Communitygithub.com

orch-refine-code

Orquestra uma refatoração que preserva comportamento — confirma que os testes estão verdes, reestrutura sem alterar comportamento, mantém testes verdes, revisa e faz commit com gate. Use quando a estrutura deve melhorar, mas o comportamento não deve mudar.

O que é orch-refine-code?

Esta skill orquestra um pipeline de refatoração comportamentalmente neutra, garantindo que o código seja reestruturado sem alterar sua funcionalidade. Ela é ideal para situações em que se deseja melhorar a estrutura do código — extraindo módulos, removendo duplicação, eliminando código morto, reduzindo aninhamento ou renomeando para maior clareza — sem qualquer modificação no comportamento observável. A skill depende de uma engine compartilhada (`orch-pipeline`) e de agentes auxiliares como `refactor-cleaner`, que executam ferramentas como knip, depcheck e ts-prune para varrer código morto e dependências não utilizadas. O fluxo de trabalho é rigoroso: primeiro confirma que os testes existentes estão verdes, depois planeja a reestruturação, executa mudanças em pequenos passos com validação contínua, e finalmente passa por dois gates de aprovação — um para o plano de reestruturação e outro para o commit final. O commit é feito com a mensagem `refactor:`, e o diff final deve ser completamente neutro em comportamento. A skill é adequada para projetos TypeScript/JavaScript e pode ser usada em qualquer plataforma que suporte execução de agentes de IA, como Claude Code, Cursor ou Codex, desde que o repositório esteja configurado com um pipeline de CI com testes.

Funciona com✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/everything-claude-code/tree/main/skills/orch-refine-code
Ver original→Navegar por todas as habilidades

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentação

O que orch-refine-code faz?

Ator · ação · alvo: orch · refine · código. Wrapper simples sobre a engine compartilhada em orch-pipeline.

Quando usar

  • Mesmo comportamento, estrutura melhor: extrair módulos, remover duplicação, eliminar código morto, reduzir aninhamento, renomear para clareza.
  • Distinguir de skills irmãs: se o comportamento deve mudar de alguma forma, esta é a skill errada (orch-change-feature / orch-fix-defect).

Configurações de operação

  • Tamanho mínimo padrão: padrão — reestruturações envolvem múltiplos arquivos.
  • Máscara de fase: 0 → 2 (planejar a reestruturação) → 4 (manter verde) → 5 → 6. Nenhum novo teste de comportamento é escrito — o conjunto existente é a rede de segurança.
  • Primeiro movimento (fase 4): confirmar que os testes relevantes existem e estão verdes antes de tocar no código; se a cobertura for fina, adicionar testes de caracterização primeiro. Em seguida, reestruturar em pequenos passos, reexecutando os testes após cada um.

Como funciona

  1. Executar a engine orch-pipeline com as configurações acima.
  2. Para varreduras de código morto/duplicação, delegar ao agente refactor-cleaner (ele executa knip / depcheck / ts-prune e remove de forma segura).
  3. Parar no Gate 1 (plano de reestruturação) e no Gate 2 (pré-commit).
  4. Fazer commit como refactor: — o diff deve ser neutro em comportamento.

Exemplo

orch-refine-code: extrair o cliente HTTP NWS do poller.py
→ confirmar testes verdes → planejar extração  [GATE 1: aprovar]
→ mover em pequenos passos, testes verdes durante todo o processo → revisão de código
→ commit refactor:  [GATE 2: confirmar]

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

affaan-m/everything-claude-code

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

affaan-m/gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

affaan-m/motion-ui

Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.

affaan-m/project-guidelines-example

Example project-specific skill template based on a real production application.

affaan-m/pubmed-database

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring.

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

Habilidades Relacionadas

steipete/video-frames

Extract frames or short clips from videos using ffmpeg.

community

steipete/summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

community

openclaw/openclaw

Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

community

obra/superpowers

Obra superpowers agent skills.

community

affaan-m/ECC

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...

community

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

community