary, use the feature boundary adapter rather than this skill's code-test generation mode. It automatically runs bounded deterministic checks for coverage, declared paths, stable IDs, explicit terminology/enums/counts and verified policy references. A single artifact skips analysis; a clean pass costs no seat. Reports are advisory and quote the original sources. Escalation uses at most one independent seat, and unavailable or failed semantic review leaves the deterministic results usable.1213## Overview1415Trace every codepath in a diff, map each path against existing tests, visualize coverage gaps, and auto-generate tests for uncovered paths.1617**Core principle:** Trace codepaths in changed files -> Map against existing tests -> Score coverage quality -> Generate tests for gaps -> Report before/after counts.181920## Caps and Limits2122These hard limits prevent runaway analysis:23…
Excerpt shown under the repository's MIT license.
More skills in claude-octopus
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
