agentleFS
ingoclaroingoclaro/claude-skills/skills/adversarial-review/SKILL.md

adversarial-review

Skill0 starsChanged 20 days agoMITView on GitHub

Adversarial review of the last commit. A background Sonnet reviewer proves each suspected bug with a repro it runs, mutation-tests the commit's own tests, and merges in /code-review's findings, giving one verified, source-tagged list. Use when the user wants the commit they just made attacked, stress-tested or given a deep second-opinion review. Args are the focus areas. Do not use for uncommitted changes, a PR or another branch, or a quick review; use /code-review for those.

106 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use rethink, root-cause-analysis and 10 more.

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.
  • fabioespindulaSkill

    rethink

    Reframe a plan, idea, or decision before the user commits to it. Use when the user asks to rethink, step back, pressure-test, gut-check, decide, right-size, simplify, think bigger about, or evaluate a concrete plan or decision in product, strategy, technical architecture, career, life, company direction, or personal priorities. This skill improves decision quality before action: clarify the real question, challenge assumptions, compare alternatives, calibrate ambition, classify the operating mode, surface risks, and recommend a next move. Do not use for broad future exploration without a concrete decision; that belongs to a think-big or research-style skill.

    Also in 3 projects that use this

  • MicrosoftSkill

    root-cause-analysis

    Use when a Regional Retail Manager asks I'm seeing unusual inventory movement at our Northwest stores. Can you help me understand what's happening?

    Also in 3 projects that use this

  • anasahmed07Skill

    better-auth-best-practices

    Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.

    Also in 4 projects that use this

  • DockerSkill

    fix-issue

    Fix a single GitHub issue end-to-end: triage, research, write the fix, review, and create a PR. Use when asked to fix an issue: "fix issue 1234", "resolve #500", "create a PR for issue 200".

    Also in 3 projects that use this

  • MicrosoftSkill

    pull-request

    Write concise, focused pull request descriptions for Wassette — at most three sentences on the what and why, with an explicit note on any breaking public-API change and how users adapt. Use when opening or editing a Wassette pull request.

    Also in 3 projects that use this

  • juriwiensSkill

    codex-review

    Run code review via Codex CLI

    Also in 3 projects that use this

  • +2 more from microsoft

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 95 edited versions we read keep these.

  • 2

    Distinctive

    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. Very specific:

    Start the reviewer in the background with the Agent tool, subagent_type: "general-purpose" and model: "sonnet", and this prompt:

    line 32
  2. Distinctive:

    When the report arrives:

    line 48
  3. Distinctive:

    Fix: ask which findings to fix.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 95 edited versions of this file we could read. “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

Adversarial review

1. Pin the commit

This session's tree, captured when the skill loaded:

  • Repo root: !git rev-parse --show-toplevel
  • HEAD: !git log -1 --format='%h %s'
  • Uncommitted changes (empty means clean): !git status --porcelain
  • It must be a repo: if the repo root is an error, stop and tell the user to restart the session in the repo to review. The reviewer's /code-review runs in this session's working directory, so no other repo can be reviewed from here.
  • It must be clean: /code-review reviews uncommitted changes whenever any exist, so if any changes are listed, ask the user to commit or stash them, then rerun git status --porcelain to confirm.
  • The review covers HEAD: the commit is the one on the HEAD line. If you asked the user to commit, that line is stale: rerun git log -1 --oneline and use that commit instead.

Done when the tree is clean and you can name the commit under review.

2. Dispatch the reviewer

Pick the focus areas: $ARGUMENTS. If that is empty, name the 2 or 3 riskiest parts of the diff yourself.

Start the reviewer in the background with the Agent tool, subagent_type: "general-purpose" and model: "sonnet", and this prompt:

Read ${CLAUDE_SKILL_DIR}/references/reviewer.md and follow it.
- Skill dir: ${CLAUDE_SKILL_DIR}
- Repo: <the repo root from step 1>
- Commit: <short sha and subject>
- Spec: <the problem statement or card in a few lines, or its path; "none" if there is none>
- Agreed decisions: <deliberate choices from this session; these are not bugs. "none" if there are none>
- Focus areas: <the focus areas you picked>
- Test command: <the project's test command, e.g. `bun test src/` or `pytest -q`>
- Scratch dir: <the scratchpad directory your environment names, or "none">

3. Present

When the report arrives:

  • Present: show the report as it came, already merged and verified. Every confirmed finding carries a repro the reviewer ran and the path of its script, so take the repros as proof; if one looks doubtful, rerun its script before presenting it. Keep its source tags, its dismissed items, and any note that /code-review or mutation testing did not run.
  • Fix: ask which findings to fix. Fix only those, in their own commit ("Review fixes: …").

Done when the user has chosen what to fix.

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.