agentleFS
schen22schen22/claude-config/skills/review-gates/SKILL.md

review-gates

Skill0 starsChanged 2 days agoMITView on GitHub

Default review gates for any of Sarah's projects — which review runs when, on which model, at what context cost. Use before every commit, when integrating a helper's lane, and when a batch of PLAN.md items is done. If the project has its own review-workflow skill, follow that too; it wins on conflict.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before the commit: the full gate (npm run gate).

    line 18
  2. Very specific:

    No raw logs, no screenshots.

    line 21
  3. Very specific:

    Read only git diff <main>...lane/<name> (or the staged diff) plus the helper's report.

    line 25
  4. Very specific:

    Update PLAN.md and Lessons.

    line 39

≈ “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

Review gates

Goal: quality at the lowest token cost. Reviews read diffs, not the codebase, and heavy output stays out of the orchestrator's context.

Gate 0 — self-check before every commit (whoever commits)

  1. While iterating: the project's fast gate (npm run gate:fast or equivalent).
  2. Before the commit: the full gate (npm run gate). Only known failures allowed (listed in PLAN.md).
  3. The project's constraints from its CLAUDE.md.
  4. No raw logs, no screenshots. Helpers report in ≤ 15 lines (see delegate).

Gate 1 — diff review, per lane or per own commit (orchestrator)

  1. Read only git diff <main>...lane/<name> (or the staged diff) plus the helper's report.
  2. Lens: does each commit do what its item says; stays in owned files; project constraints hold; each new test would fail before the change; no duplicate tests.
  3. Verdict SHIP / BLOCKED + ≤ 5 one-line findings.
  4. Blockers go back to the same helper via SendMessage. Should-fix → follow-up commit or a line in PLAN.md Next.
  5. Risky task (JS behaviour, accessibility, security): one Sonnet reviewer helper, diff only, blockers only, ≤ 10 lines.

Gate 2 — whole batch, once (Sonnet subagent)

  1. One Sonnet helper runs the review skill over the batch diff. Blockers only, ≤ 10 lines.
  2. Fix blockers only. No iterate-to-a-score loop; no expert panel unless Sarah asks.
  3. Visual sign-off is Sarah's: point at the pages to open.
  4. Update PLAN.md and Lessons.

Models

  • Helpers and reviewers: Sonnet, passed explicitly. Orchestrator: briefs, Gate 1, merges, docs — judgment only. Haiku only for mechanical edits with no judgment, never for review.

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.