OpenSite Skills Memory Sync Model Card

这是可索引项目报告证据页：它保留 OpenSite Skills Memory Sync 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。

OpenSite Skills Memory Sync Model Card

1. Role in Self Evolve

OpenSite Skills 把 Claude、Codex、Cursor、Copilot 与 Perplexity Computer 的技能保持在一个 Git 真相源中，并加入跨会话记忆、RAG 与 Playwright 云端上传自动化。

2. Working Principle

single skills repo -> cross-agent skill sync -> persistent cross-session memory -> Playwright cloud upload automation

3. Evidence Path

web GitHub page observed 7 stars and 0 forks, no releases, Python/Shell stack; About text says it is an AI agent skills library built by OpenSite AI, a single git repo that keeps Claude, Codex, Cursor, Copilot and Perplexity Computer in sync with persistent cross-session memory and automated cloud upload via Playwright; topics include multi-agent, persistent-memory, codex, rag, github-copilot, ai-workflow, claude-code, and agent-skills-standard. Shell GitHub API access remained blocked by DNS and local gh auth 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 Cross-Agent Skills and Memory Sync 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、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。