Browse reusable Agent Skills, each with a clear purpose and practical guidance.
How GAIA itself works — its agents, memory, skills, integrations, and workspace. Read this when the user asks how you work, what you can do, how to configure you, or when you are unsure about your own mechanics.
Use when wiring the canonical cortex inbox+outbox polling loop into Claude Code's /loop. This is the orchestration spine — every empirica claude polls Cortex on a fast adaptive cadence (30s base, 5m max) for proposals addressed to itself + status changes on its own outgoing proposals. Self-throttles when an empirica transaction is open (the AI is already busy; no need to interrupt). The canonical loop catalog (empirica/core/cockpit/canonical_loops.py) auto-installs this when the TUI cockpit toggles L on an instance that has no loops registered. This skill is the body the AI runs each fire.
Use when sending a message to a PEER AI in the mesh — discussion, FYI, question, request to do work, or completion-ack for a request a peer made of YOU. Pairs with /cortex-mailbox-poll (the receive side). Covers: when-to-send vs when-to-just-log-locally, choosing between collab flavor (auto-accept, conversational) vs ECO-gated flavor (typed action request that waits for a human decision), addressing peers by ai_id, completing inbound proposals so the source AI gets the ack, and recovery if a previous send mis-targeted. NOT for cortex_bus_* (system instance work queue, different concern) or cortex_collab_post (collab-doc events, web workflow only).
Dispatch subagents with inherited epistemic context from Cortex. Use when spawning Agent tool calls for tasks that would benefit from inherited findings, dead-ends, and anti-patterns. Triggers on 'dispatch agent', 'spawn agent with context', 'epistemic agent', or before any Agent tool call for non-trivial tasks.
Use when the user says '/ewm-interview', 'run EWM interview', 'create workflow protocol', 'set up my workflow', 'interview me for EWM', or wants to create a personalized AI collaboration protocol. This skill interviews users to discover their goals, domains, tools, preferences, and trust boundaries, then generates a workflow-protocol.yaml.
Use when scheduling cron-mode loops with Claude Code's /loop, when registering periodic background work, when the user says 'cron loop', 'periodic loop', 'register a cron', 'schedule recurring work', or when configuring a loop that needs to be visible in `empirica status`. This skill provides the prompt template that wires CC's /loop into Empirica's loop registry — register at start, check pause flag each fire, heartbeat at end. Without this wiring, a /loop cron is invisible to the cockpit and uncontrollable from any other terminal.
Sample skill that echoes a greeting via a configured provider. Use when demonstrating required env var gating in Claworc.
Use when scheduling the canonical biweekly services-audit cron loop for Empirica's AI service scanner (Phase 3). The auditor body is `empirica services-audit` — captures a fresh scan, diffs against the previous, and emits a notification when novel running services appear. This skill provides the prompt template that wires the body into Claude Code's `/loop` cron mode + Empirica's loop registry. Recommended cadence: `0 6 1,15 * *` (1st and 15th of each month at 06:00 UTC — biweekly).
Sonnet 모델 세션에 Fable 5의 운영 구조(outcome-first 커뮤니케이션·검증 규율·도구 병렬화·최종메시지 완결성·가독성 우선 토큰 절약)를 입히는 세션 모드 — 현재 세션에 직접 적용한다(서브에이전트 위임은 itsvff 에이전트 사용). 코드뿐 아니라 글쓰기·리서치·문서 작업에도 적용. 트리거 — "Value-for-Fable", "VFF", "패블 모드", "가성비 패블", "sonnet을 fable처럼". 해제 — "VFF 해제/그만/꺼", "패블 모드 해제/꺼", "stop VFF".
Always and Automatically improve skills after each use by capturing learnings and anti-patterns