Kim Orchestrator

What it does

When your agent uses it

• Agent Workflows work in your project

Example prompts

• “gemini”
• “kim team”
• “kim-team”
• “/kim-orchestrator”

Requirements

• A Bash shell
• Pre-approved tools (allowed-tools): Read, Write, Bash, Task

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Claude Code - 需求分析和技术方案设计
2. 2Codex CLI - 代码生成
3. 3Gemini CLI - 代码审查

What it can do on your machine

Read from SKILL.md and the folder at commit 0cb7078. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Bash
  • Task

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Shell), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Kim Orchestrator loads about 433 tokens when it runs. Until then it costs about 128 tokens; SKILL.md has 46 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~128

When it runs · the whole SKILL.md, loaded when a task matches

~433

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Bash, Task

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from KimYx0207/Claudecode-Codex-Gemini at commit 0cb7078, republished under its MIT licence (© KimYx0207). 46 words, ~433 tokens.

name

kim-orchestrator

description

多AI协作编排技能 - 自动协调Claude、Codex、Gemini完成需求分析→代码生成→代码审查工作流。 【核心触发场景】 - 开发任务、写代码、实现功能、编程任务 - 新功能开发、功能实现、代码实现 - 重构、优化代码、代码改进 - Bug修复、问题修复、错误处理 - 系统设计、架构设计、模块设计 【显式触发词】 - "AI编排"、"ai编排"、"多AI协作"、"三引擎"、"三AI" - "codex"、"gemini"、"kim team"、"kim-team" - "协作开发"、"编排流程" 【任务类型触发】 - 实现XXX功能、开发XXX模块、写一个XXX - 创建XXX、构建XXX、搭建XXX - 添加XXX功能、新增XXX特性 - 修改XXX、更新XXX、升级XXX - 修复XXX、解决XXX问题 - 重构XXX、优化XXX性能 - 设计XXX架构、规划XXX系统 【技术任务触发】 - API开发、接口实现、后端开发、前端开发 - 数据库设计、表结构、CRUD操作 - 用户认证、登录注册、权限控制 - 文件处理、数据导入导出 - 第三方集成、SDK接入

allowed-tools

Read, Write, Bash, Task

{
  "task_description": "任务描述",
  "features": ["功能列表"],
  "tech_stack": {"language": "", "framework": "", "libraries": []},
  "file_structure": {"files": [{"path": "", "purpose": ""}]},
  "key_points": ["关键实现要点"],
  "risks": ["潜在风险"]
}

使用 mcp__codex__codex 工具：
- prompt: 根据phase1的需求生成代码
- conversationId: "ai_team_<timestamp>"

使用 mcp__gemini__gemini 工具：
- prompt: 审查phase2的代码
- reviewMode: true

# 简单任务
"实现用户登录功能"

# 复杂任务
"实现JWT登录，包含注册、登录、token刷新"

# 系统设计
"设计RBAC权限系统"

© KimYx0207, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (scripts) in .claude/skills/kim-orchestrator of KimYx0207/Claudecode-Codex-Gemini.

• SKILL.md
• prompts/health-check.md
• prompts/phase1-analyze.md
• prompts/phase2-code.md
• prompts/phase3-review.md
• scripts/orchestrate.sh
• skill.yaml

Open the folder on GitHubat commit 0cb7078

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in KimYx0207/Claudecode-Codex-Gemini, which our catalogue first saw on October 7, 2026.

• KimYx0207/Kim_Servicetools/claudecode-codex-gemini/host/claude/skills/kim-orchestrator