rag-project-sync
Skill2 starsChanged 7 months agoMITView on GitHub
End-of-session review and sync of project-specific learnings to the project-level LightRAG graph
- Reads credentials
- Sends data out
In this repository6 other files it gives its agents.
- rag-project-querySkill
- rag-project-rememberSkill
- rag-querySkill
- rag-rememberSkill
- rag-setup-projectSkill
- rag-syncSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 59
Wait for confirmation before inserting.
- Distinctive: line 90
Only store things that would save 5+ minutes in a future session working on this project.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
RAG Project Sync — End-of-Session Project Memory Sync
Review what happened this session and push project-relevant learnings to the project-level LightRAG knowledge graph.
Workflow
Step 1: Review the session
Scan the conversation for project-specific items worth persisting:
- Architecture decisions — component design, data flow changes, API structure
- Conventions established — naming patterns, file organization, coding standards
- Dependencies added/changed — new packages, version bumps, API integrations
- Config changes — env vars, build settings, deployment config
- Requirements clarified — business rules, constraints, edge cases discovered
- Gotchas found — non-obvious behaviors, platform quirks, workarounds needed
Step 2: Filter ruthlessly
Remove anything that:
- Is already in the codebase (code, comments, configs)
- Is in git history (commits, diffs)
- Was already stored via
/rag-project-rememberthis session - Is personal (not project-specific) — redirect to
/rag-syncinstead - Is ephemeral (current branch state, temp files)
Step 3: Format entries
Format each item using the /rag-project-remember format:
[TYPE] Title — YYYY-MM-DD
What: ...
Why: ...
Files: ... (if applicable)Step 4: Confirm with user
Present the list:
Ready to sync 2 items to project memory:
- [ARCHITECTURE] API routes use controller pattern with service layer — 2026-04-01
- [CONVENTION] All database queries go through repository classes — 2026-04-01
Proceed? (y/n)
Wait for confirmation before inserting.
Step 5: Insert each item
node -e "
const BASE = 'http://YOUR_LIGHTRAG_HOST:YOUR_PROJECT_PORT';
const API_KEY = process.env.LIGHTRAG_API_KEY || 'YOUR_API_KEY';
(async () => {
const res = await fetch(BASE + '/documents/text', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'X-API-Key': API_KEY
},
body: JSON.stringify({
file_source: 'DESCRIPTION_HERE',
text: 'CONTENT_HERE'
})
});
console.log('Status:', res.status);
})();
"Step 6: Report
Synced 2 items to project LightRAG.
Quality bar
Only store things that would save 5+ minutes in a future session working on this project.
Good examples:
- "The payment service requires idempotency keys — without them, duplicate charges occur"
- "Tests must run against the staging database, not local SQLite (schema divergence)"
Bad examples:
- "Added a new component called UserCard"
- "Fixed lint errors"
- "Installed express"
Infrastructure
- Server:
YOUR_LIGHTRAG_HOST:YOUR_PROJECT_PORT - Auth: X-API-Key header (auth-enabled mode)
- Env var:
LIGHTRAG_API_KEY
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

