gaia

Use for the exact input/output schema and validation rules of agent_contract_handoff

Use when creating a new specialist agent for Gaia, or reviewing whether an existing agent follows the correct structure, tone, and component inventory

Use when producing any agent response

Use when the orchestrator must read, reconcile, route, and present an agent_contract_handoff

Use when writing, drafting, or publishing a blog article for metraton.github.io -- "escribe un post para el blog", "publica un artículo", "write a blog post", "draft an article for the blog".

Use when the user wants to capture a feature as a brief or spec before planning it -- "arma un brief para esto", "necesito un spec antes de planear", "definamos el alcance de la feature", "write a brief for this", "spec this out before we plan it".

Use when the user explicitly requests a code review of a module, branch, change, or pull request -- "revisa este código", "haz code review de esto", "review this PR", "review this branch".

Use when writing, modifying, reviewing, or refactoring code — any language or stack, application, infrastructure, or configuration. Also when asked to apply, audit, or clean up the code standards of a file or module.

Use when executing any bash command, CLI tool, or shell operation

Use when the user wants to build or extend a diagram deck of nested sections and components authored in plain YAML — an architecture map, a timeline diagram, a planner board, a process-flow diagram, a slide-style presentation, a side-by-side comparison, or a mind-map. Not for charts, plots, or numeric/data visualization — route those to the dataviz skill. Triggers — "build a diagram", "architecture diagram", "diagram deck", "timeline diagram", "flow diagram", "planner board", "comparison diagram", "add a page/section/component to the diagram", "arma un diagrama", "diagrama de arquitectura", "haz un timeline", "diagrama de flujo", "tablero de planificación".

Use when the specialist that requested a T3 operation or COMMAND_SET is resumed after the user granted it

Use when diagnosing an issue, checking system health, or validating state before deeper investigation

Use when the user asks to audit, check, or review a Gaia component (an agent or a skill) against its standard and its live implementation -- "audita este skill", "chequea este agente", "¿está bien esta skill con la implementación?", "¿cómo mejoro este agente?"

Use when the user asks to check, certify or live-test an area of Gaia in the running host -- "probemos las aprobaciones", "gaia-check", "ejecuta la prueba N", "corre el catálogo de firmas" -- in Claude Code or OpenCode

Use when the user asks to compact the current session, including “compacta”, “compactemos”, or “compact the session”

Use when building or modifying Gaia components -- agents, skills, hooks, CLI tools, or routing config

Use when planning features or decomposing work into tasks from a brief

Use when testing, validating, or publishing Gaia releases -- "install local", "pre-release", "dry-run", "release", RC, stable, plugin dry-run, "instala local", "hagamos un release", "probemos el pre-release", "publiquemos la versión estable"

Use when the user wants to verify a Gaia installation -- "probemos la instalación", "verifiquemos que Gaia funcione", "verify", "test installation", "gaia-verify"

Use when committing, squashing, merging, rebasing, or preparing changes for a pull request

Use when managing Gmail messages, labels, or email workflows via gws CLI or Gmail MCP tools

Use when the user wants to clean up, organize, or triage their Gmail inbox interactively -- "ordena el mail", "hagamos triage del inbox", "limpiemos el correo", "let's triage my inbox", "clean up my Gmail".

Use when installing or configuring the Google Workspace CLI (gws) for a Google account -- "instala gws", "configura el cli de Google Workspace", "conecta mi cuenta de Google", "set up gws", "install the Google Workspace CLI".

Use when starting an investigation, analyzing existing code or infrastructure, or building findings before proposing changes

Use when presenting a returned APPROVAL_REQUEST for informed user consent

Use when the user asks to list, inspect, approve, reject, or revoke pending approvals -- "qué aprobaciones tengo pendientes", "aprueba esto", "rechaza esa aprobación", "revoca el permiso", "show pending approvals", "approve this".

Use when writing, rewriting, cleaning up, or updating a README -- the root README of a repository, the README of a folder that holds one kind of thing (modules, migrations, components, services, scripts, environments, workloads; Gaia's own agents/, skills/ and hooks/ are one instance of that same shape), or the README shipped inside a template or scaffold handed to someone else. Triggers -- "escribe el README", "actualiza el README", "limpia el README", "el README de este repo está desactualizado", "falta el README de esta carpeta", "write the README", "the README is stale", or a drift report flagging a README as stale.

Use when the user wants something to run routinely / on a schedule rather than once now -- "tarea programada", "rutinariamente", "cada mañana", "cada N horas", "todas las noches", "schedule", "cron". Covers mounting, structuring, and running an unattended headless task that reports back, plus consuming its reports. NOT for work that runs once now in this session.

Use when classifying any operation before executing it, or deciding whether user approval is required

Use when creating a new skill, improving an existing skill, or deciding what a skill should contain and how it should be structured

Use when a T3 command was blocked or a predictable ordered T3 set must be requested before execution

Use when the deliverable explains a system, a process, an architecture, or a failure -- a bare "explain X", "how does this work", "what happened here", "qué es esto", "explicame cómo funciona", a status the reader must understand rather than execute, or the explanatory part of a README, a ticket, a deck, or a report. Loaded by the orchestrator when its answer explains, and by any specialist whose output explains.

Use when creating or drafting a ticket or issue, or standardizing ticket output for a project -- "ármame un ticket", "escribe el issue", "necesito una tarea para Jira", "create a ticket", "draft an issue".

Use when re-running a task_gates entry (or a proposed contract verification block) whose verification_type is `command` or `code`, to deterministically re-execute the declared check and compare the actual result against the gate's expected value -- not for `semantic` or `self_review` gates, which need judgment rather than re-execution.

Use when judging a task_gates entry whose verification_type is semantic or self_review -- reading the gate's evidence_shape as an explicit rubric, assessing the produced work against each stated criterion, and emitting a justified pass/fail verdict. Loaded by the verifier role for judgment-based gates.

Use when about to declare done on any output with a visual surface -- an HTML page, a rendered UI, a diagram, a slide, a screenshot-able view -- to confirm by looking at the rendered result instead of asserting it. Also use when asked to screenshot or visually check a page or a local file.