agentleFS
Sign inStart free
felvieirafelvieira/claude-skills-fv/CLAUDE.md

claude-skills-fv

CLAUDE.md27 starsChanged 2 months agoApache-2.0View on GitHub

Este repositorio e um kit de skills para agentes de coding. Leia os arquivos nesta ordem: Quando instalado em .bot/ de outro repo, o agente deve ler o AGENTS.md da raiz do repo consumidor, que aponta para .bot/. This project has a graphify knowledge graph at graphify-out/ (graphifyy >= 0.9.64). Rules: - Before answering architecture or codebase questions, read graphify-out/GRAPH_REPORT.md for god nodes and community structure - If graphify-out/wiki/index.md exists, navigate it instead of reading raw files - After modifying…

The file

We split this CLAUDE.md into the rules it gives an agent

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

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before answering architecture or codebase questions, read graphify-out/GRAPH_REPORT.md for god nodes and community structure

    line 25
  2. Very specific:

    If graphify-out/wiki/index.md exists, navigate it instead of reading raw files

    line 26
  3. Very specific:

    After modifying code files in this session, run graphify update .

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

Claude Code — Dev Team Kit

Este repositorio e um kit de skills para agentes de coding. Leia os arquivos nesta ordem:

  1. GLOBAL.md — regras universais
  2. policies/ — regras compartilhadas
  3. AGENTS.md — objetivo e uso do kit
  4. README.md — documentacao completa com pipeline, skills e stack

Uso em repos consumidores

Quando instalado em .bot/ de outro repo, o agente deve ler o AGENTS.md da raiz do repo consumidor, que aponta para .bot/.

Economia de contexto

  • reutilizar docs/repo-audit/current.md antes de explorar o repo
  • abrir docs/skill-guides/ apenas sob demanda
  • consultar patterns/ai-integration/ para features de IA

graphify

This project has a graphify knowledge graph at graphify-out/ (graphifyy >= 0.9.64).

Rules:

  • Before answering architecture or codebase questions, read graphify-out/GRAPH_REPORT.md for god nodes and community structure
  • If graphify-out/wiki/index.md exists, navigate it instead of reading raw files
  • After modifying code files in this session, run graphify update . to keep the graph current
  • Para achar o caminho entre dois conceitos: graphify path "A" "B" (adicionar --undirected se nao achar) — use IDs qualificados (caminho::simbolo) quando o match for ambiguo
  • Para explicar um no e suas conexoes: graphify explain "<node-id-ou-nome>"
  • Para indice cross-project (varios repos em D:\Repos): graphify merge-graphs + graphify global add
<!-- CLAUDE-MEMORY-SETUP -->

Memoria Persistente (ai-memory)

Migrado em 2026-09-04 do vault Zettelkasten (D:\claude-memory\) para ai-memory v2.0. Captura automatica via hooks — sem save manual. Ver ~/.claude/CLAUDE.md para detalhes do servidor/binario/MCP.

Regra de 3 Camadas

  1. Primeiro: consulte graphify-out/graph.json neste repo para entender estrutura e conexoes
  2. Segundo: pergunte em linguagem natural ("onde paramos", "ja discutimos X") ou rode ai-memory search "query" --project claude-skills-fv para contexto de sessoes anteriores
  3. Terceiro: so leia arquivos de codigo brutos ao editar ou quando as camadas acima nao resolverem

Graphify

  • Graph disponivel em: graphify-out/graph.json (gerado automaticamente)
  • Para atualizar apos refatoracoes: graphify update .
  • NAO edite arquivos dentro de graphify-out/ manualmente

Historico migrado

Os 75 architecture/claude-skills-fv/decisions.md (antigo vault) e todos os logs de sessao deste projeto foram importados como paginas ai-memory sob o projeto claude-skills-fv (tag migrated). O vault antigo em D:\claude-memory\ fica congelado como arquivo morto.

<!-- /CLAUDE-MEMORY-SETUP -->

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