agentleFS
Sign inStart free
LuciowayLucioway/way-stack/skills/vault-query/SKILL.md

vault-query

Skill0 starsChanged 2 months agoMITView on GitHub

Use when user asks 'what do we know about X?', 'have we solved this before?', 'find notes on Y'. Reads vault index → drills into relevant pages → synthesizes answer with [[wikilink]] citations. Karpathy LLM Wiki pattern.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If nothing in vault matches → say so explicitly.

    line 39
  2. Very specific:

    Run vault-ingest on a new source to fill the gap

    line 40
  3. Distinctive:

    Run WebSearch if online info would help

    line 41
  4. Very specific:

    Follow with citations as [[wikilink]]

    line 46

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

vault-query — Karpathy LLM Wiki Query

When to use

User asks:

  • "what do we know about X?"
  • "have we solved this before?"
  • "find notes on Y"
  • "any learnings about Z?"
  • "check the vault for …"

Process

  1. Locate vault — read $VAULT_PATH from ~/.claude/CLAUDE.md or probe standard locations
  2. Read index.md — catalog-first retrieval
  3. Grep for topic across 02_KNOWLEDGE/ + 03_REFERENCE/ + 00_INBOX/ — pattern: case-insensitive substring or tag match
  4. Drill into matching pages — read relevant ones
  5. Synthesize answer with citations:
    Based on vault: X works this way because [[02_KNOWLEDGE/patterns/x|X pattern]].
Seen in: [[01_PROJECTS/proj-a]], [[01_PROJECTS/proj-b]].
Gotcha documented in [[02_KNOWLEDGE/learnings/x-edge-case]].
  6. Promote valuable queries — if the synthesis itself is novel (comparison across sources, new connection), ask user: "save as new page?" → if yes, write to 02_KNOWLEDGE/ and update index
  7. Append to log.md:
    ## [YYYY-MM-DD] query | <question>
Answered from [[...pages...]]

Fallback

If nothing in vault matches → say so explicitly. Do NOT fabricate. Offer to:

  • Run vault-ingest on a new source to fill the gap
  • Run WebSearch if online info would help

Output format

  • Lead with direct answer
  • Follow with citations as [[wikilink]]
  • End with confidence level: "high (3 sources agree)" / "medium (single source)" / "low (inferred)"

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free