rag-intake
Skill1 starsChanged 3 months agoMITView on GitHub
Use when admitting user-provided files into D:/RAG, checking a material list, running sensitive prechecks, or producing admission/reject reports for the local RAG knowledge base.
In this repository22 other files it gives its agents.
- analysis-skillSkill
- auto-testcase-generatorSkill
- create-agent-skillSkill
- create-skillSkill
- development-systemSkill
- domain-modelingSkill
- figma-rest-syncSkill
- grill-systemSkill
- grill-with-docsSkill
- rag-change-impactSkill
- rag-downstream-handoffSkill
- rag-governanceSkill
- rag-querySkill
- rag-schemaSkill
- rag-structure-fidelitySkill
- rag-systemSkill
- researchSkill
- session-handoffSkill
- skill-packagerSkill
- task-understanding-routerSkill
- ui-testSkill
- write-requirements-prdSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Only read files explicitly provided by the user or listed in D:/RAG/00_inbox/candidate-materials.json.
- Distinctive: line 11
Do not scan directories to discover new materials.
- Distinctive: line 12
Run sensitive precheck before content extraction.
- Distinctive: line 13
Do not echo matched sensitive values in reports.
- Very specific: line 19
Verify path, material ID, status, hash when available, and knowledge_space_id metadata.
- Distinctive: line 20
Run format identification and no-value sensitive precheck.
- Very specific: line 21
Write an admission or reject report under D:/RAG/reports.
≈ “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 Intake
Operating Rules
- Only read files explicitly provided by the user or listed in
D:/RAG/00_inbox/candidate-materials.json. - Do not scan directories to discover new materials.
- Run sensitive precheck before content extraction.
- Do not echo matched sensitive values in reports.
- Block materials with credential, token, cookie, or unredacted production/customer-data shapes.
Workflow
- Load
D:/RAG/manifest.jsonandD:/RAG/00_inbox/candidate-materials.json. - Verify path, material ID, status, hash when available, and
knowledge_space_idmetadata. - Run format identification and no-value sensitive precheck.
- Write an admission or reject report under
D:/RAG/reports. - Set candidate status only; never create RC.
Validation
Run python D:\RAG\scripts\validate_rag_mvp.py.
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.