メニュー
Pick up a task from the backlog and implement it. Reads the spec if one exists, starts the task, does the work, and marks it done. Use when the user wants to work on a specific task or the next available task.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Prepare a session handoff — summarize progress, annotate tasks with current status, and identify what's ready for the next session. Use at the end of a work session or when the user says they're done for now.
Break down a goal into actionable tasks with dependencies, priorities, and optional specs. Use when the user wants to plan work, decompose a feature, or create a task breakdown.
Review and improve the backlog — identify vague tasks, missing priorities, broken dependencies, tasks needing specs, and stale items. Use when the user wants to groom, refine, clean up, or improve their task backlog.
Write a detailed spec document for a task before implementation begins. Use when the user wants to define requirements, acceptance criteria, or technical design for a task.
Daily standup summary — what was completed recently, what's in progress, and what's blocked. Use when the user asks for a standup, status update, or summary of recent work.
Show the current task backlog — pending, active, blocked, and overdue tasks. Use when the user asks about tasks, status, what needs to be done, or what's in progress.
| name | implement |
| description | Pick up a task from the backlog and implement it. Reads the spec if one exists, starts the task, does the work, and marks it done. Use when the user wants to work on a specific task or the next available task. |
Pick up a task and implement it. If an argument is provided, use it as the task ID. Otherwise, pick the highest-urgency unblocked task.
Find the task — if "$ARGUMENTS" is provided, ALWAYS resolve it with task_info first to confirm the task exists and get its current state (status, project, deps, attached doc). Otherwise, call task_list with filter status:pending and pick the highest-urgency task that is NOT blocked (+BLOCKED). Use the UUID from this lookup for every subsequent task_start/task_done/task_annotate call — never substitute a UUID from memory or a previous unrelated context.
Read the spec — call task_doc_read to check if the task has an attached spec. If it does, read it carefully — it defines what to build and how to verify.
Start the task — call task_start to mark it as actively being worked on.
Do the work — implement what the task and spec describe. Write code, create files, run tests. Use the codebase tools (Read, Edit, Write, Bash, Grep, Glob) as needed.
Verify — check the acceptance criteria from the spec. Run relevant tests. Make sure the implementation is complete.
Complete the task — call task_done to mark it as completed. Add an annotation with task_annotate summarizing what was done if the changes aren't obvious.
Check what's next — call task_list with filter status:pending to see if completing this task unblocked anything. Mention what's ready to pick up next.
