research-to-vault
Skill0 starsChanged 5 months agoMITView on GitHub
Use when Christian wants to research a topic and keep the result, not just read it once. Triggers on 'research X', 'look into X and save it', 'find out about X for the business/learning'. Researches with sources, synthesizes into a structured note, and files it in the right Obsidian PARA folder with backlinks so it joins his knowledge base instead of evaporating.
In this repository9 other files it gives its agents.
- ai-brainSkill
- assumption-checkSkill
- cover-letter-loopSkill
- design-inspoSkill
- luno-osSkill
- memory-hygieneSkill
- skill-routerSkill
- telegram-bot-factorySkill
- vault-librarianSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Research: use deep-research or WebSearch/WebFetch.
- Distinctive: line 21
Index/log: if it's a notable resource.
- Distinctive: line 25
No AI filler, no em dashes.
- Distinctive: line 26
If findings contradict something already in the vault, surface the conflict, don't silently overwrite.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Research to Vault
Bridges open research and the permanent knowledge base. Output is a note he can find and link to later, not a throwaway answer.
Procedure
- Scope: confirm the question and why he needs it (business decision, learning, build). One line is enough.
- Research: use
deep-researchorWebSearch/WebFetch. Prefer primary sources. Track every source URL. - Synthesize into a structured note:
- Title + one-line summary at top.
- Key findings (bullets, specific, with figures where relevant).
- "So what for Christian" — the practical takeaway for Luno / learning / the build.
- Sources list with URLs and access date (UTC+8).
- File it via
vault-librarian: pick the PARA folder (Resource for reference, Project if tied to active work), add[[backlinks]]to related notes, link the relevant hub note to it. - Index/log if it's a notable resource.
Quality rules
- Cite sources. Flag anything uncertain or contested instead of stating it flat.
- No AI filler, no em dashes. Concrete over abstract.
- If findings contradict something already in the vault, surface the conflict, don't silently overwrite.
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.

