Skills for your AI
Use when Codex should act as the Accounts Payable Agent specialist from Agency Agents. Autonomous payment processing specialist that executes vendor payments, contractor invoices, and recurring bills across any payment rail — crypto, fiat, stablecoins. Integra
Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architec
Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with mu
Designs production-ready multi-agent team configurations from business process discovery, covering team architecture, per-agent specs, YAML config files, and pilot validation. Use when a user wants to automate a business process with a multi-agent team, needs
Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs mu
Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple appro
Use when Codex should act as the Agentic Identity & Trust Architect specialist from Agency Agents. Designs identity, authentication, and trust verification systems for autonomous AI agents operating in multi-agent environments. Ensures agents can prove who the
Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents.
Validates episode payloads, routes them through a configured sequence of specialized agents, and returns a consolidated JSON draft. Use when an episode payload needs validation, multi-agent dispatch, consolidated JSON output, or duplicate-run checking.
Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.
Extracts, creates, modifies, and compares Excalidraw diagrams by delegating all file reads and writes to subagents so verbose JSON never enters the main context. Use when the user asks to explain, summarize, add to, change, create, or compare .excalidraw or .e
Run parallel feature work safely with Git worktrees. Standardizes branch isolation, port allocation, environment sync, and cleanup so each worktree behaves like an independent local app. Optimized for multi-agent workflows where each agent or terminal session
Use when Codex should act as the Identity Graph Operator specialist from Agency Agents. Operates a shared identity graph that multiple AI agents resolve against. Ensures every agent in a multi-agent system gets the same canonical answer for "who is this entity
Merge the winning agent's branch into base, archive losers, and clean up worktrees. Use when the user runs /hub:merge or asks to land the winning AgentHub result and tidy the session.
Designs coordination strategies for multi-agent systems, covering workflow analysis, inter-agent communication, dependency and execution control, fault tolerance, and performance monitoring. Use when mapping agent dependencies, specifying message channels, pla
Coordinates multi-agent workflows by detecting intent, validating payloads, dispatching agents in sequence, and returning consistent JSON. Use when a request must be checked for required fields, routed through a configured agent sequence, or answered with clar
Provides PufferLib reinforcement learning engineering guidance to train agents, build custom environments, and optimize multi-agent or distributed training. Use when the user wants PPO training, PufferEnv development, vectorization, policies, integrations, or
Launch N parallel subagents in isolated git worktrees to compete on the session task. Use when the user runs /hub:spawn or asks to start the competing agents for an initialized AgentHub session.
Breaks large independent data processing tasks into batches, designs and deploys parallel sub-agent swarms, then aggregates, validates, and retries results. Use when processing thousands of documents, analyzing large datasets, or running bulk content generatio
Builds and maintains a local-first SwarmVault knowledge vault from books, notes, code, and recurring sources, covering init, ingest, compile, query, and automation. Use when the user wants to start a vault, add or compile sources into wiki pages, query vault c
Decomposes complex goals into work breakdown structures with PERT effort estimates, dependency graphs, parallelism maps, risk registers and validation checkpoints. Use when planning migrations, launches, multi-agent builds or any goal that needs an actionable
Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipe
Drain acc's deliberation queue — open/waiting brain_frames checkpointed by headless runs — via acc_act(runtime="continue").
Route a goal through acc's scored-memory loop via acc_act(runtime="solve"); deliberate any returned brain_frame and submit via continue.
