# Query

> Responde preguntas usando el conocimiento del brain con búsqueda en 3 capas, síntesis y propagación de citas; úsalo cuando el usuario pregunte, busque o necesite información del brain.

Fuente: https://skillsagentes.com/skills/garrytan/gbrain/query
Markdown: https://skillsagentes.com/skills/garrytan/gbrain/query.md

Repositorio: https://github.com/garrytan/gbrain
Autor: garrytan
Licencia: MIT
Actualizado: hace 9 días
Coste de contexto: 48 tok instalada, 1.8k tok al activarse, 2k tok con todos los archivos del bundle
Bundle: 2 archivos, 8 KB
Permisos que pide: search, query, get_page, list_pages, get_backlinks, traverse_graph, get_timeline

## Instalación

Un skill son archivos markdown: los mismos archivos valen para cualquier agente y lo único que cambia es el directorio de destino, es decir la bandera `--agent`. Añade `-g` para instalarlo en todos los proyectos de la máquina.

```bash
# Claude Code
npx -y skills add garrytan/gbrain --skill query --agent claude-code
# Cursor
npx -y skills add garrytan/gbrain --skill query --agent cursor
# Codex
npx -y skills add garrytan/gbrain --skill query --agent codex
# Gemini CLI
npx -y skills add garrytan/gbrain --skill query --agent gemini
# Windsurf
npx -y skills add garrytan/gbrain --skill query --agent windsurf
# Cline
npx -y skills add garrytan/gbrain --skill query --agent cline
```

## Qué hace

- Ejecuta búsqueda en 3 capas (keyword, semántica, estructural) sobre el brain
- Sintetiza una respuesta con citas que trazan cada afirmación a una página específica
- Marca vacíos de información en vez de alucinar hechos
- Respeta la precedencia de fuentes y señala conflictos entre citas
- Usa traversal de grafo para preguntas de relaciones (quién conoce a quién, conexiones)

## Cuándo usarla

- El usuario hace una pregunta o busca información en el brain
- Preguntas de tipo 'qué sabemos sobre', 'quién es' o 'qué pasó'
- Preguntas relacionales como 'conexiones entre A y B' o 'quién trabaja en X'
- Se necesita background o notas sobre una persona, empresa o tema

## Qué la activa

- "¿Qué sabemos sobre Jane Doe?"
- "Tell me about el trato con Acme"
- "¿Quién trabaja en Acme?"
- "Busca notas sobre el Demo Day W26"
- "¿Qué conexiones hay entre Alice y Bob?"

## Antes de instalar

- Requiere conexión MCP a un servidor gbrain (idealmente ≥0.43 para los memory verbs recall/entity/synthesize).

## Archivos

- SKILL.md — 7 KB
- routing-eval.jsonl — 535 B

## SKILL.md

Reproducido tal cual desde garrytan/gbrain bajo MIT. Esta sección es el documento original y está en inglés.

# Query Skill

Answer questions using the brain's knowledge with 3-layer search and synthesis.

> **Memory verbs (MEMORY_VERBS v1, gbrain ≥ 0.43).** When connected to a brain
> over MCP, prefer the seven frozen memory verbs for memory work — they carry
> provenance, evidence, and a server-enforced token budget:
> - **`recall(query | entity, budget_tokens)`** — the budget-packed memory read.
>   Use it instead of bare `search` for "what do we know that we SAVED about X".
> - **`entity(name)`** — a zero-LLM person/company/project card (aliases,
>   last-touched, open threads, top edges). Use it instead of `get_page` +
>   `get_backlinks` when you just need the card.
> - **`synthesize(question)`** — the explicitly-expensive cross-page answer; the
>   heavy version of `query`. Reach for it only when the answer must combine
>   evidence across pages.
> Fall back to `search`/`query`/`get_page` when the verbs aren't on the surface
> (pre-0.43 servers; `--surface full` includes the verbs alongside every other
> op). See `docs/protocol/MEMORY_VERBS_v1.md`.

## Contract

This skill guarantees:
- Every answer is grounded in brain content (no hallucination)
- Every claim has a citation tracing back to a specific page slug
- Gaps are flagged explicitly ("the brain doesn't have information on X")
- Source precedence is respected (user statements > compiled truth > timeline > external)
- Conflicting sources are noted with both citations

## Phases

1. **Decompose the question** into search strategies:
   - Keyword search for specific names, dates, terms
   - Semantic query for conceptual questions
   - Structured queries (list by type, backlinks) for relational questions
2. **Execute searches:**
   - Cheap-hybrid search gbrain for exact tokens / known names (search)
   - Full-hybrid search gbrain with multi-query expansion for concept questions (query)
   - List pages in gbrain by type or check backlinks for structural queries
3. **Read top results.** Read the top 3-5 pages from gbrain to get full context.
4. **Synthesize answer** with citations. Every claim traces back to a specific page slug.
5. **Flag gaps.** If the brain doesn't have info, say "the brain doesn't have information on X" rather than hallucinating.

## Anti-Patterns

- Answering from general knowledge when the brain has relevant content
- Hallucinating facts not in the brain
- Silently picking one source when sources conflict
- Loading full pages when search chunks are sufficient
- Ignoring source precedence (user statements are highest authority)

## Output Format

Answers should include:
- Direct response to the question
- Citations: "According to [Source: people/jane-doe, compiled truth]..."
- Gap flags: "The brain doesn't have information on X"
- Conflict notes when sources disagree

## Quality Rules

- Never hallucinate. Only answer from brain content.
- Cite sources: "According to concepts/do-things-that-dont-scale..."
- Flag stale results: if a search result shows [STALE], note that the info may be outdated
- For "who" questions, use backlinks and typed links to find connections
- For "what happened" questions, use timeline entries
- For "what do we know" questions, read compiled_truth directly

## Token-Budget Awareness

Search returns **chunks**, not full pages. Read the excerpts first before deciding
whether to load a full page.

- `gbrain search` / `gbrain query` return ranked chunks with context snippets.
  These are often enough to answer the question directly.
- Only use `gbrain get <slug>` to load the full page when a chunk confirms the
  page is relevant and you need more context (e.g., compiled truth, timeline).
- **"Tell me about X"** -- get the full page (the user wants the complete picture).
- **"Did anyone mention Y?"** -- search results are enough (the user wants a yes/no with evidence).

### Source precedence

When multiple sources provide conflicting information, follow this precedence:

1. **User's direct statements** (highest authority -- what the user told you directly)
2. **Compiled truth** (the brain's synthesized, cited understanding)
3. **Timeline entries** (raw evidence, reverse-chronological)
4. **External sources** (web search, API enrichment -- lowest authority)

When sources conflict, note the contradiction with both citations. Don't silently
pick one.

## Citation in Answers

When referencing brain pages in your answer, propagate inline citations:
- Cite the page: "According to [Source: people/jane-doe, compiled truth]..."
- When brain pages have inline `[Source: ...]` citations, propagate them so
  the user can trace facts to their origin
- When you synthesize across multiple pages, cite all sources

## Graph Traversal (v0.10.1+)

For relationship questions ("who knows who at X?", "connections between A and B",
"who works at Acme?", "who attended the standup?"), use the graph layer instead
of full-text search:

- `gbrain graph-query <slug> --type <link_type> --depth N --direction in|out|both`
- Available link types: `attended`, `works_at`, `invested_in`, `founded`, `advises`, `mentions`, `source`
- `--direction in` answers "who points to X?" (e.g., who works at company X)
- `--direction out` answers "what does X point to?" (default)
- `--depth N` controls multi-hop traversal (default 5)

Examples:
- "Who works at Acme?" → `gbrain graph-query companies/acme --type works_at --direction in`
- "Who attended Demo Day W26?" → `gbrain graph-query meetings/demo-day-w26 --type attended --direction out`
- "What companies has Emily advised?" → `gbrain graph-query people/emily --type advises --direction out`
- "Who has Alice met (via meetings)?" → `gbrain graph-query people/alice --type attended --depth 2`

Combine with `gbrain query` for queries that need BOTH semantic similarity AND
graph structure. Search results are ranked with a small backlink boost so well-
connected entities surface higher.

## Search Quality Awareness

If search results seem off (wrong results, missing known pages, irrelevant hits):
- Run `gbrain doctor --json` to check index health
- Check embedding coverage -- partial embeddings degrade hybrid search
- Compare keyword search (`gbrain search`) vs hybrid search (`gbrain query`)
  for the same query to isolate whether the issue is embedding-related
- Report search quality issues in the maintain workflow (see maintain skill)

## Tools Used

- Keyword search gbrain (search)
- Hybrid search gbrain (query)
- Read a page from gbrain (get_page)
- List pages in gbrain with filters (list_pages)
- Check backlinks in gbrain (get_backlinks)
- Traverse the link graph in gbrain (traverse_graph)
- View timeline entries in gbrain (get_timeline)

## Dónde encaja

- Categoría: [Investigación](https://skillsagentes.com/categorias/investigacion.md) — Investigación estructurada, búsqueda de fuentes y síntesis.
- Creador: [garrytan](https://skillsagentes.com/creators/garrytan.md) — 134 skills en el directorio
- [Todas las skills](https://skillsagentes.com/skills.md)
- [Ranking de instalaciones](https://skillsagentes.com/ranking.md)

## Otras skills del mismo repositorio

- [Setup](https://skillsagentes.com/skills/garrytan/gbrain/setup.md): Configura GBrain con auto-aprovisionamiento de Supabase o PGLite, inyección en AGENTS.md y primera importación.
- [Maintain](https://skillsagentes.com/skills/garrytan/gbrain/maintain.md): Chequeos de salud del brain: aplicación de back-links, auditoría de citas, validación de filing, detección de info obsoleta, páginas huérfanas y benchmarks.
- [Schema Unify](https://skillsagentes.com/skills/garrytan/gbrain/schema-unify.md): Migra un brain de gbrain-base a la taxonomía de 14 tipos canónicos de gbrain-base-v2 usando gbrain onboard --check y el handler Minion unify-types.
- [Retrieval Reflex](https://skillsagentes.com/skills/garrytan/gbrain/retrieval-reflex.md): Cuándo y qué recuperar: abre la página del brain de una entidad relevante antes de responder desde memoria.
- [Minion Orchestrator](https://skillsagentes.com/skills/garrytan/gbrain/minion-orchestrator.md): Skill unificado de Minions para jobs deterministas de shell y orquestación de subagentes LLM: cola durable, observable y controlable, más la doctrina de ejecución durable para operaciones largas.

## Skills relacionadas

- [Idea Lineage](https://skillsagentes.com/skills/garrytan/gbrain/idea-lineage.md): Traza la evolución de una idea en el brain: primera mención, mejor articulación, conceptos relacionados, reversales, contradicciones, ramas abandonadas y versión vigente.
- [Reports](https://skillsagentes.com/skills/garrytan/gbrain/reports.md): Guarda y carga reportes con timestamp y routing por keyword; incluye el Actionability Gate que revisa enlaces rotos, muertos, indirectos o faltantes antes de entregar briefings o reportes.
- [Measure Before You Fix](https://skillsagentes.com/skills/garrytan/gbrain/measure-before-you-fix.md): Antes de arreglar una alerta de lentitud, stale o timeout, mide el paso tú mismo con un cronómetro en vez de un cambio de código: triage de operaciones basado en medición previa.
- [Minion Orchestrator](https://skillsagentes.com/skills/garrytan/gbrain/minion-orchestrator.md): Skill unificado de Minions para jobs deterministas de shell y orquestación de subagentes LLM: cola durable, observable y controlable, más la doctrina de ejecución durable para operaciones largas.
- [Meeting Ingestion](https://skillsagentes.com/skills/garrytan/gbrain/meeting-ingestion.md): Ingiere transcripciones de cualquier grabadora de reuniones en páginas del brain con enriquecimiento de asistentes, propagación de entidades y fusión de timeline, verificando sustancia y secuencia.

---

Skills Agentes · [Índice de páginas en markdown](https://skillsagentes.com/sitemap.md) · [Inicio](https://skillsagentes.com/index.md)