convez.ai
SkillProdutividadeIntermediário
costrict-plugins-repo

Capture — Organizador de Brain Dump

costrict-plugins-repo/alirezarezvani-claude-code-skills-capture-skill

Transforma brain dump caótico em 4 seções acionáveis sem perda de informação

Ver no GitHub
InicialPluginScore · de 0 a 100

Skill que captura pensamentos, tarefas e ideias desorganizadas e as transforma em um sistema estruturado de quatro seções: Projetos & Ideias, Tarefas, Conexões e Como Posso Ajudar. Preserva zero perda de informação e faz apenas uma pergunta clarificadora se necessário antes de oferecer ações concretas.

Instalação

$npx convez-ai costrict-plugins-repo/alirezarezvani-claude-code-skills-capture-skill

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
37%
Último commit
há 2 semanas
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Organizar pensamentos soltos e ideias mistas em estrutura clara
  • Converter listas longas desordenadas em tarefas e projetos separados
  • Identificar conexões entre itens e encontrar referências no workspace
  • Preparar ações prioritárias a partir de um fluxo mental desorganizado

Veredito

Skill bem-arquitetada para quem trabalha com captura de ideias ad hoc. A estrutura de quatro seções é clara, os scripts Python (workspace_inventory, dump_classifier, complexity_estimator) são simples e stdlib-only, e o design evita fabricação de conexões. Útil para profissionais que precisam canalizar pensamentos caóticos em ação estruturada.

README

A tradução para o português deste README ainda está na fila.

capture

Brain-dump organizer. Catches an unstructured stream of mixed thoughts, tasks, and ideas and transforms it into a clean four-section actionable system with zero information loss.

What it does

When the user dumps (explicitly with phrases like "brain dump" / "let me get this out of my head", or implicitly by pasting a long unstructured block of mixed ideas), the skill:

  1. Captures everything (zero loss; trivial items go in)
  2. Asks at most ONE mid-organization clarifying question — only if a single item is genuinely ambiguous between task and project
  3. Returns four sections:
    • Projects & Ideas — clustered themes with embedded questions/decisions
    • Tasks — flat scannable action list
    • Connections — real workspace links (Glob/Grep verified — never fabricated)
    • How I Can Help — concrete offers with what + where
  4. Ends with a directive question: "Which of these should I tackle?"
  5. Waits for the user's pick before any further action.

When the dump is small (≤5 items, unrelated), the skill drops into a compressed output instead of forcing 4 sections.

Source spec

This skill is a Path-B direct conversion of megaprompts/05-capture-megaprompt.md (PR #657). The megaprompt is the canonical spec; this plugin is the working implementation. Drift between the two is a bug — re-grill with /cs:grill-with-docs if they diverge.

Plugin layout

FileRole
skills/capture/SKILL.mdThe skill itself (Claude reads this when triggered)
skills/capture/scripts/workspace_inventory.pyGlob+Grep helper for Section 3 — given a working dir + keyword list, returns a structured inventory of file matches + folder structure. Stdlib-only.
skills/capture/scripts/dump_classifier.pyRegex-classify dump lines into task / decision / question / project-component. Heuristic, not authoritative.
skills/capture/scripts/complexity_estimator.pyCount items in dump; recommend full 4-section vs compressed output format.
skills/capture/references/workspace_detection.mdContext-specific detection tactics (CLI / web / MCP / inaccessible)
skills/capture/references/voice_preservation.mdConcrete examples of corporate-speak anti-patterns
skills/capture/references/complexity_matching.mdWhen to compress vs full 4-section, with worked examples
agents/cs-capture.mdCapture-organizer persona (no-fabrication, voice-preservation enforcer)
commands/cs-capture.md/cs:capture <dump> slash command for explicit invocation

Quick start

# Run the workspace-inventory helper against this repo
python skills/capture/scripts/workspace_inventory.py --root . --keywords "skill,megaprompt,capture"

# Classify a dump file
python skills/capture/scripts/dump_classifier.py path/to/dump.txt

# Estimate output complexity
python skills/capture/scripts/complexity_estimator.py path/to/dump.txt

License

MIT.

Ver o original no GitHub

Bom para

Relacionados