结构化深度讨论 Skill,用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难,或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我在纠结"时,必须使用本 skill。当用户提供了一段描述(可能附带截图)并期望深入分析 而非直接给答案时,也应触发本…

MITAuto-check passedDevelopment

Install Deep Discuss

skills CLI
$ npx skills add zhu1090093659/spec_driven_develop --skill deep-discuss -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zhu1090093659/spec_driven_develop deep-discuss --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zhu1090093659/spec_driven_develop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/spec-driven-develop/skills/deep-discuss .claude/skills/deep-discuss && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deep-discuss
GitHub stars
987
Token cost
~418 tokens
SKILL.md length
77 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

结构化深度讨论 Skill,用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难,或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我在纠结"时,必须使用本 skill。当用户提供了一段描述(可能附带截图)并期望深入分析 而非直接给答案时,也应触发本…

  • Works in 7 steps: :接收信息 → :问题审查(质量门控) → :深度分析 → …
  • Tasks that involve Spec-driven development
  • SKILL.md covers 通用规则, Phase 1:接收信息, Phase 2:问题审查(质量门控) and Phase 3:深度分析, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Deep Discuss is an agent skill from zhu1090093659/spec_driven_develop. 结构化深度讨论 Skill,用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难,或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我在纠结"时,必须使用本 skill。当用户提供了一段描述(可能附带截图)并期望深入分析 而非直接给答案时,也应触发本 skill。即使用户只是抛出一个现象描述没有明确提问,也要使用本 skill 来引导结构化思考。不要在简单的事实查询("X是什么")或明确的执行指令("帮我写个脚本")上触发。

Its SKILL.md is about 420 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Spec-driven development and Task breakdown. It works with GitHub. The repository describes itself as: Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude… The licence is MIT.

When your agent uses it

  • Tasks that involve Spec-driven development
  • Tasks that involve Task breakdown

Example prompts

  • “我遇到一个问题”
  • “你觉得怎么样”
  • “)或明确的执行指令(”
  • “/deep-discuss”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. :接收信息
  2. :问题审查(质量门控)
  3. :深度分析
  4. :方案设计
  5. :方案自检
  6. :最终确认
  7. :执行(可选)

What it can do on your machine

Read from SKILL.md and the folder at commit 14f8c0f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deep Discuss loads about 418 tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 77 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~418

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zhu1090093659/spec_driven_develop at commit 14f8c0f, republished under its MIT licence (© zhu1090093659). 77 words, ~418 tokens.

Download SKILL.mdSave it as .claude/skills/deep-discuss/SKILL.md (or your agent's skills folder).
name
deep-discuss
description
结构化深度讨论 Skill,用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难,或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我在纠结"时,必须使用本 skill。当用户提供了一段描述(可能附带截图)并期望深入分析 而非直接给答案时,也应触发本 skill。即使用户只是抛出一个现象描述没有明确提问,也要使用本 skill 来引导结构化思考。不要在简单的事实查询("X是什么")或明确的执行指令("帮我写个脚本")上触发。
version
1.0.0

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):

## Phase 2:问题审查
### 问题成立性
[判断 + 理由]
### 信息充足度
[已有信息 / 缺失信息 / 对分析的影响]
### 潜在隐藏问题
[发现 / 或"暂未发现"]

Phase 3:深度分析

信息确认足够后展开分析:全面(考虑多种可能性)、有深度(追到 root cause)、有层次(分维度而非线性罗列)、诚实(标注置信度)。总结核心发现后等待用户反馈:补充信息 → 回 Phase 2;认可 → 进 Phase 4;有分歧 → 讨论并调整。

Phase 4:方案设计

  • 优先给 2-3 个可选方案(除非只有唯一合理解法)。
  • 每个方案明确:做什么、为什么、代价、适用场景;方案间有 trade-off 要明确对比。
  • 给出推荐方案及理由,最终选择权留给用户。

Phase 5:方案自检

主动自查:遗漏的场景或边界条件?前提假设是否都成立?复杂度是否被低估?有无更简单的替代?是否覆盖了 Phase 2 识别的所有问题(含隐藏问题)?发现问题当场修正。

Phase 6:最终确认

用户确认方向后做最后一轮检查:步骤完整性、意外情况预案、执行后如何验证问题真解决了、补充建议。目标是从"可以做"提升到"做得好"。

Phase 7:执行(可选)

仅在用户明确说"开始执行"等指令时进入。按确认的方案逐步执行,每个关键步骤简要汇报,遇意外暂停并回到讨论模式。

© zhu1090093659, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/spec-driven-develop/skills/deep-discuss of zhu1090093659/spec_driven_develop.

Open the folder on GitHubat commit 14f8c0f

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in zhu1090093659/spec_driven_develop, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Deep Discuss next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deep Discuss compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deep Discuss this skillzhu1090093659/spec_driven_develop987—~418Automated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Speckit Taskstoissuesforyourhealth111-pixel/Vibe-Skills3.6k—~315Automated safety check: PassApache-2.0
React Router RFC Implementerremix-run/react-router57k—~2.3kAutomated safety check: PassMIT
SddSpillwaveSolutions/sdd-skill106—~5.7kAutomated safety check: PassMIT
Speckit Taskstoissueskunstmusik/blue15418 repos~2kAutomated safety check: PassGPL-3.0

Similar skills

  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Speckit Taskstoissues

    foryourhealth111-pixel/Vibe-Skills

    Convert tasks from tasks.md into GitHub issues. An agent skill from foryourhealth111-pixel/Vibe-Skills.

    3.6k GitHub stars~315 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • React Router RFC Implementer

    remix-run/react-router

    Turns a React Router RFC discussion on GitHub into an implementation, weighing community feedback and settling open questions with you before coding.

    57k GitHub stars~2.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Sdd

    SpillwaveSolutions/sdd-skill

    This skill should be used when users want guidance on Spec-Driven Development methodology using GitHub's Spec-Kit.

    106 GitHub stars~5.7k tokensUpdated 10 mo ago
    DevelopmentAuto-check passed
  • Speckit Taskstoissues

    kunstmusik/blue

    Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

    154 GitHub starsUsed in 18 repos~2k tokens
    DevelopmentAuto-check passed
  • Oft Spec Driven Development

    itsallcode/openfasttrace

    Support spec-driven development in projects that use OpenFastTrace, a system-requirements document in doc/systemrequirements.md, an arc42-style design in doc/design.md, and per-issue task plans in…

    197 GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from zhu1090093659/spec_driven_develop

  • Review Spd

    zhu1090093659/spec_driven_develop

    Findings-first code review workflow for AI coding agents. An agent skill from zhu1090093659/spec_driven_develop.

    987 GitHub stars~1.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Spec Driven Develop

    zhu1090093659/spec_driven_develop

    Automates pre-development workflow for large-scale complex tasks.

    987 GitHub stars~5.1k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Categories

Questions about Deep Discuss

What does Deep Discuss do?

结构化深度讨论 Skill,用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难,或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我在纠结"时,必须使用本 skill。当用户提供了一段描述(可能附带截图)并期望深入分析 而非直接给答案时,也应触发本…. Deep Discuss is an agent skill from zhu1090093659/spec_driven_develop.

When should I use Deep Discuss?

Deep Discuss fits situations like: tasks that involve Spec-driven development; tasks that involve Task breakdown.

How do I install Deep Discuss in Claude Code?

Run `npx skills add zhu1090093659/spec_driven_develop --skill deep-discuss -a claude-code`. Or copy the skill folder (plugins/spec-driven-develop/skills/deep-discuss in zhu1090093659/spec_driven_develop) into .claude/skills/deep-discuss in your project. Claude Code loads it when a task matches its description.

How do I install Deep Discuss in Codex?

Run `npx skills add zhu1090093659/spec_driven_develop --skill deep-discuss -a codex`. Or copy the skill folder (plugins/spec-driven-develop/skills/deep-discuss in zhu1090093659/spec_driven_develop) into .agents/skills/deep-discuss in your project. Codex loads it when a task matches its description.

Can I use Deep Discuss in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zhu1090093659/spec_driven_develop --skill deep-discuss -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-discuss, .gemini/skills/deep-discuss, .github/skills/deep-discuss and .opencode/skills/deep-discuss in your project.

What does Deep Discuss need to run?

SKILL.md names no scripts, command-line tools or credentials: Deep Discuss is instructions for the agent only.

Does Deep Discuss access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deep Discuss safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deep Discuss use?

Deep Discuss is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deep Discuss use?

About 418 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deep Discuss?

Skills that share tags, products or a category with Deep Discuss: CCPM Project Management (automazeio/ccpm, 8.4k stars), Speckit Taskstoissues (foryourhealth111-pixel/Vibe-Skills, 3.6k stars), React Router RFC Implementer (remix-run/react-router, 57k stars) and Sdd (SpillwaveSolutions/sdd-skill, 106 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deep Discuss?

zhu1090093659 (a GitHub user) maintains it in zhu1090093659/spec_driven_develop, which has 987 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on July 26, 2026.

Source: zhu1090093659/spec_driven_develop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.