Not in the top 1,000 by GitHub stars
axtonliu/ai-pair
Coordinate multiple AI models (Claude + GPT + Gemini) as a heterogeneous team. One creates, two review. A Claude Code Skill.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 60961fa39156
No earlier version was observed for comparison.
348GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- ai-pair
/
How it works
ai-pair
When your agent uses it
AI Pair Collaboration Skill. Coordinate multiple AI models to work together: one creates (Author/Developer), two others review (Codex + Gemini). Works for code, articles, video scripts, and any creative task. Trigger: /ai-pair, ai pair, dev-team, content-team, team-stop
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
4,040 tokensWhen the skill is activated
Reference documents
3,984 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why Multiple AI Reviewers?
- Commands
- Prerequisites
- Team Architecture
- Workflow (Semi-Automatic)
- Project Detection
- Team Lead Execution Steps
- CLI Invocation Protocol (Shared)
- Agent Prompt Templates
- team-stop Flow
Files
.gitignoreasset38 bytesLICENSEasset1,066 bytesREADME.mddoc11,476 bytesSKILL.mdcore16,902 bytesSKILL.mdcore16,902 bytesSKILL.mdcore16,902 bytesSKILL.mdcore16,902 bytesexamples/content-team.mddoc2,940 bytesexamples/dev-team.mddoc1,938 bytes
Read SKILL.md
# AI Pair Collaboration
Coordinate heterogeneous AI teams: one creates, two review from different angles.
Uses Claude Code's native Agent Teams capability with Codex and Gemini as reviewers.
## Why Multiple AI Reviewers?
Different AI models have fundamentally different review tendencies. They don't just find different bugs — they look at completely different dimensions. Using reviewers from different model families maximizes coverage.
## Commands
```bash
/ai-pair dev-team [project] # Start dev team (developer + codex-reviewer + gemini-reviewer)
/ai-pair content-team [topic] # Start content team (author + codex-reviewer + gemini-reviewer)Skills included
- ai-pair
Repository facts
- License
- MIT
- Created
- Mar 8, 2026
- Last pushed
- Mar 22, 2026
- Forks
- 63
- Open issues
- 1
- Project activity
- Slowing
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 3 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 5 dangerous shell commandsin 1 file: SKILL.md:184
- 22 network referencesin 1 file: README.md:5
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 27 signals by file
README.md
- Network accessline 5
[](https://opensource.org/licenses/MIT) - Network accessline 6
[](#status) - Network accessline 7
[](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/skills) - Network accessline 13
> **Next Step:** Want to turn Skills from demo to asset? Check out [Agent Skills Resource Library](https://www.axtonliu.ai/agent-skills) (includes slides, PDF, diagnostics) - Network accessline 30
AI-Pair turns model differences into a structured workflow: assign each model a role that matches its strength, and let them review the same work from different angles. It's a [Claude Code Skill](https://docs.anthropic.com/en/docs/agents-an - Network accessline 32
AI-Pair 把模型差异变成结构化的工作流：给每个模型分配匹配其特长的角色，让它们从不同角度审查同一份工作。它是一个 [Claude Code Skill](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/skills) — 一组可复用的指令，扩展 Claude Code 的能力。 - Network accessline 60
| Tool | Purpose | Install | |------|---------|---------| | [Claude Code](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview) | Team Lead + agent runtime | `npm install -g @anthropic-ai/claude-code` | - Network accessline 61
|------|---------|---------| | [Claude Code](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview) | Team Lead + agent runtime | `npm install -g @anthropic-ai/claude-code` | | [Codex CLI](https://github.com/openai/codex) - Network accessline 62
| [Claude Code](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview) | Team Lead + agent runtime | `npm install -g @anthropic-ai/claude-code` | - Network accessline 63
| [Codex CLI](https://github.com/openai/codex) | GPT-powered reviewer | `npm install -g @openai/codex` | - Network accessline 64
| [Gemini CLI](https://github.com/google-gemini/gemini-cli) | Gemini-powered reviewer | `npm install -g @google/gemini-cli` | - Network accessline 77
# Clone to your global Claude Code skills directory # 克隆到 Claude Code 全局 skills 目录 git clone https://github.com/axtonliu/ai-pair.git ~/.claude/skills/ai-pair - Network accessline 79
git clone https://github.com/axtonliu/ai-pair.git ~/.claude/skills/ai-pair - Network accessline 179
AI-Pair evolved from [AI Roundtable](https://github.com/axtonliu/ai-roundtable), a Chrome extension that lets multiple AI web interfaces discuss and cross-review in the same panel. AI-Pair moves this concept to the command line with structu - Network accessline 181
AI-Pair 从 [AI Roundtable](https://github.com/axtonliu/ai-roundtable) 演变而来。AI Roundtable 是一个 Chrome 扩展，让多个 AI 的网页版在同一个面板里讨论和互评。AI-Pair 把这个概念搬到了命令行，加入了结构化的角色分工，更适合日常工作流。 - Network accessline 205
- Website: [axtonliu.ai](https://www.axtonliu.ai) - Network accessline 206
- YouTube: [@AxtonLiu](https://youtube.com/@AxtonLiu) - Network accessline 207
- Twitter/X: [@axtonliu](https://x.com/axtonliu) - Network accessline 211
- [MAPS™ AI Agent Course](https://www.axtonliu.ai/aiagent) - Systematic AI agent skills training - Network accessline 212
- [Claude Skills: A Systematic Guide](https://www.axtonliu.ai/newsletters/ai-2/posts/claude-agent-skills-maps-framework) - Complete methodology - Network accessline 213
- [AI Elite Weekly Newsletter](https://www.axtonliu.ai/newsletters/ai-2) - Weekly AI insights - Network accessline 214
- [Free AI Course](https://www.axtonliu.ai/axton-free-course) - Get started with AI
SKILL.md
- Dangerous shell operationline 184
- Clean up: rm -f $REVIEW_FILE after capturing output. - Dangerous shell operationline 271
6. If temp file was used: rm -f $REVIEW_FILE - Dangerous shell operationline 319
6. Clean up: rm -f $REVIEW_FILE - Dangerous shell operationline 368
6. Clean up: rm -f $REVIEW_FILE - Dangerous shell operationline 418
6. Clean up: rm -f $REVIEW_FILE
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 27 facts
- Network access in prose of documentationREADME.md:5Low confidence
- Network access in prose of documentationREADME.md:6Low confidence
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in prose of documentationREADME.md:13Low confidence
- Network access in prose of documentationREADME.md:30Low confidence
- Network access in prose of documentationREADME.md:32Low confidence
- Network access in prose of documentationREADME.md:60Low confidence
- Network access in prose of documentationREADME.md:61Low confidence
- Network access in prose of documentationREADME.md:62Low confidence
- Network access in prose of documentationREADME.md:63Low confidence
- Network access in prose of documentationREADME.md:64Low confidence
- Network access in code of documentationREADME.md:77Low confidence
- Network access in code of documentationREADME.md:79Low confidence
- Network access in prose of documentationREADME.md:179Low confidence
- Network access in prose of documentationREADME.md:181Low confidence
- Network access in prose of documentationREADME.md:205Low confidence
- Network access in prose of documentationREADME.md:206Low confidence
- Network access in prose of documentationREADME.md:207Low confidence
- Network access in prose of documentationREADME.md:211Low confidence
- Network access in prose of documentationREADME.md:212Low confidence
- Network access in prose of documentationREADME.md:213Low confidence
- Network access in prose of documentationREADME.md:214Low confidence
- Dangerous shell operation in code of the SKILL.mdSKILL.md:184High confidence
- Dangerous shell operation in code of the SKILL.mdSKILL.md:271High confidence
- Dangerous shell operation in code of the SKILL.mdSKILL.md:319High confidence
- Dangerous shell operation in code of the SKILL.mdSKILL.md:368High confidence
- Dangerous shell operation in code of the SKILL.mdSKILL.md:418High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
