repo-compliance-auditlisted

Run the read-only repo compliance audit — use whenever the ask is "run the compliance audit", "audit this repo against the standard", "is this repo conformant", "check this repo's structure/layout compliance", or any request for a pass/gap verdict against the repo meta-structure or project-memory standards. Runs the bundled script from the repo root and presents its `ID | Area | Verdict | Detail` table plus `N pass / M gap` summary verbatim. Strictly informational: it never writes to the audited repo, never fixes gaps (that is the mise-en-place scaffold skill), and defines no checklist content of its own (rows come from the sibling standards' checklist files). Not for questions about what the standard says (repo-meta-structure / project-memory skills) or for scaffolding missing structure.
hsb3/dotfiles-agents · ★ 0 · AI & Automation · score 70

Install: claude install-skill hsb3/dotfiles-agents

# Repo compliance audit Resolve `<plugin-root>` to the installed package directory containing this skill's `skills/` parent, using the loaded skill's absolute path. Do not assume a shell variable is set by the client. Substitute that absolute path in the commands below; both Claude Code and Codex can run them from the target repository. The rollout's measuring instrument: one command, a pass/gap table, exit 0 either way. The output IS the compliance checklist — do not maintain a separate tracking document. ## How to run From the **audited repo's root** (the script resolves the git toplevel of the cwd): ```bash python3 "<plugin-root>/skills/repo-compliance-audit/scripts/audit.py" --plugin-root "<plugin-root>" ``` The explicit `--plugin-root` locates the checklists without client-specific environment. When supplied, `$CLAUDE_PLUGIN_ROOT` remains the legacy default. The package must contain `skills/repo-meta-structure/references/checklist.md` and `skills/project-memory/references/checklist.md`. Then **present the table verbatim** (fenced code block), including the summary line. Do not re-derive, filter, or re-score rows yourself — the script is the instrument. ## Hard rules - **NEVER write to the audited repo during an audit.** No fixes, no scaffolding, no manifest creation, no "quick cleanups" — even if gaps look trivial. Fixing gaps is the mise-en-place scaffold skill's job (audit → scaffold → re-audit loop). - **Reports, never polices.** Gaps do not make the run