メニュー
Use this skill to add comments or notes to an existing task. Comments help track progress, document decisions, or explain issues.
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
You MUST use this anytime you want to ask the user a question or feel like something is unclear. If you think you want to use the AskUserQuestion tool, first invoke this skill, we may have a different way of asking the user a question.
You MUST use this skill in order to create, update, edit, or build artifacts or files. Artifacts can be of any type but are typically markdown files.
Use this skill to create a new task for tracking work within the current ticket. Tasks help break down work into smaller trackable units.
Use this skill to create a new ticket in the current project. Use this to convert a brainstorm into a formal ticket for tracking development work.
Use this skill to retrieve details of a specific task by its ID. Returns the task's description, status, comments, and other metadata.
Use this to send status updates, progress notifications, or informational messages to the user without waiting for a response.
| name | potato:add-comment-to-task |
| description | Use this skill to add comments or notes to an existing task. Comments help track progress, document decisions, or explain issues. |
Document as you go, not after. Every significant action, decision, or blocker gets a comment immediately. Future sessions have no memory of your reasoning - comments are the only record.
add_comment_to_task({
taskId: "task1",
text: "Completed initial implementation, moving to tests"
})
Comments are timestamped automatically and appended to the task's comment history.
| When... | Add a comment IMMEDIATELY |
|---|---|
| You complete a significant milestone | Document what was accomplished |
| You encounter a blocker or error | Document exactly what failed and why |
| You make a non-obvious decision | Record the reasoning before you forget it |
| You're about to end a session | Leave handoff notes for the next session |
| A task fails or can't be completed | REQUIRED: Explain what went wrong |
These thoughts mean you're rationalizing:
| Excuse | Reality |
|---|---|
| "The code is self-documenting" | Code shows WHAT, not WHY. Add the comment. |
| "I'll remember this" | You won't. The next session definitely won't. |
| "It's obvious why this failed" | Nothing is obvious without documentation. Write it. |
| "I'll add comments at the end" | You'll forget details. Comment as you go. |
| "This decision doesn't need explaining" | Every non-trivial decision needs reasoning recorded. |
add_comment_to_task({
taskId: "task1",
text: "API endpoint implemented, testing locally"
})
add_comment_to_task({
taskId: "task2",
text: "Failed: TypeScript compilation error in user.types.ts - missing interface export"
})
add_comment_to_task({
taskId: "task3",
text: "Chose Redis over in-memory cache for persistence across restarts"
})
add_comment_to_task({
taskId: "task4",
text: "Paused mid-implementation. Next: wire up the event handlers in src/handlers/events.ts"
})
| Bad Comment | Good Comment |
|---|---|
| "Done" | "Implemented user validation with email regex and length check" |
| "Failed" | "Failed: API returns 403 - auth token expired during request" |
| "Made some changes" | "Refactored auth flow to use middleware pattern" |
Vague comments = no comments. Be specific about what happened and why.
Tasks without comments = lost context. Lost context = repeated mistakes and wasted investigation time.