agentleFS
AbilityaiAbilityai/cornelius/.claude/skills/search-vault/SKILL.md

search-vault

Skill109 starsChanged 39 days agoMITView on GitHub

Quick search across Obsidian vault using keywords or semantic similarity

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search the Obsidian vault using both semantic and keyword-based search.

    line 11
  2. Distinctive:

    Use Local Brain Search for all semantic search operations.

    line 15
  3. Distinctive:

    Semantic Search: - Use Local Brain Search:

    line 26
  4. Very specific:

    Keyword Search: - Use Grep:

    line 38
  5. Very specific:

    Use Read tool to get full content

    line 45
  6. Distinctive:

    Keep results concise and actionable.

    line 62

≈ “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.

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

Quick Vault Search

Search the Obsidian vault using both semantic and keyword-based search.

Local Brain Search

Use Local Brain Search for all semantic search operations. Supports two modes:

  • static: Fast vector similarity (default)
  • spreading: SYNAPSE-inspired graph traversal (better for connections)

Note: Usage-based learning is active - searches are tracked and rankings improve over time.

Query

$ARGUMENTS

Instructions

  1. Semantic Search - Use Local Brain Search:
    # For quick lookups, use static mode
    BRAIN_READ_SCOPE=core,Books,document-insights resources/local-brain-search/run_search.sh "$ARGUMENTS" --limit 5 --json
    
    # For finding connections, use spreading mode
    BRAIN_READ_SCOPE=core,Books,document-insights resources/local-brain-search/run_search.sh "$ARGUMENTS" --mode spreading --limit 5 --json
    Read role: lookup (contract: scope-mount): the reasoning mount, output grouped as your thinking (core) · what you have read (Books / Document Insights) · records (a reference scope, only if a trigger mounted it); --scope core pins to your own notes.
  2. Keyword Search - Use Grep:
    • Pattern: $ARGUMENTS
    • Path: Brain/
    • Output mode: "files_with_matches" to get file list
    • Then use output mode: "content" with -C flag for context
  3. Retrieve Content - For the top result from semantic search:
    • Use Read tool to get full content

Output Format

# Search Results: "$ARGUMENTS"

## Semantic Matches
[Top 5 notes with similarity/activation scores]

## Keyword Matches
[Top 5 notes with context snippets from Grep]

## Top Result Content
[Full content of the most relevant note]

Keep results concise and actionable. Highlight the most relevant findings.

State Dependencies

SourceLocationReadWriteDescription
Brain notesBrain/**/*.mdXAll vault notes for search
Local Brain Search indexresources/local-brain-search/XVector index for semantic search
Memory configresources/local-brain-search/memory_config.pyXTunable memory parameters

Completion Checklist

  • Semantic search executed with top 5 results
  • Keyword search executed with file matches
  • Top result full content retrieved and displayed
  • Results formatted and highlighted

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.