Communitygithub.com

external-context

Invoca agentes especialistas en documentos de forma paralela para búsquedas web externas y consulta de documentación.

¿Qué es external-context?

Esta habilidad permite descomponer una consulta en 2 a 5 facetas independientes y lanzar agentes Claude especialistas en documentos de forma paralela para buscar documentación externa, referencias y contexto en la web. Cada agente utiliza herramientas de búsqueda web (WebSearch) y recuperación de páginas (WebFetch) para obtener documentación oficial y ejemplos, citando todas las fuentes con sus URLs. Es especialmente útil para desarrolladores que necesitan respuestas rápidas y fundamentadas sobre mejores prácticas, comparaciones de herramientas (como Prisma vs Drizzle ORM) o patrones técnicos avanzados (como los React Server Components). Soporta la invocación explícita mediante el comando `/oh-my-claudecode:external-context` y no tiene activación por palabra clave mágica. El resultado se sintetiza en un formato estructurado con hallazgos clave, resultados detallados por faceta y una lista de fuentes con enlaces.

Compatible con✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/external-context
Ver original→Ver todas las habilidades

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentación

Habilidad de Contexto Externo

Obtén documentación externa, referencias y contexto para una consulta. Descompone la consulta en 2 a 5 facetas y lanza agentes Claude especialistas en documentos en paralelo.

Uso

/oh-my-claudecode:external-context <tema o pregunta>

Ejemplos

/oh-my-claudecode:external-context ¿Cuáles son las mejores prácticas para la rotación de tokens JWT en Node.js?
/oh-my-claudecode:external-context Compara Prisma vs Drizzle ORM para PostgreSQL
/oh-my-claudecode:external-context Últimos patrones y convenciones de React Server Components

Protocolo

Paso 1: Descomposición en Facetas

Dada una consulta, descomponer en 2 a 5 facetas de búsqueda independientes:

## Descomposición de Búsqueda

**Consulta:** <consulta original>

### Faceta 1: <nombre-faceta>
- **Enfoque de búsqueda:** Qué buscar
- **Fuentes:** Documentación oficial, GitHub, blogs, etc.

### Faceta 2: <nombre-faceta>
...

Paso 2: Invocación Paralela de Agentes

Lanzar facetas independientes en paralelo mediante la herramienta Task:

Task(subagent_type="oh-my-claudecode:document-specialist", model="sonnet", prompt="Buscar: <descripción de faceta 1>. Usa WebSearch y WebFetch para encontrar documentación oficial y ejemplos. Cita todas las fuentes con URLs.")

Task(subagent_type="oh-my-claudecode:document-specialist", model="sonnet", prompt="Buscar: <descripción de faceta 2>. Usa WebSearch y WebFetch para encontrar documentación oficial y ejemplos. Cita todas las fuentes con URLs.")

Máximo 5 agentes especialistas en documentos en paralelo.

Paso 3: Formato de Salida Sintetizada

Presentar los resultados sintetizados en el siguiente formato:

## Contexto Externo: <consulta>

### Hallazgos Clave
1. **<hallazgo>** - Fuente: [título](url)
2. **<hallazgo>** - Fuente: [título](url)

### Resultados Detallados

#### Faceta 1: <nombre>
<hallazgos agregados con citas>

#### Faceta 2: <nombre>
<hallazgos agregados con citas>

### Fuentes
- [Fuente 1](url)
- [Fuente 2](url)

Configuración

  • Máximo 5 agentes especialistas en documentos en paralelo.
  • Sin activación por palabra clave mágica: solo invocación explícita.

Individual skills in this repo

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

agent-doc-discipline

Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already says. Mandatory at drydock seed generation and the launch C5 sediment pass; opt-in for any other agent-facing doc edit. The companion of minimal-code-discipline: that one disciplines code, this one disciplines papers.

ai-slop-cleaner

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

ask

Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly

ask-navigator

Shipyard

autopilot

Full autonomous execution from idea to working code

autoresearch

Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior

cancel

Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state

configure-notifications

Configure notification integrations (Telegram, Discord, Slack) via natural language

debug

Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction

deepinit

Deep codebase initialization with hierarchical AGENTS.md documentation

deep-interview

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

drydock

Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift.

execute

Carry an approved task through to working, verified code

graph

Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery

harbor

Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence. Agent-autonomous for facts and for actions covered by standing authorization; signed for every new judgment. Never merges.

hud

Configure HUD display options (layout, presets, display elements)

launch

Shipyard

loft

Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks. Use when a design question stalls in words, when a navigator map carries a loft ticket, or when a spec discussion reaches

minimal-code-discipline

YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away

omc-doctor

Diagnose and fix oh-my-claudecode installation issues

Skills relacionados

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