agentleFS
Sign inStart free
trac3r00trac3r00/agent-skills/skills/diff-review/SKILL.md

diff-review

Skill0 starsChanged 3 months agoMITView on GitHub

Fast mechanical review pass over a unified diff before a human or agent reads it. Flags debug output left in production paths, TODO/FIXME/HACK markers added by the change, trivial test assertions that prove nothing, and deleted tests. Chains sibling gates (secret-gate, comment-checker) so one command runs the entire mechanical layer. Deterministic, stdlib-only, reads a unified diff from stdin.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use test-design.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • shabarabaSkill

    test-design

    Automatically design comprehensive E2E test cases for newly implemented vibing.nvim features. Use immediately after completing feature implementation (Phase 5.4) and before running E2E tests. Generates test scenarios covering Happy paths, Error cases, Edge cases, and Integration points with priority ranking (Critical/High/Medium/Low) and ready-to-use test code templates using e2e_helper.lua.

    Also in 3 projects that use this

The file

Create a free account to mount
Files
SKILL.md

Diff Review

The mechanical layer of code review, automated: run it on every diff and the human (or agent) reviewer only sees what actually needs judgment.

Commands

git diff | python3 scripts/diff_review.py
git diff main...HEAD | python3 scripts/diff_review.py --json
git diff | python3 scripts/diff_review.py --tools-dir skills/
git diff --cached | python3 scripts/diff_review.py --fail-over 3

Detects

KindWhat it catches
debug-outputprint(, console.log(, puts, pprint, dbg! added to non-test code
unresolved-markerTODO, FIXME, HACK, XXX, WIP, REMOVE ME added by the change
trivial-assertionassert True, assert 1 == 1 — tests that can never fail
test-deleteddef test_ / it( lines removed without replacement
secret-gate-findingscredential leaks (when chained via --tools-dir)
comment-checker-findingsunjustified comments (when chained via --tools-dir)

Chaining ecosystem gates

--tools-dir <skills-root> looks for secret-gate/scripts/secret_gate.py and comment-checker/scripts/comment_checker.py in that directory and feeds them the added lines. Their findings appear as *-findings entries with the first evidence line. Both are optional — chain whatever is installed.

Pairs with

merge-quiz (the human comprehension gate after the mechanical pass), remove-ai-slops (structural cleanup beyond what a diff pass can see), verification-before-completion (the evidence-before-claims wrapper around the whole workflow).

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.

Check your setup, free