cleanlisted
Install: claude install-skill Rockielab/rockie-claude
# /clean — Pre-commit audit adapted for a research repo
Research repos are typically majority prose — scripts, experiment dirs,
and many `.md` docs read by humans AND future agents. Slop in either
kind hurts. The audit covers both.
## When to run
- Before EVERY `git commit`. The `pre-commit-gate` hook will block if the
sentinel hash doesn't match current staged state.
- When the user asks to commit.
- When the hook emits a block message.
## What the skill does
1. Runs `${OPENCLAW_SKILLS_DIR}/clean/audit.py`. Arguments:
- `--scope staged` (default) — audits files in `git diff --cached --name-only`
- `--scope dirty` — audits all modified + untracked non-gitignored files
2. The audit reports findings in three buckets:
- **Blockers** — must fix before commit (new `.md` files created during
cleanup runs, broken internal doc links, obvious debug artifacts,
syntax errors)
- **Warnings** — should review (TODO markers pointing to resolved work,
duplicate content across docs, rules contradicting `${OPENCLAW_WORKSPACE_DIR}/memory/workflow.db`)
- **Info** — worth knowing (file size growth, complexity spikes)
3. If zero blockers: the audit invokes
`${OPENCLAW_WORKSPACE_DIR}/scripts/clean-finalize.sh <hash>` as its final
action. That script writes `${OPENCLAW_WORKSPACE_DIR}/.state/clean-ok-<hash>`
(where `<hash>` is computed by
`${OPENCLAW_WORKSPACE_DIR}/scripts/compute_clean_hash.sh`) AND emits the
upstream-contribute nudge to stderr. Th