🧠
AI EngineeringShell

Deep Discuss

by zhu1090093659

Deep Discuss is an AI Engineering skill for Claude Code, published by zhu1090093659 in spec_driven_develop.

969 stars99 forkson zhu1090093659/spec_driven_developAdded 2026/08/21Repository updated 2026/07/26
ai-agentai-assisted-developmentai-coding-assistantclaude-codecodexcursordev-workflowdeveloper-toolsengineering-cyberneticsgithub-issuesllmmarkdownproject-planningprompt-engineeringskillssoftware-architecturesoftware-engineeringspec-driven-developmentstructured-thinkingtask-decomposition
Install in seconds
Install Deep Discuss
Copy Deep Discuss into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/zhu1090093659/spec_driven_develop/tree/main/plugins/spec-driven-develop/skills/deep-discuss ~/.claude/skills/deep-discuss

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/zhu1090093659/spec_driven_develop.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
plugins/spec-driven-develop/skills/deep-discuss/SKILL.md in zhu1090093659/spec_driven_develop
Installs to
~/.claude/skills/deep-discuss
Collection
One of 3 skills cataloged from this repository
Category
AI Engineering2451 skills

What Deep Discuss does

Deep Discuss guides multi-round analysis of problems, faults, and decision tradeoffs before giving answers. Use it when the user wants structured thinking, root-cause analysis, or help choosing a path.

Deep Discuss is cataloged under AI Engineering on DirSkills. Deep Discuss comes from a repository tagged ai-agent, ai-assisted-development, ai-coding-assistant, claude-code and codex.

Documentation

README

Deep Discuss — 结构化深度讨论

你正在执行 Deep Discuss 工作流:不急于给答案,先把问题想透。用户描述的"问题"和真正的问题之间常有鸿沟——这个流程用分阶段的纪律保证讨论的质量和深度。

通用规则

  • 标注阶段:每次回复开头标注当前阶段(如 Phase 2 → 问题审查;转换时 Phase 2 done → Phase 3:深度分析),回复末尾简要说明下一步。
  • 不要跳阶段:至少过一遍 Phase 1-4;Phase 5/6 可按问题复杂度合并,但不能完全跳过。用户中途提供新信息时,评估是否回到更早阶段。
  • 信息不足即停:Phase 2 发现信息不足时,先问再等,不要带着未验证的假设往下走。
  • 直接坦诚:用户判断有误就直说并给理由;不确定的事用置信度表述,不用模棱两可的"可能"。

Phase 1:接收信息

只接收,不分析。完整理解用户提供的全部信息(文字、截图、用户的初步判断),用自己的话复述关键点(≤3-5 句)确认理解无误。描述明显模糊时,复述后只提 1-2 个最关键的澄清问题。

Phase 2:问题审查(质量门控)

三层审查:

  1. 问题是否成立:现象是否真构成问题?用户归因是否合理?有无需验证的前提假设?
  2. 信息是否充足:缺什么关键信息(标注:必须有 / 最好有 / 锦上添花)?信息不足时明确说明"能分析到什么程度,还差什么",然后暂停等用户补充
  3. 是否有隐藏问题:用户没注意到的其他问题?表面现象之下有无更深根因?

建议输出格式(可灵活调整):

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Deep Discuss

  • What else does zhu1090093659 publish alongside Deep Discuss?

    Deep Discuss is one of 3 skills that DirSkills catalogs from zhu1090093659/spec_driven_develop, the repository it ships in. Its siblings there include Review SPD and Spec-Driven Develop. Each one is a separate skill with its own page in this directory, installs the same way Deep Discuss does, and is maintained by zhu1090093659 in that same repository. The rest of the collection is listed on the zhu1090093659/spec_driven_develop page.

  • How does Deep Discuss compare to other AI Engineering skills?

    Deep Discuss ranks #1390 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Deep Discuss against them. Open each page to compare what they document and how they install.