agentleFS
mick-gskmick-gsk/drift/.github/skills/drift-pr-review/SKILL.md

drift-pr-review

Skill14 starsChanged 7 months agoMITView on GitHub

Systematic PR review workflow aligned with Drift Policy. Use when reviewing pull requests that touch src/drift/, tests/, or scoring logic.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Before reviewing code, verify the PR passes the Policy Gate:

    line 28
  2. Distinctive:

    If the gate fails, comment with the reason and suggest what should be prioritized instead.

    line 40
  3. Very specific:

    If src/drift/ is modified:

    line 64
  4. Distinctive:

    Verify the change respects the priority hierarchy:

    line 81

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Drift PR Review Skill

Purpose

Guide Copilot agents through a policy-conformant, evidence-based pull request review for the drift repository.

When to Use

  • Reviewing PRs that change src/drift/, tests/, or docs-site/
  • Evaluating signal quality, scoring changes, or output format changes
  • Checking benchmark evidence for new features

Strukturierte Review-Checkliste

Pflicht-Referenz: Die vollständige Review-Checkliste liegt unter .github/prompts/_partials/review-checkliste.md. Bei jedem adversarialen Review wird diese Checkliste Punkt für Punkt abgearbeitet. Der Reviewer dokumentiert pro Punkt Ja / Nein / N/A mit Kurzbegründung.

Review Workflow

Step 1: Policy Gate

Before reviewing code, verify the PR passes the Policy Gate:

### Drift Policy Gate
- Aufgabe: [PR title / description]
- Zulassungskriterium erfüllt: [JA / NEIN] → [which criterion]
- Ausschlusskriterium ausgelöst: [JA / NEIN] → [if YES: which]
- Roadmap-Phase: [1 / 2 / 3 / 4] — blockiert durch höhere Phase: [JA / NEIN]
- Entscheidung: [ZULÄSSIG / ABBRUCH]
- Begründung: [one sentence]

If the gate fails, comment with the reason and suggest what should be prioritized instead.

Step 2: Signal Quality Checklist

For every new or modified finding/signal, verify all 5 mandatory elements:

  • Technical traceability — finding points to specific code location
  • Reproducibility — finding can be reproduced from the same input
  • Unique cause attribution — finding maps to exactly one root cause
  • Clear justification — rationale is documented and understandable
  • Actionable next step — a concrete remediation or investigation step exists

A finding missing any element is non-compliant with Policy §13.

Step 3: Benchmark Evidence

For feature PRs (feat: commits), verify:

  • benchmark_results/v*_feature_evidence.json artifact exists
  • Self-analysis score is equal or better than baseline
  • No regression in precision/recall on known test repos

Step 4: Self-Score Delta

If src/drift/ is modified:

drift analyze --repo . --format json

Compare the composite score against the CI threshold (currently 0.47). A score drop below threshold blocks the PR.

Step 5: Test Coverage

  • New behavior has corresponding test(s) in tests/
  • make check passes (lint + typecheck + tests + self-analysis)
  • No new # type: ignore or # noqa without justification

Step 6: Priority Compliance

Verify the change respects the priority hierarchy:

Glaubwürdigkeit > Signalpräzision > Verständlichkeit > FP/FN-Reduktion > Einführbarkeit > Trend > Features

A lower-priority change must not compromise a higher-priority property.

Review Comment Template

### PR Review — Drift Policy

**Policy Gate:** ✅ ZULÄSSIG / ❌ ABBRUCH
**Signal Quality (§13):** ✅ All 5 elements / ❌ Missing: [list]
**Benchmark Evidence:** ✅ Present / ⚠️ Missing / N/A
**Self-Score Delta:** ✅ ≥ 0.47 / ❌ Below threshold
**Test Coverage:** ✅ Covered / ❌ Missing tests for: [list]
**Priority Compliance:** ✅ OK / ❌ Violates: [explanation]

**Summary:** [1-2 sentences]

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.