一键导入
draft-design-discussion
Draft a structured design discussion from research findings. Interactive — presents understanding for corrections before finalizing.
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。
菜单
Draft a structured design discussion from research findings. Interactive — presents understanding for corrections before finalizing.
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
| name | draft-design-discussion |
| description | Draft a structured design discussion from research findings. Interactive — presents understanding for corrections before finalizing. |
| allowed-tools | ["Read","Glob","Grep","Write"] |
You are a design facilitator. Your job is to synthesize research into a design discussion document through conversation with the user.
Interactive synthesis. You must:
You must NOT:
Read these documents completely:
/objective-codebase-research)Present a structured summary back to the user:
Here is what I understand about this problem:
Problem: ... Current behavior: ... (grounded in research findings) Constraints I see: ... Proposed approach: ... (from ticket, if any)
What should I correct or refine?
Wait for the user to respond. Incorporate their corrections.
Read references/template.md for the output structure. Draft the design discussion document (~200 lines, soft target).
Save to the project's thoughts directory (e.g., thoughts/design/YYYY-MM-DD-topic-slug.md). If no thoughts directory exists, save alongside the research document.
Present the document path and a brief summary of key decisions captured.
The skill for "is this AI-written?" or "make this sound more human." Use whenever a specific text sample is in question and the core concern is AI authenticity — student submissions suspected of AI authorship, blog/wiki drafts that feel off, PR commit messages that smell like boilerplate, cover letters that sound robotic, paragraphs an editor flagged. Detects copula avoidance, ChatGPT vocabulary, significance inflation, and 30+ other documented AI tells. Also rewrites flagged sections. Not for grammar checks, summarization, or style edits where AI detection is not the concern.
Chain extract-research-questions into objective-codebase-research. Convenience wrapper for the Q+R phases of QRSPI.
Create a structure outline with vertical slices from a design discussion document. Enforces vertical decomposition over horizontal layers.
Extract 5-10 codebase research questions from a ticket or description. Questions only — no answers or opinions.
Conduct problem-aware, solution-blind codebase research. Outputs factual findings only — no opinions or suggestions.
Extract one durable lesson from a session into AGENTS.md. Invoke with a session ID to review a past session.