Anthropic Skills Model Card
这是可索引项目报告证据页：它保留 Anthropic 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。
Anthropic Skills Model Card
| Field | Value |
|---|---|
| Repository | anthropics/skills |
| Category | 官方 Agent Skills 标准样例库 |
| Stars / forks snapshot | 142,000 / 16800 |
| Language | Python |
| License | Mixed: Apache-2.0/source-available |
| Raw capture | raw-github/anthropics_skills.md |
| Updated by | hourly public metadata update, 2026-06-04 01:56 +0800 |
1. Role in Self Evolve
Anthropic 官方 Agent Skills 公共仓库，提供技能规范、模板、示例技能与 Claude Code 插件市场安装入口，是技能生态的上游参考实现。
2. Working Principle
官方技能规范 -> 示例技能 -> Claude Code/Claude API 加载
3. Evidence Path
The current run rechecked a cached GitHub search result observed on 2026-06-04, with crawl recency surfaced as last week. That cached public result showed 142k stars, 16.8k forks, 248 issues, 637 pull requests, Python as the primary language, and explicit skills / spec / template structure plus Claude Code marketplace install flows. Shell GitHub API was still blocked by DNS and local gh auth remained invalid, so this card marks freshness as cached public-page evidence rather than live API verification.
4. Teaching Use
Use this card to explain whether a repository is a runtime, benchmark, harness-evolution loop, memory/skill substrate, or resource index. The key 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；star/fork/commit 快照来自公开 GitHub 页面文本。