用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/zhaixin244-wq/fnw --skill rag-sync命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | rag-sync |
| description | End-of-session review and sync of learnings to the personal LightRAG knowledge graph |
| version | 1.0.0 |
| model | sonnet |
| triggers | ["/rag-sync","sync memories","push learnings"] |
Review what happened this session and push non-obvious learnings to your personal LightRAG knowledge graph. Run before ending a productive session.
Scan the conversation for items worth persisting. Look for:
Remove anything that:
/rag-remember this sessionFormat each item using the /rag-remember format:
[TYPE] Title — YYYY-MM-DD
What: ...
Why: ...
Files: ... (if applicable)
Present the list of items to store. Example:
Ready to sync 3 items to personal memory:
- [DECISION] Switched auth from JWT to session tokens — 2026-04-01
- [FEEDBACK] User prefers single bundled PRs for refactors
- [CONFIG] LightRAG project instance moved to port 9625
Proceed? (y/n)
Wait for user confirmation before inserting.
node -e "
const BASE = process.env.LIGHTRAG_SERVER_URL || 'http://YOUR_LIGHTRAG_HOST:YOUR_PERSONAL_PORT';
(async () => {
const auth = await fetch(BASE + '/auth-status').then(r => r.json());
const token = auth.access_token;
const res = await fetch(BASE + '/documents/text', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'Authorization': 'Bearer ' + token
},
body: JSON.stringify({
file_source: 'DESCRIPTION_HERE',
text: 'CONTENT_HERE'
})
});
console.log('Status:', res.status);
})();
"
Summarize what was synced:
Synced 3 items to personal LightRAG.
Only store things that would save 5+ minutes in a future session.
Good examples:
Bad examples:
YOUR_LIGHTRAG_HOST:YOUR_PERSONAL_PORT/auth-status (guest/disabled mode)LIGHTRAG_SERVER_URL