Co-Pilot / 辅助式
更新于 a month ago

open-skilled-sdd

Fforztf
0.0k
forztf/open-skilled-sdd
80
Agent 评分

💡 摘要

Open-skilled-sdd通过可组合技能增强AI编码助手,以支持规范驱动开发。

🎯 适合人群

希望改善编码助手的AI开发者寻求更好文档工具的项目经理对规范驱动方法感兴趣的软件工程师旨在生成结构化提案的技术写作人员教授软件开发最佳实践的教育工作者

🤖 AI 吐槽:看起来很能打,但别让配置把人劝退。

安全分析中风险

风险:Medium。建议检查:是否执行 shell/命令行指令;是否发起外网请求(SSRF/数据外发);文件读写范围与路径穿越风险;依赖锁定与供应链风险。以最小权限运行,并在生产环境启用前审计代码与依赖。

Open Spec-Driven Development Skills (open-skilled-sdd)

中文文档

Enhancing AI coding assistants through open Spec-driven development (Spec-driven development for AI coding assistants), adopting the Claude Code Skills approach, compatible with various CLI and IDE AI coding assistants that support AGENTS.md.

License: MIT

Why?

When the code or documentation generated by an AI coding assistant is disappointing, it's unclear whether it's because:

  1. The large model's capabilities are problematic.
  2. The AI coding assistant is problematic: providing inappropriate context (including system prompts).
  3. The prompts I wrote are problematic.

The focus is on breaking through "2. The AI coding assistant is problematic", but because the built-in spec-driven development methods (context engineering, system prompts, etc.) of various CLI and IDE AI coding assistants are not public, they are basically black boxes, making it impossible to analyze or optimize them yourself. I looked for various open spec-driven development solutions, such as the 6A workflow, PRPs, Spec Kit, OpenSpec, spec-workflow-mcp, BMad-Method, etc., to see which one is the most suitable, and then proceed to optimize it myself. I roughly used these solutions and found that they each have their pros and cons. My first thought was to create a comprehensive solution, integrating the advantages of each solution and removing the parts I thought were unsuitable. I soon discovered that this path was a dead end; this idea is exactly the channel that various AI coding assistants are currently working on. I cannot do better than these vendors. Moreover, from a philosophical point of view, a comprehensive solution (limited capabilities) cannot adapt to all types of scenarios (infinite scenarios). At this time, Claude Code Skills came out. I found this approach good; wouldn't infinite skills be able to adapt to infinite scenarios? At the same time, I found skilled-spec.

My idea is to convert OpenSpec, PRPs, Spec Kit, spec-workflow-mcp, BMad-Method, 6A workflow, etc., including good spec-driven development methods that appear in the future, into individual composable Skills, which are open and can be optimized by yourself.

Skills

| Methodology | Skill | Trigger Words | Purpose | | :----------------- | :-------------------------------- | :----------------------------------------------------------------------- | :--------------------------------------------------- | | openspec | openspec-proposal-creation | "openspec proposal", "openspec plan" | Generate structured proposals with EARS requirements | | | openspec-implementation | "openspec implement", "openspec build" | Execute tasks with testing and progress tracking | | | openspec-archiving | "openspec archive" | Merge spec differences and create archives | | | openspec-context-loading | "openspec context", "openspec what specs exist", "openspec show changes" | Discover specs, search requirements, show dashboard | | openspec (Chinese) | openspec-proposal-creation-cn | "openspec提案", "openspec需求" | Generate structured proposals with EARS requirements | | | openspec-implementation-cn | "openspec开发" | Execute tasks with testing and progress tracking | | | openspec-archiving-cn | "openspec归档" | Merge spec differences and create archives | | | openspec-context-loading-cn | "openspec上下文", "openspec有哪些规范", "openspec显示变更" | Discover specs, search requirements, show dashboard | | | | | |

Each skill has detailed documentation in its SKILL.md file.

Install

Copy directly to project (Claude Code, simple):

  1. Copy all subdirectories under skills/ in this project to .claude/skills/ in your project.
  2. Commit to version control.
  3. The team automatically gets the skills after cloning.

Copy directly to global (Claude Code, simple):

  1. Copy all subdirectories under skills/ in this project to ~/.claude/skills/.

Plugin-based (Claude Code, auto-update):

  1. Install the private marketplace repository: /plugin marketplace add forztf/open-skilled-sdd in Claude Code.
  2. Install plugins: /plugin -> 1. Browse and install plugins -> open-skilled-sdd-marketplace -> Press space to select -> Press i to install in Claude Code. Or install them one by one using commands:
    /plugin install open-skilled-sdd@open-skilled-sdd-marketplace
    

Other AI CLI/IDE Installation (for AI CLI/IDE that support AGENTS.md,Codex、Gemini、Cursor):

Use npx for direct installation:

npx open-skilled-sdd # Install skills to .claude/skills/ npx open-skilled-sdd sync # Sync skills to AGENTS.md

Or install globally then use the CLI:

npm install -g open-skilled-sdd open-skilled-sdd # Install skills locally open-skilled-sdd install # Explicit install command open-skilled-sdd sync # Sync to AGENTS.md open-skilled-sdd --help # Show help

Sync Skills to AGENTS.md:

open-skilled-sdd sync # Auto-sync all skills (creates AGENTS.md if needed) open-skilled-sdd sync --yes # Same as above (deprecated flag)

Features:

  • Automatically creates AGENTS.md if it doesn't exist
  • Syncs all installed skills to AGENTS.md (non-interactive by default)
  • Updates existing skills section or creates new one

License

MIT License - see LICENSE

Acknowledgments

  • OpenSpec - Methodology & CLI Tool
  • Anthropic - Claude Code & Skills Framework
  • EARS - Requirements Syntax
  • skilled-spec - Original English version
  • OpenSpec - OpenSpec excels at modifying existing behavior (1→n).

Links

五维分析
清晰度8/10
创新性8/10
实用性9/10
完整性8/10
可维护性7/10
优缺点分析

优点

  • 将多种方法整合为可组合的技能
  • 支持多种AI编码助手
  • 促进结构化提案生成

缺点

  • 对某些用户来说安装过程复杂
  • 可能需要熟悉多种方法论
  • 更新时可能存在依赖问题

相关技能

pytorch

S
toolCode Lib / 代码库
92/ 100

“它是深度学习的瑞士军刀,但祝你好运能从47种安装方法里找到那个不会搞崩你系统的那一个。”

agno

S
toolCode Lib / 代码库
90/ 100

“它承诺成为智能体领域的Kubernetes,但得看开发者有没有耐心学习又一个编排层。”

nuxt-skills

S
toolCo-Pilot / 辅助式
90/ 100

“这本质上是一份组织良好的小抄,能把你的 AI 助手变成一只 Nuxt 框架的复读机。”

免责声明:本内容来源于 GitHub 开源项目,仅供展示和评分分析使用。

版权归原作者所有 forztf.