Auto-triggers on 'new project [name]', 'load project [name]', 'save project', 'list projects'. Also triggers on 'create project', 'resume project', 'open project', 'show projects', or when user mentions switching between active projects.
Execute Unity Editor menu commands programmatically. Use when you need to: (1) Trigger menu commands like save, build, or refresh, (2) Automate editor actions via menu paths, (3) Run custom menu items defined in project scripts.
Execute Unity Editor menu commands programmatically. Use when you need to: (1) Trigger menu commands like save, build, or refresh, (2) Automate editor actions via menu paths, (3) Run custom menu items defined in project scripts.
Execute the implementation plan by processing tasks from tasks.md phase-by-phase, following TDD order, respecting task dependencies and parallel markers, setting up ignore files, and marking completed tasks. Use when the plan and tasks are ready and the user wants to begin coding, or when resuming implementation after a pause.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), or any work in ~/clawd workspace (never spawn agents here). Requires a bash tool that supports pty:true.
Hands-free epic execution. Runs until ALL children are CLOSED. Uses /swarm with runtime-native spawning (Codex sub-agents or Claude teams). NO human prompts, NO stopping. Triggers: "crank", "run epic", "execute epic", "run all tasks", "hands-free execution", "crank it".
Create a prompt from a short task description in a JSON file
DEFAULT PIPELINE for all tasks requiring execution. You (Claude) are the strategic orchestrator. Codex agents are your implementation army - hyper-focused coding specialists. Trigger on ANY task involving code, file modifications, codebase research, multi-step work, or implementation. This is NOT optional - Codex agents are the default for all execution work. Only skip if the user explicitly asks you to do something yourself.
Run single-file C# programs as scripts (file-based apps) for quick experimentation, prototyping, and concept testing. Use when the user wants to write and execute a small C# program without creating a full project.
Create user-defined TypeScript execution drivers for swamp — implement ExecutionDriver to control where and how model methods run. Use when users want custom execution environments (remote servers, cloud functions, custom containers). Triggers on "custom driver", "extension driver", "execution driver", "ExecutionDriver", "extensions/drivers", "create driver", "new driver type", "driver plugin", "remote execution", "driver implementation".
Use when executing a pre-written implementation plan that requires orchestrated task-by-task execution with TDD enforcement, selective code review, and smart user escalation. Use after writing-plans has produced a plan file.
Run autonomous task execution using the codex CLI. Use when the user asks to "codex exec", "run codex exec", "execute a task with codex", or "delegate to codex".
Execute an implementation plan file produced by /draft-plan or /turboplan. Runs pre-implementation prep, loads task-specific skills by matching plan content against available skill triggers, executes the plan steps, and runs /finalize. Use when the user asks to "implement plan", "implement the plan", "execute the plan", "run the plan", "implement plans/<slug>.md", "start implementing the plan", or starts a fresh session to implement a previously drafted plan.
Audit shell scripts for correctness, portability, and common pitfalls.
Optimize multi-tool workflow chains via MCP server integration for processing large datasets, files, or complex pipelines.
Async Python patterns and concurrency: async APIs, I/O-bound apps, rate limiting, context managers
Generates production-ready FastGPT workflow JSON from natural language requirements. Uses AI-powered semantic template matching from built-in workflows (document translation, sales training, resume screening, financial news). Performs three-layer validation (format, connections, logic completeness). Supports incremental modifications to add/remove/modify nodes. Activates when user asks to "create FastGPT workflow", "generate workflow JSON", "design FastGPT application", or mentions workflow automation, multi-agent systems, or FastGPT templates.
Set up and run an autonomous experiment loop for any optimization target. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".
