メニュー
Use when extracting actionable tasks from meeting notes, Slack threads, PR descriptions, specs, or other unstructured text. Converts ephemeral notes into tracked issues with context, acceptance criteria, deduplication, and learning capture.
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
Use when debugging a failing test, broken build, runtime error, or unexpected system behavior. Drives hypothesis-based investigation, root-cause fixes, verification, and reusable learning capture.
Use when a claim, plan, spec, doc, or design must be attacked against source evidence before implementation or approval. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when fixing broken behavior and the priority is reproduce, root cause, regression proof, and the smallest safe repair. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when reviewing code changes with explicit stage, target, and focus so own-code checks and others’ PR reviews stay distinct but share one contract. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when the deliverable is docs or reference material and every claim must stay tied to observed behavior or cited source evidence. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when adding or changing product behavior that must ship with explicit purpose, scenarios, and verification. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
| name | task-to-issues |
| description | Use when extracting actionable tasks from meeting notes, Slack threads, PR descriptions, specs, or other unstructured text. Converts ephemeral notes into tracked issues with context, acceptance criteria, deduplication, and learning capture. |
Use this skill when:
Do not use for a single obvious task or text with no concrete action items.
An issue without context is a to-do that will be ignored. Every extracted task must include what to do, why it matters, and how to verify it.
Title: <Imperative verb + object>
Context:
<1-2 sentences from the source material.>
Acceptance Criteria:
- [ ] <Observable done condition.>
Priority: <P0 | P1 | P2>
Assignee: <name | unknown>
Source: <link or note reference>
Use canonical/learning-template.md after completion when extraction reveals a reusable classification rule, template, trap, or workflow pattern.
Store raw findings in specs/memory/sessions/learning-YYYY-MM-DD-<slug>.md. Promote durable facts only through memory-promotion.
issue-triage — classify incoming issues after creation.diagnose — investigate confirmed bugs.memory-promotion — promote reusable learnings after approval.