ワンクリックで
plan
Scope, architect, and plan new tasks
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。
メニュー
Scope, architect, and plan new tasks
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
| name | plan |
| description | Scope, architect, and plan new tasks |
This workflow guides the agent through scoping, architecting, and planning a new feature or project. It results in a robust, peer-reviewed implementation plan and a comprehensive task list.
When the user asks to plan a new feature, project, or gives a high-level request, or explicitly uses /plan.
Before writing the plan, you MUST read the following to inform your architecture:
.agent/rules/*.md)..agent/skills/*.md.docs/solutions/ for compounded learnings to avoid repeating past mistakes.Draft an initial Implementation Plan based on the gathered context. Follow our architectural standards and compounded learnings.
Do NOT present the first draft to the user immediately.
review-plan skill (.agent/skills/review-plan/SKILL.md).review-plan skill.After the 3rd iteration, finalize the output. You MUST generate:
task.md file containing every required step to complete the project, broken down into granular, actionable tasks. Ensure no parts of the project are missing.Present a summary of the plan and the tasks to the user, and ask for their approval.
Structured brainstorming for exploring new features or solving complex problems
Multi-angle code review before merging
Summarize the day's work and put it in context
Wrap up work — atomic commits and push to origin
Full end-to-end (E2E) testing skill utilizing the browser. Make sure to use this skill whenever the user asks to "test the app", "run end to end tests", "verify the UI", "check if the app works", or wants you to use the browser to interact with and test the application flow. This skill orchestrates creating a test plan, getting user approval, navigating the application using the browser, independently fixing obstacles, and generating a progressive test report.
Analyzes the current project repository and workflows to provide a high-level status report. Use this skill when the user asks for a status update, wants to know "what's next", asks where development left off, or needs a summary of recent work to regain context. Do NOT use this skill if the user is asking you to actually implement the next feature, commit code, or search the codebase for specific files.