agentleFS
jamie8johnsonjamie8johnson/cqs/.claude/skills/check-my-work/SKILL.md

check-my-work

Skill18 starsChanged 5 months agoMITView on GitHub

Run after making changes, before committing — reviews the current git diff for impact and risk via cqs review.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run after making changes, before committing.

    line 8
  2. Very specific:

    Run cqs review --json via Bash (analyzes current diff).

    line 16
  3. Distinctive:

    If no diff, say "No changes to review" and stop

    line 17
  4. Distinctive:

    If risk is High, recommend the user review each affected caller manually before committing

    line 47
  5. Distinctive:

    If no tests cover the changed functions, flag prominently

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Check My Work

Run after making changes, before committing. Reviews your diff for impact and risk.

Arguments

None — operates on the current git diff.

Process

  1. Run 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.
  2. If no diff, say "No changes to review" and stop
  3. Present results as a review checklist

Output Format

## 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`

Rules

  • If 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
  • If risk is High, recommend the user review each affected caller manually before committing
  • If no tests cover the changed functions, flag prominently

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.