Menu
Run after making changes, before committing — reviews the current git diff for impact and risk via cqs review.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Run a multi-category code audit on the cqs codebase. Spawns parallel agents per batch.
Trust-boundary security audit of cqs — fans out unbiddable-auditor agents across 6 categories (RT-INJ/RT-FS/RT-RES/RT-DATA/RT-RELAY/RT-EXFIL), attacker mindset, run-the-attack PoC + regression guard.
Run the retrieval recall gate with dead-gold triage and the binary A/B regression test. Required before release tags; use after any retrieval-adjacent merge.
Release a new version of cqs. Bumps version, updates changelog, runs the recall gate, publishes to crates.io, creates GitHub release.
One-command setup for cqs in a new project — skills, tears infrastructure, CLAUDE.md, init, index.
Comment-archaeology sweep - find work items hiding in TODO/FIXME/for-now comments and plan-doc ledgers, judge them, file issues, queue trivial fixes. Good idle-loop activity.
| name | check-my-work |
| description | Run after making changes, before committing — reviews the current git diff for impact and risk via cqs review. |
Run after making changes, before committing. Reviews your diff for impact and risk.
None — operates on the current git diff.
cqs review --json via Bash (analyzes current diff). Default covers unstaged changes; if the work is already committed on a branch, use cqs review --base <ref> (e.g. --base main) to diff against the base instead of raw git plumbing.## Diff Review
### Changed Functions
<from review: list of modified functions with risk scores>
### Affected Callers
<from review: callers of changed functions that may need updates>
### Tests to Re-run
<from review: tests that exercise the changed functions>
### Risk Assessment
<from review: overall risk level and reasoning>
### Checklist
- [ ] All affected callers still work with your changes
- [ ] Tests listed above pass: `cargo test --features cuda-index -- <test_names>`
- [ ] No new warnings from `cargo clippy --all-targets --features cuda-index`
- [ ] Changes formatted: `cargo fmt`
cqs review returns no changed functions, first confirm the diff is genuinely non-code (docs, config) with git diff --stat. From a .claude/worktrees/ lane an empty review despite real .rs edits is a RED FLAG — cqs review diffs the worktree, so an empty result means either no indexed function changed or something is wrong; do NOT rationalize it away, verify against git diff before skipping the impact analysis