Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Enforces PROTOCOLS.md "stay quiet in group chats" deterministically. Blocks outbound messages in Discord/Telegram/Slack/etc group channels when the bot was not @mentioned and recently spoke.
When the agent calls memory_search with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledge_graph backend where it will actually find the answer.
Operate Math-To-Manim with Hermes: inspect artifacts, run deterministic checks, use Codex-backed codegen, render/review Manim outputs, and avoid committing generated media.
Discover and call agents already running on a local AgentField control plane. Use when the user asks to use, call, query, run, or delegate work to an installed AgentField agent (swe-planner, pr-af, sec-af, …), to list what agents or reasoners are available, or to check on an execution. Not for building new agents — that is the agentfield skill.
EMP v4 Agent-First usage guide for Codex agents and automation. Use when creating or configuring EMP v4 projects, plugins, Module Federation host/remote/shared/manifest work, validation gates, release evidence, or when official docs point to repository skills for complete usage.
Codex-local role pack for dialectic multi-agent reviews, designed to be compatible with the local vibe skill.
Codex compatibility layer for SuperClaude /sc:* commands with vibe-adapted routing.
Codex-compatible Ralph loop runner with dual engines (compat local state loop + optional open-ralph-wiggum backend).
Compatibility router for /speckit.* workflows into /vibe-first Codex execution.
4-phase structured analysis wrapper for vibe pre-routing (compatible with claude-code-settings think-harder semantics).