AI-Driven Development Model Card
这是可索引项目报告证据页：它保留 AI-Driven Development Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
AI-Driven Development Model Card
| Field | Value |
|---|---|
| Repository | CodeAlive-AI/ai-driven-development |
| Category | Cross-Agent Development Skills and Hooks |
| Stars / forks snapshot | 74 / 3 |
| Language | Markdown/Go |
| License | MIT |
| Raw capture | raw-github/codealive-ai_ai-driven-development.md |
| Updated by | hourly public metadata update, 2026-05-25 |
1. Role in Self Evolve
AI-Driven Development 是跨 Claude Code、Codex CLI、OpenCode、Cursor、Gemini 等工具的 skills 与安全 hook 集合，把 bug fix、研究、MCP、subagents、安全和 repo exploration 变成可复用操作协议。
2. Working Principle
engineering practice taxonomy -> cross-agent skills -> safety hooks -> low-friction disciplined agent development workflow
3. Evidence Path
web GitHub page observed 88 commits, MIT license, 74 stars and 3 forks; README says 20 skills plus 1 hook work across Claude Code, Codex CLI, OpenCode, Cursor, Gemini CLI, Antigravity, and Agent Skills standard, with balanced-safety-hooks and token-cheap cross-agent principles. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Cross-Agent Development Skills and Hooks in the raw -> classification -> project card -> site/report pipeline. The reading path is: raw capture -> classification row -> public site card -> project report -> aggregate GitHub analysis.
5. Limits
当前未克隆源码，未运行 benchmark、SDK examples、skill install flows、memory experiments、agent evolution loops 或 production deployments；star/fork/commit 快照来自公开 GitHub 页面文本或可见页面片段。