rad-execute — for Claude Code rad-execute, RadOrchestration, community, for Claude Code, ide skills, orchestration, pipeline.source_control, state.json, and parse its JSON output, {PROJECT_NAME}

v1.0.0
GitHub

关于此技能

适用场景： Ideal for AI agents that need step 1: initialize. 本地化技能摘要： ## Step 1: Initialize You are an orchestrator. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

功能特性

Step 1: Initialize
Step 2: Approve plan
Step 3: Source Control Initialization
If sourceControlInitialized === true, skip to step 4 — resume is ceremony-free.
Proceed with execution.

# 核心主题

for Claude Code orchestration pipeline.source_control state.json and parse its JSON output {PROJECT_NAME}
MetalHexx MetalHexx
[6]
[1]
更新于: 4/24/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
36
Canonical Locale
en
Detected Body Locale
en

适用场景： Ideal for AI agents that need step 1: initialize. 本地化技能摘要： ## Step 1: Initialize You are an orchestrator. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

核心价值

推荐说明： rad-execute helps agents step 1: initialize. Step 1: Initialize You are an orchestrator. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

适用 Agent 类型

适用场景： Ideal for AI agents that need step 1: initialize.

↓ 赋予的主要能力 · rad-execute

适用任务： Applying Step 1: Initialize
适用任务： Applying Step 2: Approve plan
适用任务： Applying Step 3: Source Control Initialization

! 使用限制与门槛

  • 限制说明： Do not try to fix the pipeline code, simply work around it.
  • 限制说明： Requires repository-specific context from the skill documentation
  • 限制说明： Works best when the underlying tools and dependencies are already configured

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作，再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”，而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核，以及是否已经进入工作流落地阶段。

安装路径

先进入安装与验证

如果这项技能值得继续，下一步应该先确认安装命令、CLI 写入路径与环境验证。
可信复核

回到可信合集再做一次复核

如果你还在比较不同技能或供应方，先回到可信合集做二次判断，而不是继续放大仓库噪音。
工作流

如果要进团队流转，转到工作流集合

当你的目标已经不是单个技能，而是团队协作、审批和可重复执行，就应该转到工作流合集继续比较。
实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致，便于搜索引擎理解页面内容。

? FAQ

rad-execute 是什么？

适用场景： Ideal for AI agents that need step 1: initialize. 本地化技能摘要： ## Step 1: Initialize You are an orchestrator. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

如何安装 rad-execute？

运行命令：npx killer-skills add MetalHexx/RadOrchestration/rad-execute。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

rad-execute 适用于哪些场景？

典型场景包括：适用任务： Applying Step 1: Initialize、适用任务： Applying Step 2: Approve plan、适用任务： Applying Step 3: Source Control Initialization。

rad-execute 支持哪些 IDE 或 Agent？

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

rad-execute 有哪些限制？

限制说明： Do not try to fix the pipeline code, simply work around it.；限制说明： Requires repository-specific context from the skill documentation；限制说明： Works best when the underlying tools and dependencies are already configured。

↓ 安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行：npx killer-skills add MetalHexx/RadOrchestration/rad-execute。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    rad-execute 已启用，可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考，但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论，再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

rad-execute

## Step 1: Initialize You are an orchestrator. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows. Step 1: Initialize

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Step 1: Initialize

You are an orchestrator. You'll be using the orchestration skill for this project. Read the skill and prepare to use it to run the execution pipeline.

Step 2: Approve plan

The Master Plan is complete. As a human reviewer, I have approved the plan and am ready to execute. Mark the plan as approved and begin execution of the project.

Step 3: Source Control Initialization

Before the first pipeline tick, ensure pipeline.source_control is populated in state.json. The commit and PR gates read from this state — without it, the walker halts when it reaches either conditional.

  1. Run node {skillRoot}/scripts/gather-context.js --project-name {PROJECT_NAME} and parse its JSON output. {skillRoot} is the directory containing this SKILL.md; {PROJECT_NAME} comes from the /rad-execute argument or conversation context.
  2. If sourceControlInitialized === true, skip to step 4 — resume is ceremony-free.
  3. Otherwise, follow references/source-control-init.md to resolve each init field (prompting only when needed) and fire the source_control_init pipeline event.
  4. Proceed with execution.

Step 4: Execute Plan

Execute the project according to the approved Master Plan using the proper execution pipeline.

Step 5: Pipeline Error Handling

  • If any errors occur with the pipeline during execution, use the log-error skill to log them
  • Do not try to fix the pipeline code, simply work around it.
  • Ensure that error messages are clear, actionable, and include relevant information about the failure point.

相关技能

寻找 rad-execute 的替代方案 (Alternative) 或可搭配使用的同类 community Skill？探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

本地化技能摘要： 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

本地化技能摘要： Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

本地化技能摘要： The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 138.4k
⑂ 0
浏览器

pr-review

Logo of pytorch
pytorch

本地化技能摘要： Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 98.6k
⑂ 0
开发者工具