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

code-review

Code review by several models at once — Claude sub-agents, OpenAI Codex, and a cheap third reviewer via OpenCode — reconciled into one report. Reviews whatever is named: a diff, a branch, specific files, one function, a legacy module, a whole repo. Use for any review request, a second or third opinion, a cross-check before a PR, or "code-review", "multi", "consensus review".

szarkans · 已有 AI 审核记录

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 szarkans/multi --skill code-review

技能说明


name: code-review description: >- Code review by several models at once — Claude sub-agents, OpenAI Codex, and a cheap third reviewer via OpenCode — reconciled into one report. Reviews whatever is named: a diff, a branch, specific files, one function, a legacy module, a whole repo. Use for any review request, a second or third opinion, a cross-check before a PR, or "code-review", "multi", "consensus review". allowed-tools: Bash, Read, Grep, Glob, Agent, TodoWrite argument-hint: "[what to review, in words] [lite|normal|ultra] [haiku|sonnet|opus|fable] [low|medium|high|xhigh|max]"

Multi-model code review

!sh -c 'for p in "$CLAUDE_PLUGIN_ROOT/scripts" "$HOME/.claude/skills/multi/scripts" "./.claude/skills/multi/scripts"; do [ -x "$p/probe.sh" ] && { "$p/probe.sh"; echo "scripts-dir: $p"; exit 0; }; done; echo "probe: NOT FOUND — locate scripts/probe.sh in this plugin and run it yourself"'

Several models read the same code, and you decide what reaches the user. That is the whole idea: one model invents problems and walks past real ones, and you cannot tell which from a single report. Independent models disagree, and the disagreement is the signal.

You are the judge, not a dispatcher. The reviewers propose; they do not vote, and none of them gets the last word. When they conflict, open the code and decide.

This is normally reached at the end of a session — work is done, PR or push comes next. Act like it: the question is "is this ready", not "here are some observations".

$SCRIPTS below is whatever the probe printed as scripts-dir:.

The gate

From the probe lines above — they are already there, do not re-run it.

No second reviewer family → stop. This is multi-model review; the review pipeline can run two non-Claude families, Codex and OpenCode — without at least one of them there is nothing here that a single-model review does not already do. OpenRouter and Gemini are real second families, but this pipeline cannot run them as reviewers yet: they serve /multi:ask, not this skill. Say which is missing and point at /multi:setup. Do not quietly deliver a one-model review wearing a three-model label.

Anything else missing is a note, not a stop: no OpenCode, no ponytail, not a git repo (fine — then the target is files, not a diff). Name what was missing in the report and carry on.

Whatever is missing, point them at /multi:setup to connect it — it walks through this step by step and does not need them to know any of the above.

Decide what you are reviewing

Whatever the user named. A diff, a branch, two files, one function, a line range, a module nobody has touched in three years, the whole repository. There is no fixed vocabulary here and no menu — read what they wrote and work out what they mean, the way a colleague would.

When nothing was named, in this order:

  1. What this session was about. If you just wrote or changed something, that is the target — you know which files, what the task was, where you were unsure, what you fixed blind. That is better than a diff, which in a dirty tree also holds debug leftovers and unrelated edits, and which misses the old code the change leans on.
  2. The branch, if it is ahead of main and the tree is clean.
  3. The uncommitted diff otherwise.

Ask only when the answer genuinely changes what gets reviewed and you cannot tell — dirty tree and they mentioned a PR, say. Never open with a questionnaire: this skill runs at the end of a session, sometimes inside an autonomous run, and three questions there are worse than a wrong guess you announced. Guess, say what you guessed, let them correct you.

Whatever you settle on, resolve it into concrete paths, or a concrete git range, before dispatching. Every reviewer must look at the same thing — otherwise "two of them agreed" means nothing, they just happened to read the same file. If the target is vague, resolve it and say what you resolved it to.

Say what you are about to do

Always, before launching anything. Short, then go — this is not a request for permission, and you do not wait for an answer:

Reviewing: <target, and where it came from — "what we just did", "branch vs main", "you asked for src/auth.py">
           <when $REPO is not the session's own checkout, show the resolved path so a wrong-tree review is caught before it runs>
Running now: Codex <effort> · OpenCode <model> · ponytail          <— or why one is missing
Then: <what decides the Claude spend>

If they wanted something else they will say so, and interrupting is cheaper than an interrogation.

Launch everything free, immediately

Codex, OpenCode and the ponytail lens cost nothing per run and take 30–70 seconds wall clock. There is never a reason to hold them back or make them conditional on a mode. Start the two external ones in the background, both at once — OpenCode spends about a minute just warming up — and do everything else while they run.

RUN="$($SCRIPTS/run-dir.sh --slug <two-to-four words: the project and the job, e.g. skills-fixing-multi>)"

# The tree under review. Usually the session's own repo; set REVIEW_DIR to a
# path or a different worktree when THAT is the target. Resolve it once and hand
# it to every backend: cwd resets between these blocks, so without an explicit
# --repo the reviewers silently read the session checkout and can "agree" on an
# empty diff.
REPO="$(git -C "${REVIEW_DIR:-.}" rev-parse --show-toplevel)"

$SCRIPTS/collect-context.sh --repo "$REPO" [--diff <spec>] [--paths "<paths>"] > "$RUN/ctx.md"

$SCRIPTS/review-prompt.sh --repo "$REPO" --target "<in words>" [--diff <spec>] [--paths "<paths>"] \
                          [--focus "<user text>"] --context "$RUN/ctx.md" > "$RUN/review.prompt.md"
$SCRIPTS/ask.sh --repo "$REPO" --question-file "$RUN/review.prompt.md" --out-prefix "$RUN/review" \
                --backend "codex,opencode:<model from probe>" --fallback <from probe> \
                --e
阅读完整来源 ↗