maestro-init
Initialize project with auto state detection — creates .workflow/ directory, project.md, state.json, config.json, and specs/
Initialize project with auto state detection — creates .workflow/ directory, project.md, state.json, config.json, and specs/
Wave-based parallel task execution via CSV wave pipeline. Reads plan.json to build CSV with pre-computed waves, executes tasks in parallel per wave with cross-wave context propagation. Core execution engine replacing maestro-execute command.
Memory consolidation — 4-phase reflective pass: Orient → Gather → Consolidate → Prune. Scans session transcripts and daily logs for new signals, merges/deduplicates topic files, keeps MEMORY.md under 200 lines. Run after intensive sessions or when memories feel stale.
Guidelines for building RoboCorp RPA automation with Python, emphasizing functional programming, Pydantic validation, and async operations.
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), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Requires a bash tool that supports pty:true.
Record, register, and invoke iPhoneClaw action scripts to reduce VLM tokens and make automations repeatable. Use when you want the model/agent to call `run_script(name=..., vars=...)`, when updating `action_scripts/registry.json`, when exporting scripts from `runs/*/events.jsonl`, or when triggering scripts remotely via `python -m iphoneclaw ctl run-script` while the worker is paused.
Create and validate JSON automation configs for the After Effects automation pipeline
Create ExtendScript/JSX files that integrate with the Python-to-AE file-based command bridge
YouTube 영상에서 쇼츠 클립 3개를 자동 제작합니다. yt-dlp, whisper, ffmpeg 파이프라인을 사용합니다. "쇼츠 만들어줘", "영상 클립 추출해줘" 요청 시 사용합니다.
Write and execute Python scripts using the IDA Domain API for reverse engineering. Analyze binaries, extract functions, strings, cross-references, decompile code, work with IDA Pro databases (.i64/.idb). Use when user wants to analyze binaries, reverse engineer executables, or automate IDA Pro tasks.
Boss dispatches tasks — auto-create .tasks/ files and record in dev-plan
Create a new Agenvoy script tool (JavaScript or Python) stored at ~/.config/agenvoy/script_tools/. Use when asked to create, add, or generate a script tool. A script tool is a local executable invoked by the agent via stdin/stdout JSON.
Capture a session's repeatable process into a reusable SKILL.md file following the agentskills.io standard. Use when the user says "skillify this", "turn this into a skill", "capture this as a skill", "make this repeatable", "save this workflow", or "create a skill from this session". Works at end of any workflow worth repeating.
Capture a session's repeatable process into a reusable SKILL.md file following the agentskills.io standard. Use when the user says "skillify this", "turn this into a skill", "capture this as a skill", "make this repeatable", "save this workflow", or "create a skill from this session". Works at end of any workflow worth repeating.
Structured dev workflows via /brainstorm, /write-plan, /execute-plan. Use when breaking down complex projects into systematic steps.
Prompt engineering for production LLMs — structured outputs, RAG, tool workflows, and safety. Use when designing or debugging prompts for LLM APIs.
Use when a task needs capabilities BEYOND basic tools (Read/Grep/Glob/Bash) - semantic search, AI analysis, research, image generation, etc.
Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".
Automate repetitive tasks and workflows using scripting, file watchers, scheduled jobs, CI triggers, and API polling to eliminate manual toil.
Используй только внутри активного Codex Project Autopilot-проекта для automation-задач по его плану; не включай для обычных скриптов вне автопилота.
Fullstack development toolkit with project scaffolding for Next.js/FastAPI/MERN/Django stacks and code quality analysis. Use when scaffolding new projects, analyzing codebase quality, or implementing fullstack architecture patterns.