会話文脈からタスクを追加する。GitHub Issue / Project draft item / repo Milestone を自動判定し、`gh tasks add` を呼び出す。
Use when spawning a Claude Code, Codex, Gemini, Aider, or other CLI task agent whose work needs parent Eliza runtime context.
Performs metacognitive task analysis and skill selection. Use when determining task complexity, selecting appropriate skills, or estimating work scale.
Programmatic interaction with the agent-taskboard task API over HTTP - create, move, triage, reissue, and reorder tasks when clicking through the board UI would be too slow.
Use when delegating any implementation work to a subagent. Enforces spec traceability, TDD, and engineering standards.
When the user wants to optimize task assignments, match workers to jobs, or solve assignment problems.
Autonomously drive one task from open or checked to ready by looping through task_check as the only readiness gate, reviewer repair proposals, verifier-approved intent-safe edits,…
Execute development tasks from manifest, run parallel agents, verify builds, manage task pipeline. Use when user wants to run tasks, check task status, execute dev loop, or work…
Windows Task Scheduler, schtasks, polling automation. Use when user mentions 'Task Scheduler', 'schtasks', 'polling'.
Set up task-based multi-agent systems with shared task files. Use when setting up parallel agent execution, designing worktree isolation patterns, or implementing task file…
Break complex features into implementable tasks with estimates, dependencies, and risk assessment
Rewrite a task request into the canonical XML brief — objective, inputs, invariants, success_criteria, boundaries, autonomy, verification, communication, output_format — so the…
Generate perfect delegation briefings for AI agents or junior team members. Creates complete task specifications including dependency graphs, artifact maps, acceptance tests, risk…
Writes a single, repo-accurate task card in `agents/tasks.md` (or queues one in `agents/tasksbacklog.md`) that is executable by the Builder/QA cycles without interpretation.
Check one task before implementation. Use when the user asks if a task is ready to build or still valid.
Perform the terminal task lifecycle transition for a finished task: verify the spec done-conditions, set TASK_STATE.md to its final closed state, and move the task folder from…
Use when finishing a task — moves the v3.0.0 task folder to completed/, updates project_state.md, suggests next task.
Focuses on a specific target object to signal task completion. Use when you have produced the required final object (like a grown banana) and need to formally complete the…
Evidence-based completion claims. Use before claiming work is complete, fixed, or passing - requires running verification commands and confirming output before any success claims.
Use when orchestrating multi-step workflows with Claude Code's native Task system (TaskCreate, TaskUpdate, TaskGet, TaskList) - lifecycle management, parallel execution, crash…
Decompose a project plan into numbered POML task files for systematic AI-assisted execution
dart-query task operations - create_task, get_task, update_task, delete_task, add_task_comment with relationship management and incremental updates.
Décomposition automatique de tâches complexes en sous-tâches pour distribution aux sous-agents. Se déclenche avec "décomposer tâche", "task decomposition", "découper en s — from…
Convert technical plans into actionable development tasks with dependency graphs, effort estimates, and parallelization opportunities.
Task delegation patterns for multi-agent systems - hierarchical, parallel, and reactive delegation.
Final delivery phase of the taskmaster pipeline — commits changes and opens a pull request by delegating to the commit and pr-create skills, and refuses to proceed if the…
Send a task to another Dev Crew agent through their webhook door. Use when handing work from the PM to the developer or qa.
Distribute work across multiple agents using queue-based load balancing. Use for parallel execution, work distribution, and team coordination.
Expert in load balancing and dynamic task allocation for multi-agent systems. Specializes in optimal routing based on agent capability, availability, and cost (Token Economics).
Marca una feature de docs/features/ como terminada: actualiza sus checkboxes, la mueve a docs/done/, agrega/actualiza su fila en docs/logros.md y agrega una entrada en…
Turns a request source — a chat thread, a page, a spoken agreement — into a task record's context table.
Verify and enrich task descriptions to ensure each is independently executable with sufficient context.
Execute a POML task file with proper context loading, ADR awareness, proactive checkpointing, and rigor-level decision tree — the load-bearing task-execution protocol for every…
Task execution workflow and quality pipeline for Dart task automation. Dart任務執行工作流與品質管道。 Use when: execute dart task, run quality pipeline, implement task, code review workflow,…
Experience summaries for OpenClaw tasks, including common installation problems, troubleshooting steps, and best practices for packages, configurations, and tools.
Trích xuất tự động các nhiệm vụ, yêu cầu, phân công từ văn bản hành chính. Dùng khi người dùng nói "tạo task từ văn bản này", "có việc gì cần làm sau cuộc họp", "phân công từ biên…
Per-task self-reflection workflow triggered by user thumbs-up/down on a completed Kookr task. Reads a feedback bundle, walks the project Persistence Mechanism Picker, and proposes…
Master dart-query filtering - list_tasks filters, search_tasks queries, detail levels, pagination, query composition patterns.
Use when migrating existing single-file tasks to folder-based structure - preserves content, creates organized folders, backs up originals
Maintains a repo-local task forest or task DAG for the current workspace. Use when the user asks to initialize, update, close a session, summarize evolving project tasks, decide…
На основе проанализированных ответов стейкхолдеров формирует короткий ёмкий промпт для навыка business-analyst. Работает с любым уровнем полноты данных.
Use when a framework command needs to read the hierarchy metadata of a task — parses the YAML frontmatter block at the top of task.md and returns structured data (id, kind,…
Execute multi-stage verification pipelines (linting, type checking, test suites, schema validation) and emit structured diagnostics for agent self-repair before declaring…
Visualize the task graph from the task graph as a formatted table or DOT graph. Filter by plan, open-only tasks, or export for Graphviz rendering.
Identify current session's task list and generate commands to start a new Claude session sharing the same tasks.
Reads and displays task execution history from crew-history.json with filtering by type, agent, cost, and configurable limits.
Use at the beginning of a new task. Ensures you fully understand the requirements, boundaries, and acceptance criteria before writing code.
Protocolo de Inteligência Pré-Tarefa — ativa TODOS os agentes relevantes do ecossistema ANTES de executar qualquer tarefa solicitada pelo usuário.
AI reasoning skill for detecting user intents from natural language, mapping to MCP tools, handling multi-step workflows, and generating friendly confirmations for Todo task…
Interrogatório implacável para planos e designs. Estressa planos antes de implementar. Baseado em grill-me/grilling de Matt Pocock.
Use at the START of handling ANY user prompt that contains a task or assignment (including tasks added mid-turn), and whenever starting/finishing work on something.
Open every task by writing a kickoff brief — the task restated exactly as understood, the concrete work that will follow, and the explicit list of skills to load before the first…
Manage canonical task state through the task-ledger MCP server. Use when creating, reading, updating, or transitioning tasks, adding notes or artifact links, or querying task…
Task lifecycle state machine — states, transitions, and task tree model. Use when you need to understand task states, dispatch subtasks, or review completions.
List tasks by directory with progress and visual indicators
Do the next unblocked task from tasks/. Exactly one slice, then stop. Use when the user says "do the next task"; /tasks repeats it to drain the queue.
Generate config + adapter for the generic long-task progress loop (scaffold task_loop_scaffold.py / task_loop_poll.py / task_loop_start.sh from templates/).
Verify the current task and output a completion marker. Use this to check if a task is complete and signal the stop hook to allow session exit.
Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.
Task Master CLI(tm) 기반 프로젝트 작업 관리. "다음 작업", "작업 목록", "tm", "task", "작업 상태" 요청 시 활성화됩니다.