Claude Skill

gotalab/cc-sdd

Minimal SDD harness that transforms approved specs into long-running autonomous implementations using Claude Skill for Claude Code, Codex, Cursor, Copilot, and other AI coding assistants.

Overview

Stars3,485
Forks258
LanguageTypeScript
Last pushed2026-05-20
Last synced2026-06-17
View on GitHub

Repository

Ownergotalab
Repositorycc-sdd
Full namegotalab/cc-sdd
Repo ID1,021,219,064

Install this Skill

npx cc-sdd@latest

Registry

Typecursor_rule
Quality score75/100
Verificationreadme_parsed
Last verified2026-05-30
Platforms
ClaudeCodexCursor
Capabilities
pdfterminalworkflowagent-skillsclaude-codecodexcursorgemini-cligithub-copilotkiro
Detected files
README.mddocs
Install methods
  • npx cc-sdd@latest
  • npx cc-sdd@latest --codex-skills --lang ja # Codex, Japanese
  • npx cc-sdd@latest --cursor-skills --lang zh-TW # Cursor IDE, Traditional Chinese
  • npx cc-sdd@latest # Claude Code Skills (default)
  • npx cc-sdd@latest --claude-skills # Claude Code Skills

Summary

A minimal, adaptable Software Design Document (SDD) harness that transforms approved specifications into long-running autonomous implementations. It integrates Claude Skill agent capabilities for popular AI coding assistants like Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.

Chinese description

将已批准的规格转化为长期自主运行的实现。构建一个最小化、可适应的软件设计文档(SDD)框架,集成针对Claude Code、Codex、Cursor、Copilot、Windsurf、OpenCode、Gemini CLI及Antigravity的Claude Skill代理能力。

Key features

  • Minimal and adaptable SDD harness
  • Turns specs into autonomous implementations
  • Integrates Claude Skill for multiple AI coding assistants
  • Supports long-running execution
  • Agent Skills for steering and subagents
  • Spec-driven development approach

Use cases

  • Automated code generation from specifications
  • Long-running autonomous software development
  • AI-assisted software design documentation
  • Multi-agent coding workflows
  • Spec-driven development pipelines
  • Integration with various AI coding tools

README excerpt

# cc-sdd: Long-running spec-driven implementation for AI coding agents <!-- npm badges --> [![npm version](https://img.shields.io/npm/v/cc-sdd?logo=npm)](https://www.npmjs.com/package/cc-sdd?activeTab=readme) [![install size](https://packagephobia.com/badge?p=cc-sdd)](https://packagephobia.com/result?p=cc-sdd) [![license: MIT](https://img.shields.io/badge/license-MIT-green.svg)](./LICENSE) <div align="center" style="font-size: 1.1rem; margin-bottom: 1rem;"><sub> Package README: <a href="./tools/cc-sdd/README.md">English</a> | <a href="./tools/cc-sdd/README_ja.md">日本語</a> | <a href="./tools/cc-sdd/README_zh-TW.md">繁體中文</a> </sub></div> ## Turn approved specs into long-running autonomous implementation One command installs an agentic SDLC workflow as Agent Skills: discovery, requirements, design, tasks, and autonomous implementation with per-task independent review. Works across 8 AI coding agents, with the same 17-skill set on each. 👻 **Kiro-inspired.** Similar spec-driven, agentic SDLC style as Kiro IDE. Existing Kiro specs remain compatible and portable. ## What's new in v3.0 cc-sdd v3.0 is a rework around Agent Skills and long-running autonomous implementation. - **`/kiro-discovery` as the new entry point.** Discovery routes new work into one of: extend an existing spec, implement directly with no spec, create one new spec, decompose into multiple specs, or mixed decomposition. It writes `brief.md` and, when needed, `roadmap.md`, so you can resume a workstream without re-explaining scope. - **`/kiro-impl` for long-running autonomous implementation.** Each task gets a fresh implementer running TDD (RED → GREEN) behind a feature flag, an independent reviewer, and an auto-debug pass that investigates root causes in a clean context when the implementer is blocked

Topics

Explore more

Data from GitHub. Synced on 2026-06-17