Eigent Agent Skills Model Card
这是可索引项目报告证据页：它保留 Eigent 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。
Eigent Agent Skills Model Card
| Field | Value |
|---|---|
| Repository | eigent-ai/agent-skills |
| Category | Cowork Agent Skills Collection |
| Stars / forks snapshot | 10 / 0 |
| Language | Markdown/Python/TypeScript |
| License | Not observed |
| Raw capture | raw-github/eigent-ai_agent-skills.md |
| Updated by | hourly public metadata update, 2026-05-25 13:21 +0800 |
1. Role in Self Evolve
Eigent Agent Skills is an open cowork-agent skill collection that packages research, marketing, document, analytics, image/video and communication workflows as reusable agent skills.
2. Working Principle
skill catalog -> category taxonomy -> agent cowork workflows
3. Evidence Path
web GitHub page/search evidence observed skill categories for recent-discussion research, SEO audit, ML failure audit, PDF/DOCX/XLSX/PPTX work, media generation and internal communications; search result observed open-source cowork agent skills collection and npx install flows.. 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 Eigent 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。