agentleFS
Sign inStart free
c-ibarrac-ibarra/ObsidianKnowledgeCurator/.agents/skills/graphify-query/SKILL.md

graphify-query

Skill0 starsChanged 43 days agoMITView on GitHub

Queries the local Knowledge Graph — via graphify-daemon's MCP tools when it's running, else the graphifyy CLI directly — to search the codebase or vault semantically and explicitly. Use this skill before using grep or searching files when you need to understand relationships, find notes, or explore the codebase structure efficiently.

1 other project uses 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. 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
  1. Distinctive:

    When searching for how concepts are connected in the Obsidian Vault.

    line 11
  2. Distinctive:

    When trying to understand the architecture or relationships in the codebase.

    line 12
  3. Distinctive:

    When you want to find "neighbors" of a specific node/concept.

    line 13
  4. Very specific:

    Fallback, if the daemon isn't running: use the graphifyy CLI directly:

    line 19

≈ “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

Graphify Query Skill

This skill allows you to query the local knowledge graph to find connections between notes, files, classes, and concepts without consuming excessive tokens or grepping the entire repository.

When to use

  • When searching for how concepts are connected in the Obsidian Vault.
  • When trying to understand the architecture or relationships in the codebase.
  • When you want to find "neighbors" of a specific node/concept.

Usage

Primary, if graphify-daemon is running (GET /health on its configured host/port, default 127.0.0.1:8787, returns {"ready": true}): call its MCP tools directly — query_graph, get_node, get_neighbors, get_community, god_nodes, graph_stats, shortest_path. These answer from the daemon's resident, always-current snapshot; there is no separate "update" step, since its own vault watcher republishes on every change.

Fallback, if the daemon isn't running: use the graphifyy CLI directly:

graphifyy query "What connects the concepts of Agentic AI and Hexagonal Architecture?"

To update the graph on disk after adding new files (only needed in this fallback path — the daemon never needs this):

graphifyy update

Note: Graphifyy must be installed (uv tool install graphifyy) and the graph must have been initialized (graphifyy) in the current directory for the fallback CLI path to work.

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