Loading...
Loading...
Found 146 Skills
STOP — if you were dispatched as a subagent to execute a briefed task, this skill is not for you: it governs the dispatching orchestrator only, and the mode and path rules you need are already in your brief. Do the task you were briefed with instead. Use whenever the user asks to dispatch, launch, spawn, fan out, or delegate work to an agent, subagent, worker, or coding agent in a separate git worktree — phrasing like "dispatch a subagent", "launch an agent", "fan out subagents", "parallel agents", or "use a separate worktree to implement/fix/refactor/test/review X" — or whenever two or more workers must edit the same repository concurrently without colliding. Symptoms it prevents: worktrees created from the wrong base commit, workers accidentally editing the orchestrator checkout when an isolated worktree was intended (Mode D is the sanctioned single-writer exception), Edit/Write failing outside the agent CWD, colliding diffs, shared Docker/e2e infrastructure clobbered by concurrent test runs, merged worktrees left consuming disk, and force-removed worktrees losing uncommitted work.
Drive development using delegated agent workflows. Coordinates multi-agent task execution with proper supervision and result integration.
Implement tasks from docs/task/*.md. Reads the task document, follows implementation steps, and updates status in TASKS.md. Use "/implement auto {task}" to auto-chain through test → document → ship. Use "/implement -m 1 2 3" for multi-task parallel execution.
Execute an implementation plan step-by-step with completion tracking. Use when the user wants to work through a plan, implement tasks sequentially, track progress on a task list, or asks to "execute the plan" or "start implementing".
Execute a lightweight ad-hoc task (debugging, documentation, small adjustments) without the full change lifecycle. Assesses spec impact afterward.
Used when executing implementation plans containing independent tasks in the current session
Autonomous execution workflow for complex long-running tasks. This applies to scenarios where users have a complex or vague task (e.g., "Help me figure out X / Help me evaluate Y / Help me organize this pile of stuff / Help me compare N solutions / Help me run a research"), and expect the AI to decompose, execute, and verify the task on its own, only reaching out to the user at critical moments. It enables unattended autonomous execution for 1-2 hours through the process of "Task Confirmation → Task Queue → Batch Execution → Periodic Queue Verification → Triggered Reporting". It is triggered when users say phrases like "Help me figure out / Evaluate / Organize / Compare / Run a research / Run it on your own don't bother me / Long-running task / Run autonomously". **Not applicable to**: UI design (use design-exploration), to-do priority judgment (use priority-judge), article writing (use writing-assistant), backlog management (use backlog-manager), vision exploration (use vision-exploration), naming (use product-naming), implementation coding tasks with clear specs (code directly).
Compile TeamPlan for tasks with clear net parallel benefits. By default, use Codex native Multi-Agent V2 to create Luna XHigh/Max leaf Workers, and switch to App Thread when independent worktree, sidebar visibility, cross-task recovery, or durable supervision is required. Applicable for tasks with two or more independent deliverables, independent validation, or when users explicitly request model routing, background Workers, Agents Team, Grok/Gemini Workers. Simple Q&A, status queries, small single-file modifications, strongly sequential tasks, and irreversible operations will not trigger automatically.
Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key). Use when delegating a self-contained coding task to Codex from another agent — parallel implementation work, a second opinion, or an independent verification pass.
Writes precise, autonomous-execution-ready tasks using the SMART+ framework (Specific, Measurable, Actionable, Referenced, Testable, +Context). Transforms vague task descriptions into detailed specifications with file paths, verification commands, and clear success criteria. Use when writing tasks for any agent, creating todos, planning features, decomposing work, or when tasks lack precision. Triggers on "write task", "create todo", "break down feature", "make task precise", "task is vague", or when task descriptions are missing file paths, verification steps, or clear success criteria. Works with todo.md, task lists, project planning documents, and agent instructions.
Unified task execution protocol for Codex-only work. Supports Single Task, Epic Task, and Batch Task while preserving CSV truth-source, validation gates, context recovery, and Debug-First failure exposure. WHEN TO USE: user asks to "track tasks", "create todo list", "make a plan", "track progress", "long task", "big project", "build from scratch", "autonomous session", "跟踪任务", "自主执行", "长时任务", "从零开始", "任务管理", "做个计划", "大工程", or when a task clearly requires 3+ ordered steps that produce file changes. DO NOT USE: single-step fixes, pure Q&A, code review, explaining code, search/research tasks, tasks with fewer than 3 steps, or tasks that do not produce file changes.
Break down complex tasks into three layers: Dao, Shu, Fa, integrating Confucianism, Taoism, Mind Learning, and Art of War to first set the situation, main path, and first-move advantage