From rae
Audit the current repository against RAE standards. Use when the user says "audit repo", "check repo standards", "sync with RAE", "check for drift", "compare against template", or when you want to verify a repo follows RAE conventions. Compares pyproject.toml, CLAUDE.md, ruff config, pytest/coverage config, and dev dependencies against the canonical RAE template.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rae:audit-repoThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Compare the current repository's configuration against the canonical RAE template
Compare the current repository's configuration against the canonical RAE template
(templates/pyproject.toml) and report discrepancies. For major structural differences
(e.g., no src/ layout in an established repo), ask the user before proposing changes.
This skill does NOT automatically fix everything. It reports what it finds, fixes trivial gaps (missing ruff subsections, missing dev deps), and asks about anything that would be disruptive to change.
Read templates/pyproject.toml from the RAE plugin directory to get the current
source of truth. This template defines the expected configuration for:
Read the current repository's:
pyproject.toml (required — if missing, this is a scaffold-repo situation, not an audit)CLAUDE.md (optional but recommended)Compare each section and categorize discrepancies:
Auto-fixable (apply without asking):
[tool.ruff.lint.isort] section[tool.ruff.format] section[tool.ruff] src key[tool.pytest.ini_options] section[tool.coverage.run] or [tool.coverage.report] sectionsAsk the user first:
src/ layout (established repos may have good reasons)[project.optional-dependencies] when they're
installed some other way (e.g., devcontainer, system-level)line-length differs from 120ignore rules not in the template (may be project-specific, e.g., F722 for jaxtyping)Informational only (report but don't change):
.github/ CI workflows.pre-commit-config.yaml (RAE does not require this)Present a summary table:
## Audit Results: {repo_name}
### Aligned with RAE
- [x] ruff line-length = 120
- [x] Python >= 3.11
- ...
### Gaps Found
| Gap | Category | Action |
|-----|----------|--------|
| Missing [tool.ruff.format] | Auto-fix | Will add |
| Missing pytest config | Auto-fix | Will add |
| No src/ layout | Ask user | Uses body_models/ directly |
| Extra ignore F722 | Informational | Needed for jaxtyping |
### Recommended additions to CLAUDE.md
- Document F722 exception and why it's needed
- ...
pyproject.toml## RAE Deviations section so future audits understand whyAfter applying fixes:
ruff format --check .
ruff check .
Report any issues from the verification step.
templates/pyproject.toml in the RAE pluginsrc/ layout changes on established repos — that's too disruptiveignore rules are often legitimate (F722 for jaxtyping, etc.) — ask, don't removenpx claudepluginhub peabody124/reproducible_agent_environment --plugin raeAudits a repo for AI-readiness, scoring ~20 dimensions across Foundation, Why, What, Hygiene, and Sync. Use when inheriting a legacy repo or asking "is this repo agent-ready?"
Audits a repository for baseline compliance across 9 categories including code quality, security, CI/CD, testing, and documentation. Emits Markdown report and JSON sidecar.
Audits a repository to map its real stack, conventions, assets, tests, docs, risks, and integration points. Persists results in reusable markdown to reduce re-reading and save tokens. Also calculates a harnessability score (0-100) to assess how well the codebase supports autonomous agent work.