Loading...
Loading...
Found 376 Skills
Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
Vector-powered CLI for semantic file search with a Claude/Codex skill
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Codex-facing entry point for building with Alchemy. Routes to `alchemy-api` for API key-based access or `agentic-gateway` for gateway-based access when the user has not chosen an auth path yet.
Team worker protocol (ACK, mailbox, task lifecycle) for tmux-based OMX teams
Use when explicitly asked to run the security-reviewer subagent or when another skill requires the security-reviewer agent card.
Use to spawn isolated worker processes for autonomous issue work. Creates git worktrees, constructs worker prompts, and handles worker lifecycle.
Mine coding agent logs (Codex/Cursor/session histories and similar telemetry) to discover high-value candidate skills, then draft structured skill creation/reuse recommendations.
Cross-platform skill converter. Parse AgentOps skills into a universal bundle format, then convert to target platforms (Codex, Cursor). Triggers: convert, converter, convert skill, export skill, cross-platform.
Extract a learned skill from the current conversation