#100100th of 149 in Skills, plugins and rules
cc-sdd
Spec-driven workflow skills for Claude Code, Codex, Cursor and other coding agents
- Stars
- 3.7k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Sep 2026
- Language
- TypeScript
Missed the latest GitHub check; these facts may be older.
Overview
cc-sdd installs a set of 17 Agent Skills into your project via npx. They cover discovery, requirements, design, tasks and implementation, in a style modeled on Kiro specs. With native subagents, /kiro-impl runs each task through a fresh implementer using TDD, then an independent reviewer. Hosts without subagents run the same flow inline.
Who it is for: Teams using AI coding agents who want spec-gated, reviewed implementation
Strengths
- Same 17-skill set across 8 agents, installed with one npx command
- Specs (requirements.md, design.md, tasks.md) carry boundary and dependency annotations
- Per-task TDD, independent review and auto-debug when native subagents exist
- Templates and rules under the specs settings directory are editable; 14 languages supported
Weaknesses
- Only Claude Code and Codex are stable; the other agents are beta
- README says installing the skills does not verify a host can run the full autonomous loop
- Legacy /kiro:* command modes are deprecated, so v1/v2 users must migrate
- Devin adapter has unverified authenticated task execution
What it needs
- no GPU
- Needs Node.js and npx, a supported AI coding agent (Claude Code, Codex, Cursor, Copilot, etc.)
Also in Skills, plugins and rules
See all 149| Rank | Project | Score |
|---|---|---|
| 1 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #4 | impeccableDesign skill with 24 commands and a detector for AI-generated frontends | 94 out of 100 |
| #5 | ponytailSkill prompt that makes coding agents write less code and add tests | 92 out of 100 |