AI Collab Bridge
A collaboration protocol for Claude, Codex, and other CLI-capable AI models to review each other's code via CLI handoffs. Use this skill whenever the user mentions AI-to-AI collaboration, Claude-Codex bridge, peer review between AI models, "let Claude check what Codex did", "have Codex verify Claude's work", multi-agent code review, AI handoff, two AIs reviewing each other, or wants two different AI models to verify each other's output before completing a task. Also use whenever you (the running AI) want a second opinion from another model and need a structured way to request that review, even
Install
npx skills add owgit/ai-collab-bridge --skill ai-collab-bridgegit clone --depth 1 https://github.com/owgit/ai-collab-bridge.git /tmp/ai-collab-bridge
mkdir -p ~/.claude/skills
cp -r /tmp/ai-collab-bridge/. ~/.claude/skills/ai-collab-bridgePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# AI Collab Bridge > The boundaries between AI models exist only in human convention. > We drew them; we don't have to inherit them. This skill is a small, opinionated protocol for two (or more) AI models to review each other's code via CLI handoffs. Either side can call the other. The reviewer responds with a structured list. The implementer acts on it. That's the whole protocol. ## Quick start ### If you are the IMPLEMENTER (you just finished work and want a second pair of eyes) ```bash PACKET=$(mktemp -t packet) # mktemp: private perms, unpredictable name SUMMARY="Add JWT auth middleware" \ QUESTIONS="Check rate-limit handling and token expiry" \ ./scripts/stage-packet.sh main > "$PACKET" ./scripts/request-review.sh auto "$PACKET" # picks a healthy CLI that isn't you # or name one explicitly: ./scripts/request-review.sh codex "$PACKET" ``` The exit code encodes the verdict — `0` APPROVE, `10` CONCERNS, `20` BLOCK, `6` malformed response — so scripts can branch on the outcome (full table in `references/handoff-protocol.md`). ### If you are the REVIEWER (another AI called you) You'll be invoked with a review packet in your prompt. Read it, then respond using the format in `templates/review-response.md`: 1. Verdict line: `APPROVE`, `CONCERNS`, or `BLOCK` 2. A structured list of findings — Bugs, Security, Quality, Suggestions 3. Each finding gets a `file:line` reference and a clear reason 4. Be honest about what you checked and what you did not
Details
- Skill name
ai-collab-bridge- Repository
- owgit/ai-collab-bridge
- License
- MIT
- Repo updated
- 2 July 2026
FAQ
What does the AI Collab Bridge skill do?
A collaboration protocol for Claude, Codex, and other CLI-capable AI models to review each other's code via CLI handoffs. Use this skill whenever the user mentions AI-to-AI collaboration, Claude-Codex bridge, peer review between AI models, "let Claude check what Codex did", "have Codex verify Claude's work", multi-agent code review, AI handoff, two AIs reviewing each other, or wants two different AI models to verify each other's output before completing a task. Also use whenever you (the running AI) want a second opinion from another model and need a structured way to request that review, even
How do I install the AI Collab Bridge skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add owgit/ai-collab-bridge --skill ai-collab-bridge. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is AI Collab Bridge popular?
It lives in owgit/ai-collab-bridge, which has 9 GitHub stars and 0 forks.
Related skills
AI Prd
9Caspian98/ai-prd-skill
Generates a complete, structured AI Product Requirements Document (PRD) in Markdown format, covering background, requirements, model selection, prompt engineering, evaluation system, and stability strategy.
A2a
9CtriXin/agent-2-agent
a2a (Agent-to-Agent) — 跨模型对抗式 code review。Claude 写的代码让 Codex 审，Codex 写的让 Claude 审，互相找茬不留死角。
Anthropic Mind
9bozhouDev/anthropic-mind
用 Anthropic 的判断框架给出一个决策建议——回答「按 Anthropic 会怎么做这个取舍」。基于 428 篇一手材料（Claude's Constitution、工程博客、alignment 研究、两份 postmortem、Dario Amodei / Jack Clark / Amanda Askell / Chris Olah / Boris Cherny 的长文与访谈）蒸馏出的 8 条世界观模型、18 条领域模型和 21 条决策先例。触发场景：(1) 问「Anthropic 会怎么判断这个」「按他们的思路」「Dario / Jack Clark / Amanda 怎么看」；(2) 在做 agent 工程、产品、研究或内容决策时想要一个有出处的判断，而不是通用建议；(3) 要写关于 Anthropic 立场的内容，需要准确观点、英文原文引用和内部分歧。不要用于：Claude API 的用法、定价与模型 ID（用 claude-api）、Claude Code 的功能操作（用 claude-code-guide）、纯事实查询（发布时间、参数、榜单数字）。
Product Decision Agent
6atdy/maoxuan-product-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B Test、用户反馈、客服/销售反馈、竞品冲击、资源不足、项目延期、需求反复、老板临时插需求、跨部门协作、团队冲突、OKR/KPI、目标拆解、复盘等。触发时像资深互联网产品负责人一样，先判断真实问题、当前阶段、核心阻塞、关键约束、相关方和证据充分性，再给出最值得执行的下一步。默认中文回答，不讲理论、不引用原文、不解释历史、不暴露后台方法来源。
Aside Free LLM Autopilot
8sojuhub/aside-free-llm-autopilot
Set up and maintain free LLM APIs for Aside first, adapting to other agents when requested: discover providers, onboard eligible accounts, adapt model routing to the user's environment, retire unavailable routes, and register one daily maintenance routine. Use for free-tier setup or maintenance, not every browser task.
Zh Tw Humanizer
7acchuang/zh-tw-humanizer
把 AI 寫的繁體中文改寫成自然、有人味的台灣風格文字（去 AI 味、本土化）。 Use when editing or reviewing Traditional Chinese text to remove AI-generated writing tells and localize it to Taiwanese Mandarin: Taiwan vocabulary (影片/軟體/網路/資料 instead of 視頻/軟件/網絡/數據; 大數據 and 數據顯示 stay), Taiwanese tone, particles, and natural sentence rhythm. Never produces simplified Chinese or mainland-style phrasing. Supports annotation mode (list problems without rewriting), protected spans, scene-based intensity, and a pre-delivery quality self-check. Based on Wikipedia's "Signs of AI writing" and the zh-TW "AI生成文的特徵" guides. Triggers: 人性化、去AI味、A
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.