agentleFS
belentani7belentani7/claude-skills-pack/skills/graphify/SKILL.md

graphify

Skill0 starsChanged 3 months agoMITView on GitHub

Convierte cualquier codebase en un grafo de conocimiento queryable usando AST parsing. Elimina context rot, reduce tokens 70%, permite preguntas sobre la arquitectura del código. Ejecuta /graphify en cualquier proyecto.

  • Installs packages

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

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 113 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Elimina context rot: No necesitas re-leer archivos en cada sesión

    line 12

“Common” is measured: kept by at least 6 in 10 of the 113 edited versions of this file we could read. “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 - Knowledge Graph for Codebases

Qué hace

Toma tu codebase completo (código, docs, configs, SQL schemas) y lo convierte en un grafo de conocimiento consultable. Cada función, clase, import, y relación se extrae como nodo y arista del grafo.

Por qué es revolucionario

  • Elimina context rot: No necesitas re-leer archivos en cada sesión
  • Reduce tokens 70%: Solo Consultas lo relevante, no archivos enteros
  • Preguntas arquitectónicas: "¿Cómo se conecta el módulo A con B?"
  • Dependencies visuales: Ve qué archivos dependen de qué

Setup automático

# Instalar graphify
pip install graphify

# En cualquier proyecto:
graphify init

# Esto crea:
# .graphify/
# ├── graph.json      (el grafo de conocimiento)
# ├── metadata.json   (stats del proyecto)
# └── config.json     (configuración)

Uso en MiMoCode

Generar grafo de un proyecto

import tree_sitter
from graphify import GraphBuilder

builder = GraphBuilder()
builder.scan_directory("./src")
graph = builder.build()

# Guardar grafo
graph.save(".graphify/graph.json")

# Consultar
results = graph.query("¿Qué funciones usan la base de datos?")
for node in results:
    print(f"{node.file}:{node.line} - {node.name}")

Preguntas que puedes hacer

/graphify "¿Qué archivos dependen de database.py?"
/graphify "¿Qué rutas API existen?"
/graphify "¿Qué clases heredan de BaseModel?"
/graphify "¿Qué funciones son públicas vs privadas?"
/graphify "¿Cuál es el flujo de una petición HTTP?"

Integración con workflows

# Auto-graphify on save
def on_file_save(filepath):
    if filepath.endswith('.py'):
        builder.update_file(filepath)
        graph.save(".graphify/graph.json")

# Query from any skill
def get_relevant_context(query, graph, max_tokens=2000):
    nodes = graph.query(query)
    return format_nodes_for_context(nodes, max_tokens)

Beneficios medidos

  • Tokens ahorrados: 60-90% en sesiones de coding
  • Velocidad: Respuestas 3x más rápidas (sin leer archivos innecesarios)
  • Precisión: Elimina hallucinations sobre el codebase
  • Memoria: Persiste entre sesiones (no se olvida del código)

Archivos generados

.graphify/
├── graph.json          # El grafo completo
├── metadata.json       # Stats: files, functions, classes
├── config.json         # Configuración
├── queries/            # Consultas cacheadas
└── snapshots/          # Versiones del grafo

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.