Skip to content

stribus/pygerengastos / .agents/skills/reversa-docs-mapper

reversa-docs-mapper

Verified

Mapeador do Time Reversa Docs. Produz as páginas de estrutura espacial do mini-site: arquitetura 3D (Code City via Three.js), module map 2D (force-directed via D3), e topologia side-by-side (legado vs moderno vs híbrido). Ative com /reversa-docs-mapper, reversa-docs-mapper, regenerar arquitetura, refazer mapa de módulos, code city do projeto.

FileKindSize
SKILL.mdskill md8.8 KB
references/extraction-policy.mdmarkdown2.0 KB

references/extraction-policy.md

View on GitHub
# Política de extração de dados (Mapper)

Define quando invocar scripts de extração vs reusar cache em `.reversa/documentation/assets/data/`.

## Cache hit (reutilizar)

Use o JSON existente quando **todas** as condições forem verdadeiras:

1. O arquivo existe em `.reversa/documentation/assets/data/<nome>.json`.
2. `mtime` do JSON é maior que o `mtime` máximo entre todos os arquivos fonte relevantes:
   - Para `modules.json`: maior `mtime` dentro do código fonte (excluindo `.reversa/`, `_reversa_sdd/`, `node_modules/`, `.git/`).
   - Para `deps.json`: maior `mtime` do código fonte E do `modules.json`.
3. O `schemaVersion` do JSON é compatível com a versão atual (1).

## Cache miss (regenerar)

Em qualquer outro caso, invoque o script Python correspondente:

```bash
python templates/documentation/scripts/extract_modules.py \
    --root . \
    --out .reversa/documentation/assets/data/modules.json

python templates/documentation/scripts/extract_deps.py \
    --modules .reversa/documentation/assets/data/modules.json \
    --out .reversa/documentation/assets/data/deps.json
```

## Python indisponível

Faça extração inline na engine de IA:

1. Use Glob para listar arquivos por extensão (`*.py`, `*.js`, `*.ts`, `*.go`, `*.java`).
2. Use Read para contar linhas não-vazias de cada arquivo.
3. Monte estrutura idêntica ao schema `modules.json` (ver `specs/reversa-docs/design.md`).
4. Para `deps.json`, na falta de parser AST, comece com `nodes` populado e `edges: []`. Marque em `.config.json.pagesPlanned` que dependencies não foram extraídas.

## Forçar regeneração

Se o usuário passar `--force-extract` ao `/reversa-docs-mapper`, ignore o cache e regenere. Backup do JSON anterior em `.backup-<timestamp>/assets/data/`.

## Quando o Analyst invoca isolado

Se o `Analyst` rodar antes do Mapper ou em modo isolado e não encontrar `modules.json`/`deps.json`, ele deve invocar os **mesmos scripts** seguindo esta mesma política. O resultado é compartilhado: Mapper subsequente vai usar o cache.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall