Partner Skill

搭子.skill / Partner — two-direction cost-split workflow between Claude Code and Codex. Direction A (Codex-driven): Codex orchestrates and implements; Claude Code plans (/goal), polishes UI/interaction, and runs final /codex:review in one reused session. Direction B (Claude-driven): Claude plans and splits the work, runs the idea-king adversarial gate, delegates to Codex background jobs, monitors, and full-reviews before accepting. Use on "搭子" / "双向搭子" / "搭子，恢复" (resume from .partner/), "搭子，配置" (first-run setup wizard), "搭子，试跑" (identity tryout report), 分工给 codex / 让 codex 做 / codex 后台跑 / Claude

67 stars 8 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add LearnPrompt/partner-skill --skill partner-skill

Manual install

git clone --depth 1 https://github.com/LearnPrompt/partner-skill.git /tmp/partner-skill
mkdir -p ~/.claude/skills
cp -r /tmp/partner-skill/. ~/.claude/skills/partner-skill

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 搭子.skill (Partner)

> 我的 Claude Code 和 Codex 天下第一好。

## Overview

Use this skill to run a two-agent coding workflow: Claude Code is the high-value planning, polish, and review agent; Codex is the outer orchestrator and main implementer. Keep Claude Code usage focused because it may be billed through API.

Prefer one long-lived Claude Code session for small and medium tasks: ask Claude for the plan, let Codex implement, then return the diff summary and key files to the same Claude session for UI/interaction polish and final `/codex:review`. This avoids paying Claude to rebuild the same project context and gives Claude enough continuity to improve the work.

Partner is not a delegation excuse. The user remains the owner, Codex remains accountable for repository evidence, and Claude Code is treated as a high-value collaborator whose output must be verified.

## Host Detection

Partner is one Core (this file) plus one host adapter. Decide the host once at the start and say which direction you are in:

- **The host is the runtime that actually loaded this SKILL.md.** Self-identification wins: a prompt that merely mentions the other agent ("让 codex 做", "ask Claude") never switches your identity.
- The `host=codex|claude|generic` marker in `.install-meta` (written by install.sh) is a tiebreaker only, for copies whose load path is ambiguous. It never overrides self-identification.

Read the full skill on GitHub

Details

Skill name: partner-skill
Repository: LearnPrompt/partner-skill
License: MIT
Repo updated: 9 September 2026

FAQ

What does the Partner Skill skill do?

How do I install the Partner Skill skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add LearnPrompt/partner-skill --skill partner-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Partner Skill popular?

It lives in LearnPrompt/partner-skill, which has 67 GitHub stars and 8 forks.

Related skills

Agent Orchestra

3338902669-ops/agent-orchestra

Use when three or more AI agents are available and a task needs coordinated execution, or when work must be handed to another agent, session or tool. It ships the coordination rules as ENFORCED invariants rather than advice: one writer per resource (a conflicting claim is refused and names the holder), a verifier that is never the implementer and whose PASS must carry criterion-linked evidence, a failed verification that blocks both done and dispatch to evidence, three failed rounds that block the task outright, an external action that cannot be dispatched until an approval covering it is reco

AI, LLMs & Agents

Promptmaster

Jakeschincariol/promptmaster-skill

Rewrite the user's raw request into an optimized prompt before answering it, audit it against the 35 credit-waste patterns in waste-patterns.json, and enforce every locked decision in decisions.md so nothing gets re-explained and nothing contradicts itself. Use whenever the user types /promptmaster, prefixes a request with it, or asks to optimize / tighten / fix a prompt.

AI, LLMs & Agents22

Ham

kromahlusenii-ops/ham

Set up Hierarchical Agent Memory (HAM) — scoped CLAUDE.md files per directory that reduce token spend. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "ham sync".

AI, LLMs & Agents

Mcdonalds

Lemon177777/mcd-omni-assistant

麦当劳中国官方 MCP 全能助手。当用户提到麦当劳、麦乐送、开心乐园餐、麦麦省优惠券、领券、点麦当劳、外送到家、得来速、麦当劳积分、积分抽奖、积分商城兑换、麦当劳餐品热量/营养、麦当劳订单查询或取消、麦当劳周边玩具与活动时使用。覆盖官方 35 个工具的全部能力，内置领券、到店点餐、外送、玩具雷达、积分抽奖、热量计算、优惠计算器七大工作流。

AI, LLMs & Agents

AI Bounty Claim

aelf-hzz780/AI-bounty-skill

Use when claiming the AI bounty on the tDVV mainnet sidechain. This public claim skill now supports Portkey AA/CA only, requires CA sync and holder preflight before any write, and routes to AA/CA onboarding, AA/CA claim, or diagnostics-only stop handling.

AI, LLMs & Agents

Claude Code Eyes

fcavalcantirj/claude-code-eyes

Look at real hardware, screens, panels, and wiring on a desk or workbench through a camera, so Claude can SEE physical output that no unit test, log, or API can. Use whenever the user says "are you seeing this?", "olha isso", "look at this", "watch this", "can you see...", "check the camera", "look at the screen" / "look at the display", "is this wired right?", or "what's this part?"; asks to visually verify a rendered display, LCD, LED, or panel; wants a wiring, polarity, or voltage-rail check before power-on; or needs to confirm a font, layout, clipping, or on-screen value renders correctly

AI, LLMs & AgentsIn 1 list12

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.