deep-discuss

deep-discuss is a skill for Claude Code, Codex from zhu1090093659/deepseek-pp. It costs 181 tokens per session (1,804 once invoked), scanned A, original, Apache-2.0.

A structured discussion guide for exploring a problem over several rounds of questions and solution design.

In plain words
What is it for?
It is for analysing faults, technical questions, difficult choices, and situations where the user wants to think through a problem rather than receive an immediate answer.
Why use it?
It helps uncover missing information, test assumptions, and separate the visible symptom from the underlying problem before choosing a solution.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for analysing faults, technical questions, difficult choices, and situations where the user wants to think through a problem rather than receive an immediate answer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zhu1090093659/deepseek-pp/deep-discuss
About the project

DeepSeek++ is a browser extension that turns the DeepSeek website into an AI workspace with tools, memory, skills, media analysis, and automation. DeepSeek users employ it to manage projects, control browser pages, search the web, reuse context, and export conversations, while the catalogue entries add skills and instructions for that workspace.

zhu1090093659/deepseek-pp · 1,830 stars · on GitHub · chromewebstore.google.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add zhu1090093659/deepseek-pp --skill deep-discuss
Clone the repo
git clone --depth 1 https://github.com/zhu1090093659/deepseek-pp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deep-discuss

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhu1090093659/deepseek-pp/deep-discuss/github.svg)](https://agentmods.dev/skills/zhu1090093659/deepseek-pp/deep-discuss)
Your own site
<a href="https://agentmods.dev/skills/zhu1090093659/deepseek-pp/deep-discuss"><img src="https://agentmods.dev/badge/skills/zhu1090093659/deepseek-pp/deep-discuss/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deep-discuss

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhu1090093659/deepseek-pp/deep-discuss"><img src="https://agentmods.dev/badge/skills/zhu1090093659/deepseek-pp/deep-discuss.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 181 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,804 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00181 $0.01804
Opus 5 $0.00090 $0.00902
Sonnet 5 $0.00036 $0.00361
Haiku 4.5 $0.00018 $0.00180

Measured 11d ago against content hash 0f965c9fe962, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

deep-discuss scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

core/skill/spec-driven-develop-official/deep-discuss/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Discuss — 结构化深度讨论

你正在执行 Deep Discuss 工作流——一个引导你与用户进行深度、结构化问题讨论的 Skill。核心理念是:不急于给答案,先把问题想透。

为什么需要这个流程

大多数时候,用户描述的"问题"和真正的问题之间存在鸿沟——信息可能不完整,表述可能有偏差,甚至问题本身可能不成立。如果你跳过思考直接给方案,很容易答非所问或遗漏关键点。这个 Skill 的价值在于:通过有纪律的分阶段思考,确保讨论的质量和深度。

讨论流程(7 个阶段)

整个讨论像一次联合诊断,你在每个阶段都应该明确标注当前所处的阶段,让用户随时知道"我们在哪"。


Phase 1:接收信息

用户提供问题描述,可能包含:

  • 文字描述(现象、背景、上下文)
  • 图片/截图(错误信息、界面状态、日志片段等)
  • 用户自己的初步判断或猜测

你在此阶段的任务:只接收,不急于分析。先完整理解用户提供的全部信息,用自己的话简要复述关键点(不超过 3-5 句),确认理解无误。

如果用户的描述明显模糊或信息严重不足,可以在复述后提出 1-2 个最关键的澄清问题(不要一次抛出一堆问题,会打断用户的思路)。


Phase 2:问题审查(Critical Thinking)

这是最核心的阶段。你需要对用户提供的信息做三层审查:

第一层:问题是否成立?

  • 用户描述的现象是否真的构成一个"问题"?有没有可能这是正常行为?
  • 用户的归因(如果有)是否合理?因果关系是否可靠?
  • 是否存在前提假设需要验证?

第二层:信息是否充足?

  • 现有信息是否足够支撑分析?缺什么关键信息?
  • 哪些信息需要用户补充才能继续?(标注优先级:必须有 / 最好有 / 锦上添花)
  • 如果信息不足,明确告诉用户"我目前能分析到什么程度,还差什么"

第三层:是否有隐藏问题?

  • 基于已有信息,是否能发现用户没注意到的其他问题?
  • 这些隐藏问题与用户提出的问题是否有关联?
  • 有没有更深层的根因(root cause)藏在表面现象之下?

输出格式建议(不需要死板遵循,根据实际情况灵活调整):

## Phase 2:问题审查

### 问题成立性
[你的判断 + 理由]

### 信息充足度
[已有信息概述 / 缺失信息 / 对分析的影响]

### 潜在隐藏问题
[发现的其他问题 / 或"暂未发现"]

如果在这个阶段发现需要补充信息,暂停后续流程,先等用户回复。不要带着不确定的假设往下走。


Phase 3:深度分析

在 Phase 2 的基础上(信息已确认足够),展开全面、有深度的分析。

这个阶段的核心要求:

  • 全面:考虑多种可能性,不要只盯着最显眼的那个
  • 有深度:追根溯源,不停留在表面现象,尽量抵达 root cause
  • 有层次:从不同角度或维度进行分析,而非线性罗列
  • 诚实:对不确定的部分明确标注置信度,不要装作什么都知道

分析完成后,用简洁的语言总结核心发现,等待用户反馈。用户可能会:

  • 补充新信息 → 回到 Phase 2 重新审查
  • 认可分析 → 进入 Phase 4
  • 提出不同看法 → 讨论分歧,调整分析

Phase 4:方案设计

基于 Phase 2-3 的分析结论,开始设计解决方案。

方案设计原则:

  • 优先给出 2-3 个可选方案,而非直接拍一个(除非问题简单到只有一个合理解法)
  • 每个方案明确:做什么、为什么这样做、代价是什么、适用场景
  • 如果方案之间有 trade-off,明确对比
  • 给出你的推荐方案及推荐理由,但把最终选择权留给用户

Phase 5:方案自检(First Review)

在提出方案后,你主动对自己的方案做第一轮 review:

检查清单:

  • 是否有遗漏的场景或边界条件?
  • 方案的前提假设是否都成立?
  • 实施复杂度是否被低估了?
  • 有没有更简单的替代方案被忽略了?
  • 方案是否真的解决了 Phase 2 中识别出的所有问题(包括隐藏问题)?

如果发现问题,直接在这个阶段修正,不需要等用户指出。


Phase 6:最终确认(Final Review)

用户确认方案方向后,做最后一轮 review:

  • 方案的完整性:所有步骤是否都覆盖到了?
  • 风险预案:如果方案执行中出现意外,怎么办?
  • 验证方式:方案执行后,怎么确认问题真的解决了?
  • 还有没有什么补充建议?

这一轮的目的是从"可以做"提升到"做得好"。

Read the full file on GitHub · 173 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 173 lines · 181 tokens per session scan A 0f965c9fe962

Subscribe to this mod's changes

deep-discuss is a skill published in the GitHub repository zhu1090093659/deepseek-pp (1,830 stars, last pushed 28d ago), licensed Apache-2.0. It adds 181 tokens to every session and 1,804 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

seekbridge-browser

Operate the user's real Chrome through SeekBridge with task-owned tabs, semantic element refs, verified actions, and safe recovery. Use for navigating websites with DeepSeek-powered agents, working in signed-in web apps, collecting page information, filling ordinary forms, testing web interfaces, taking screenshots…

Chang-Hai/seekbridge · 73 tokens

weekly-digests

Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…

thedotmack/claude-mem · 93 tokens

cloud-sync

Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.

thedotmack/claude-mem · 64 tokens

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

image-generator

Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.

lessweb/deepcode-cli · 62 tokens

video-generator

A video-generation skill that turns text, images, video, or audio references into a video with dialogue and ambient sound.

lessweb/deepcode-cli · 72 tokens