agentleFS
Sign inStart free
uniskelauniskela/adhd-hub/.cursor/skills/graphify/SKILL.md

graphify

Skill8 starsChanged 37 days agoMITView on GitHub

Use the graphify knowledge graph to explore architecture, dependencies, and impact before reading or grepping the codebase; keep the graph current with graphify update . after code changes. Use when exploring this repo, answering architecture questions, tracing dependencies, assessing blast radius, or after editing code while graphify-out/ exists.

115 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use remotion-maps, remotion-saas and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • OpenAISkill

    remotion-maps

    Remotion Map animation knowledge

    Also in 4 projects that use this

  • OpenAISkill

    remotion-saas

    Build an app with Remotion

    Also in 4 projects that use this

  • royaluniondesign-sysSkill

    deployment-patterns

    Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.

    Also in 4 projects that use this

  • mstuder-slalomSkill

    django-verification

    Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

    Also in 3 projects that use this

  • ttmouseSkill

    prompt-master

    提示词主控 - 智能选择合适的领域skill并生成提示词，支持自动领域分类和调度

    Also in 4 projects that use this

  • seikaikyoSkill

    doubt-driven-development

    對非平凡決策啟動新鮮 context 對抗審查（找碴不背書），在修正還便宜的時候抓出錯誤方向。適用：高風險改動（production、資安敏感邏輯、不可逆操作）、不熟的程式碼、要宣稱「這樣是安全的 / 可行的」之前。機械性操作與一行修改不適用。

    Also in 6 projects that use this

The file

Create a free account to mount
Files
SKILL.md

Graphify

Local knowledge graph for this repo lives in graphify-out/.

CLI (Windows): %USERPROFILE%\.local\bin\graphify.exe — ensure that dir is on PATH, or invoke it by full path.

When to use

SituationCommand
Any architecture / “how does X work?” questiongraphify query "<question>"
Dependency between two symbolsgraphify path "<A>" "<B>"
Everything related to a conceptgraphify explain "<concept>"
Blast radius of a changegraphify affected "<symbol>"
Core hubsgraphify god-nodes
After editing codegraphify update .

Before broad exploration with Read/Grep/Glob/Bash, run query / path / explain first (same rule as .cursor/rules/graphify.mdc). Pass this requirement into subagent prompts that explore code.

After modifying code files, always run:

graphify update .

AST-only refresh — no API key / LLM cost. Use --force (or GRAPHIFY_FORCE=1) if a refactor deleted a lot of code and the rebuild looks smaller than the old graph.

Workflow

  1. graphify query "..." (or path / explain) to get a scoped subgraph.
  2. Open only the files/symbols the graph points to.
  3. Edit.
  4. graphify update .
  5. Optionally graphify affected "<changed-symbol>" to check fallout.

Navigation artifacts

  • graphify-out/GRAPH_REPORT.md — communities, god nodes, broad review
  • graphify-out/wiki/index.md — if present, prefer over raw file walks
  • Default graph: graphify-out/graph.json

Do not

  • Skip graphify because the area “feels familiar”
  • Dump the whole graph.json into chat — use query/path/explain
  • Forget graphify update . after code changes (required by AGENTS.md)

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