PRB Agent Skills Model Card
这是可索引项目报告证据页：它保留 PRB Agent Skills 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。
PRB Agent Skills Model Card
| Field | Value |
|---|---|
| Repository | PaulRBerg/agent-skills |
| Category | Personal Codex Agent Skills Pack |
| Stars / forks snapshot | 59 / 2 |
| Language | Shell |
| License | MIT |
| Raw capture | raw-github/paulrberg_agent-skills.md |
| Updated by | hourly public metadata update, 2026-05-25 13:21 +0800 |
1. Role in Self Evolve
PRB Agent Skills is a compact personal skill pack for Claude Code and Codex, with executable workflow guidance for review, commits, docs, release work and task execution.
2. Working Principle
personal skill modules -> progressive disclosure -> repeatable coding workflows
3. Evidence Path
web GitHub page observed 141 commits, MIT license, Shell/Just stack, 59 stars and 2 forks; README lists npx skills add installation plus skills for code review, simplification, docs, commits, release, Vitest, Tailwind and end-to-end work.. Shell GitHub API access remained DNS-blocked and the local gh token was invalid in this run, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain how PRB Agent Skills fits the raw -> classification -> project card -> site/report pipeline. It is useful for comparing whether self-evolution is implemented as skill supply, memory substrate, planning persistence, harness governance, multi-agent orchestration, provider API packaging, or benchmark/evaluation infrastructure.
5. Limits
当前未克隆源码，未运行 benchmark、skill install flows、memory experiments、MCP servers、agent evolution loops、security scanners 或 production deployments；star/fork/commit/release 快照来自公开 GitHub 页面文本或可见页面片段。