Loading...
Loading...
Found 19 Skills
楽勝で流す。Agent Teamsで完全自走、寝てる間にゴール。Use when user mentions '/breezing', agent teams, team execution, full auto completion, multi-agent workflow, 'チームで完走', 'チームで全部'. Do NOT load for: single tasks, reviews, setup, or /work (direct implementation).
OpenAgents desktop pane and CAD control for Codex via openagents.* tool calls.
Local proxy that lets OpenAI Codex CLI/desktop talk to MiMo, DeepSeek, and other LLMs via Responses API translation
Use when "codex", "use gpt", "gpt-5", "openai codex", "let openai", "full-auto", "autonomous code generation"
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.
Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Codex non-interactive mode with auto-continuation. Trigger phrases include autonomous, long-running task, multi-session, 自主执行, 长时任务, autonomous skill.
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.