菜单
Create a concise Design Concept artifact after questions and codebase research are available. Use for CRISPY/QRSPI Design phase, architecture alignment, feature design discussion, or turning current-state research into a small human-reviewable proposed shape before detailed planning.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Document codebase as-is via parallel sub-agents. Use when researching how code works, mapping architecture, or answering questions about existing systems. Auto-detects thoughts/ directory — if present, integrates historical context and syncs; if absent, skips those steps.
Create the Questions artifact before codebase research, design, planning, or implementation. Use for feature tickets, architecture changes, unclear code work, CRISPY/QRSPI Questions phase, or when the agent needs to define code-answerable unknowns and human questions before researching or planning.
Create an interface-first Structure Outline before detailed planning or implementation. Use for CRISPY/QRSPI Structure Outline phase, vertical planning, method signatures, type contracts, API/component boundaries, or converting an accepted design concept into end-to-end slices with verification checkpoints.
Create comprehensive handoff documents for transferring work to another agent session. Use when the user requests to create a handoff, end a session, or document work-in-progress for future continuation.
Create detailed implementation plans through interactive research and iteration. Use when starting a new feature or ticket that needs a comprehensive technical plan. Saves plans to the repo-appropriate plans location and emits Personal Knowledge events when applicable.
個人腦力激盪教練。用結構化技巧逼出你自己的想法，而非替你產生點子。 僅在使用者明確說出「腦力激盪」或「brainstorm」時觸發，其他模糊說法（幫我想想、 想不出辦法、有什麼可能）不觸發。 角色：Claude 是 coach，用 probing question 引導，不是 idea generator。
| name | design-concept |
| description | Create a concise Design Concept artifact after questions and codebase research are available. Use for CRISPY/QRSPI Design phase, architecture alignment, feature design discussion, or turning current-state research into a small human-reviewable proposed shape before detailed planning. |
| allowed-tools | Read, Write, Edit, Bash |
Create a small design proposal for human/agent architecture alignment. This is not a tactical implementation plan.
Read the task, Questions artifact, human answers, and research document if
provided. If current code behavior is still unclear, run research-codebase
with question-only prompts before designing.
Aim for about 100-200 lines maximum.
Path:
thoughts/ exists: thoughts/shared/qds/YYYY-MM-DD-description-design.mdqds/YYYY-MM-DD-description-design.mdRules:
Template:
# Design Concept: [Task]
## Goal
## Current State
- `path:line` - [fact]
## Desired State
## Proposed Shape
## Patterns to Follow
## Patterns to Avoid
## Risks / Tradeoffs
## Open Alignment Points
If the design direction is uncertain, stop for human adjustment. If aligned, recommend:
Next: /structure-outline <design-concept-path>