跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

review

Review the local diff against Darkroom's checklist, or summarize feedback on the active PR. Triggers "review my changes", "check this diff", "summarize PR feedback". Native /code-review handles a diff or PR without the checklist.

darkroomengineering · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add darkroomengineering/cc-settings --skill review

技能说明


name: review description: Review the local diff against Darkroom's checklist, or summarize feedback on the active PR. Triggers "review my changes", "check this diff", "summarize PR feedback". Native /code-review handles a diff or PR without the checklist. context: fork agent: reviewer

Code Review

Reviews against the full Darkroom quality checklist defined in the reviewer agent.

Focus areas: TypeScript strictness, React patterns, accessibility, performance, security, file structure.

Standalone Codex host setup

Claude frontmatter does not enforce a fork or reviewer identity in standalone Codex. Keep the main pass read-only or create a fresh reviewer with spawn_agent. Deliver context to a running reviewer with send_message, trigger another turn for an idle existing reviewer with followup_task, wait with wait_agent, and stop its current turn with interrupt_agent only when necessary. Never spawn codex-verifier and never run codex-run.ts from inside Codex.

Writers share the working tree unless the live host explicitly offers isolation. Reviewers may overlap because they are read-only; serialize any later implementer and test-writer work with non-overlapping ownership. Gather the current state by explicitly running git branch --show-current, git diff --staged --stat, and git diff --stat. The !command lines below are Claude interpolation only.

Claude current state

  • Branch: !git branch --show-current 2>/dev/null || echo "unknown"
  • Staged files: !git diff --staged --stat 2>/dev/null || echo "nothing staged"
  • Unstaged files: !git diff --stat 2>/dev/null || echo "nothing unstaged"

Get Changes

# Unstaged changes
git diff

# Staged changes
git diff --staged

# Specific file
git diff path/to/file

Large diffs: walk a reading diff, not a summary

Past ~200 changed lines, present the diff walkthrough as a reading diff — the real diff, abridged — never a prose-only summary (prose can lie by omission; a diff can't). Every line shown is verbatim from git diff; the only editing allowed is removal and compression: drop whole no-signal lines, fold 2+ contiguous same-polarity lines into a ... row, or elide a noisy span inside a kept line. Never rewrite one. Drop import churn, lockfiles, generated files, and formatting-only hunks; show one instance of a mechanical rename and fold the rest with a count; keep every behavioral change. Close with an accounting line — showing N of M changed lines — dropped: ... — naming any new dependency, changed import target, or lockfile version/integrity bump even though import churn is dropped. The full diff remains the merge authority. Full protocol: the "Reading diffs" section of /review-batch (adapted from boldsoftware/meat, Apache-2.0).

Standalone Codex review

Follow the native lifecycle above, then adjudicate the fresh reviewer's findings against the diff. The fresh agent supplies the independent review; skip the Claude bridge branch below.

Cross-model review (when the Codex bridge is available)

This skill runs as the Claude reviewer agent — often Claude reviewing a diff Claude just wrote, the self-preferential-bias case. Run an independent review from a different model family in parallel and reconcile (the reviewer has Bash, so call the bridge directly):

bun "$HOME/.claude/src/scripts/codex-run.ts" review

Codex reads the same diff and returns HIGH / MEDIUM / LOW findings. Adjudicate every finding before it drives a fix — Codex produces false positives and stale findings, so its output is a set of claims, not a verdict. Tag each one:

  • confirmed — you reproduced or traced it in the diff. Only confirmed findings drive a fix or land as Critical.
  • rejected — a false positive or stale claim; note the one-line reason you rejected it.
  • unverified — you couldn't check it cheaply; surface it as a Suggestion for a human, don't act on it.

Then fold the confirmed findings into the verdict below — map HIGH→Critical, MEDIUM→Warning, LOW→Suggestion. Agreement with your own review raises confidence. The bridge is gated and fails open: if Codex is unavailable, proceed with the Claude review alone.

Output Format

## Summary
[1-2 plain-English sentences: what this change does, then your overall read]

## Critical Issues
- [Must fix before merge]

## Warnings
- [Should fix, but not blocking]

## Suggestions
- [Nice to have improvements]

## Verdict
[APPROVED / NEEDS CHANGES / BLOCKED]

Remember

  • Be constructive, not just critical
  • Explain WHY something is an issue
  • Comments in plain English — explain the issue and its impact like you're talking to a teammate, not citing a rulebook. No jargon dump.
  • Suggest specific fixes
  • If you find a pattern worth remembering, save it via auto-memory (personal) or /share-learning (team-wide).
  • Escalate to /verify when the diff touches auth, payments, crypto, input validation, or a breaking public API — this skill is the fast checklist pass; /verify runs three adversarial agents (issue-finder, disprover, judge) and is the gate for security-sensitive or financial code.

Animation & Motion Checklist

Fires whenever the diff touches CSS transitions/animations or any motion-library code — new or edited GSAP/Motion/Framer Motion/Lenis calls, animation props, spring configs, or WAAPI usage, not just added imports. Adapted from emilkowalski/skills review-animations (MIT). Default to flagging — approval is earned, not assumed.

Ten standards — each violation is a finding:

  1. Justified motion — every animation answers "why does this animate?" (spatial consistency / state indication / feedback / explanation / preventing a jarring change). "It looks cool" on a frequently-seen element is a block.
  2. Frequency-appropriate — keyboard-initiated and 100+/day actions get zero animation; tens/day gets reduced motion; occasional gets standard; rare/first-time can have delight.
阅读完整来源 ↗