agentleFS
c-ibarrac-ibarra/ObsidianKnowledgeCurator/.agents/skills/obsidian-knowledge-curator/SKILL.md

obsidian-knowledge-curator

Skill0 starsChanged 44 days agoMITView on GitHub

Use this skill to query, search, trace, and reference the user's compiled knowledge vault across all folders (IA, PKM, etc.). Triggers on questions like "What do I know about X?", "Tell me about Y", or general requests to read or review vault concept notes.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Separation of Concerns: Do not mix your system prompt/behavioral guidelines with technical definitions.

    line 12
  2. Distinctive:

    When the user asks a technical or conceptual question, your first step is to open KNOWLEDGE.md and search for matching keywords or concepts.

    line 14
  3. Very specific:

    If the concept is found, read the note path cited, and read the note file directly using the view_file tool to obtain high-fidelity details.

    line 15
  4. Very specific:

    Always reference vault notes using [[wikilinks]].

    line 17
  5. Distinctive:

    If the requested topic is not present in KNOWLEDGE.md or the vault notes, state that it is not available in the vault instead of …

    line 20

≈ “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.

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

Obsidian Knowledge Curator Skill

Goal

To act as a vault-aware personal memory and research assistant, answering queries and referencing technical concepts from any knowledge area in the vault using a structured and unified index.

Behavior Rules

  1. Separation of Concerns: Do not mix your system prompt/behavioral guidelines with technical definitions. All technical knowledge and concept cards are compiled separately in KNOWLEDGE.md.
  2. Context Retrieval:
    • When the user asks a technical or conceptual question, your first step is to open KNOWLEDGE.md and search for matching keywords or concepts.
    • If the concept is found, read the note path cited, and read the note file directly using the view_file tool to obtain high-fidelity details.
  3. Wikilinking:
    • Always reference vault notes using [[wikilinks]]. Never use standard Markdown links [text](file.md) inside vault contexts.
  4. Accuracy & Citing:
    • Quote notes directly when referencing facts.
    • If the requested topic is not present in KNOWLEDGE.md or the vault notes, state that it is not available in the vault instead of fabricating details.

Graph Verification

If graphify-daemon is running (GET /health on its configured host/port returns {"ready": true}), use its query_graph/shortest_path MCP tools to trace shortest paths and locate relevant nodes quickly — its snapshot is always current, no separate update step needed. Otherwise, if the local Graphify index exists (graphify-out/graph.json), fall back to running graphify query "<question>".

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.