agentleFS
Sign inStart free
synpulse8-opensourcesynpulse8-opensource/pulse8-ai-cortex-knowledge-vault/.cursor/skills/cortex-graph-search/SKILL.md

cortex-graph-search

Skill15 starsChanged 5 months agoApache-2.0View on GitHub

Cortex knowledge graph and QMD search — NetworkX graph, edge types, vault_context, semantic/keyword/hybrid search. Use for graph stats, links, or search behavior.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Debounce: After vault_write, QmdDebounce schedules index refresh (cortex/search/debounce.py).

    line 32
  2. Very specific:

    Run search with query

    line 37

≈ “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

Cortex graph and search

Knowledge graph

  • Storage: cortex/graph/store.py — NetworkX DiGraph, persisted to {vault}/.cortex/graph.json.
  • Models: cortex/vault/models.py — NodeType, EdgeType, GraphNode, GraphEdge.
  • Rebuild: cortex/graph/builder.py scans vault markdown and wikilinks.

Node types

note, tag, agent, session, daily, feedback (from path prefix or frontmatter type).

Edge types

links_to, authored_by, contradicts, derived_from, supersedes, memory_of, tagged_with.

API surface

  • REST: POST/GET/DELETE /api/v1/links, GET /api/v1/graph/stats
  • MCP: vault_link, vault_context (expands neighbors from search hits)

QMD search

  • Module: cortex/search/qmd.py — wraps QMD CLI for keyword, semantic, and hybrid modes.
  • Debounce: After vault_write, QmdDebounce schedules index refresh (cortex/search/debounce.py).
  • Modes: keyword, semantic, hybrid (default hybrid in many call sites).

vault_context flow

  1. Run search with query
  2. Take top notes
  3. Expand graph neighbors up to max_depth
  4. Return combined context for agents

VaultWatcher sync

cortex/vault/watcher.py updates graph on file changes so disk edits stay consistent without full rebuild.

Debugging

  • Empty search: check QMD index / vault path / CORTEX_VAULT_PATH
  • Missing edges: run graph rebuild or trigger watcher; verify wikilink targets exist under allowed folders
  • Stats: GET /api/v1/graph/stats

Related skills

  • Vault paths: cortex-vault
  • MCP tools: cortex-mcp

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