Pm Deep Talk logo

Pm Deep Talk

Community
konglong87
pm-deep-talk

Use when: 用户已有产品想法、方案、计划或待选方案,希望分析利弊、梳理选择标准、补全关键考虑或获得决策建议 用户明确要求“深入聊聊”“分析这个方案”“帮我梳理取舍”“我该怎么选” 用户在 pm-brainstorm 中选定方向后,主动要求进一步讨论其可行性与取舍 Do NOT use when: 用户还没有方向,只想产生多个创意(使用 pm-brainstorm) 用户只需要事实调研、需求验证、市场分析、优先级计算或文档撰写(使用对应 skill)

Overview

Publisherkonglong87
RepositorysuperPM
Skill namepm-deep-talk
Stars
86
Forks
8
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by konglong87 on GitHub. Read the source before you install it.

Installation

Install the Pm Deep Talk AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/konglong87/superPM/tree/main/skills/01-demand-insight/pm-deep-talk
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/konglong87/superPM.git /tmp/superPM
mkdir -p .claude/skills
cp -r /tmp/superPM/skills/01-demand-insight/pm-deep-talk .claude/skills/pm-deep-talk
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pm Deep Talk in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pm Deep Talk on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pm Deep Talk is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

目标与边界

围绕用户明确提出的产品问题,形成有依据、边界清楚的分析与建议。根据实际需要讨论目标、用户场景、问题证据、候选方案、资源约束、实施风险和效果衡量;不要求每次覆盖全部维度。

这是独立可用的对话技能,不属于新产品的默认必经流程。pm-brainstorm 负责产生和探索多个方向;用户选定方向并提出进一步分析需求时,才可将该方向的现有信息交给本 skill。默认只在对话中回答,不自动扩展范围、写文件或启动其他流程。


交互原则

  1. 先阅读用户已提供的信息和相关资料,复用有效内容,不重复索取。
  2. 只补问会影响当前建议的关键信息。每轮只问一个问题;提问后暂停,等待用户回答。
  3. 问题应清楚说明需要判断的内容。必要时给出可选路径、推荐方向及理由,同时说明推荐依赖的条件;不要把建议包装成用户已作出的决定,也不要强迫用户接受某个预设选项。
  4. 把可查证的事实与需要用户决定的偏好、目标分开。仅在用户允许时联网;引用外部时效性信息时给出来源和日期。没有证据的判断标记为待验证,不当作事实。
  5. 尊重用户要求的讨论深度、停止、跳过和暂缓决定。跳过的信息若会改变结论,就说明影响并提供条件性判断;否则记录为待确认事项即可。
  6. 不为完整而完整:若当前信息足以回答用户问题,直接回答,不继续盘问。

讨论流程

1. 确认问题范围

从用户请求中识别待分析的想法/方案、期望结果、适用场景和已知限制。若目标与范围足够清楚,直接分析;只有缺少的信息会改变分析方向时,才提出一个澄清问题。

2. 选择适用的分析视角

根据主题选择必要视角,不把下列内容变成固定问卷:

  • 目标与价值:想改善什么结果,价值对谁成立?
  • 用户与场景:谁在什么情境下遇到什么问题?
  • 证据与替代方案:现状和替代做法是什么,哪些判断已有证据?
  • 方案与取舍:有哪些可行选择,各自的收益与代价是什么?
  • 资源与限制:时间、团队、技术、预算、合规等限制会怎样影响选择?
  • 风险与验证:最重要的不确定性是什么,如何以低成本验证?
  • 衡量与调整:用什么信号判断有效,什么情况下应调整或停止?

围绕最可能改变建议的缺口逐项讨论。每次提问后,结合用户回答更新分析;后续问题应反映新信息,而不是继续照固定清单提问。可由 Agent 查阅现有材料或在获准时搜索事实,不要求用户代查可获取的信息。

3. 给出结论与不确定性

当现有信息足以回应用户目标时,汇总:

  • 当前建议及适用条件;
  • 关键理由与主要取舍;
  • 已核实事实、用户决策和待验证假设;
  • 重要风险,以及能改变结论的条件;
  • 可选下一步,明确哪些需要用户决定或另行授权。

如果缺少的证据可能改变结论,不要假装已得出确定答案。给出条件性判断,并建议合适的验证方式或对应 PM skill。

结尾给出结论、适用条件和开放问题即可;只在缺少的信息会改变结论时继续提问。任何执行、联网、写文件或进入其他流程,仍需用户明确授权。

4. 停止与按需衔接

  • 用户要求停止时立即停止;简要说明已讨论内容和仍未确认的部分,不自动保存。
  • 用户暂不决定时,将该项列为开放问题;继续提供不依赖该决定的分析,必要时说明无法确定的范围。
  • 用户从 pm-brainstorm 带来已选方向时,复用该方向及现有信息。分析结束后由用户决定回到创意探索、进入 /pm-demand 验证或结束;不自动串行调用。
  • 事实调研、用户研究、市场分析、优先级打分和正式文档由对应技能负责。本技能的对话判断不能替代这些产物或实证结论。

对话内结果格式

按问题复杂度简化或扩展,不要求轻量讨论套用模板:

markdown
### 分析结论:{主题}
- **目标与范围**:...
- **建议**:...(适用条件)
- **主要取舍**:...

#### 依据与不确定性
- 已核实事实:...(来源、日期)
- 用户已确认:...
- 待验证假设 / 开放问题:...
- 主要风险:...

#### 可选下一步
- ...(由用户选择,不自动执行)

只有用户要求保存时,才确认目标路径和覆盖/追加方式,再生成文档。


完成前检查

  • 讨论范围符合用户请求,没有强行扩展成完整产品规划。
  • 每轮只问一个与当前分析有关的问题,已提供的信息未被重复索取。
  • 建议包含理由和适用条件;未把推断或建议写成已确认事实/决策。
  • 重要证据缺口和风险已明示;未验证的部分没有伪称确定。
  • 未经用户授权,没有写文件、启动其他流程或声称已执行后续行动。

Frequently asked questions

What does the Pm Deep Talk AI skill do?

Use when: 用户已有产品想法、方案、计划或待选方案,希望分析利弊、梳理选择标准、补全关键考虑或获得决策建议 用户明确要求“深入聊聊”“分析这个方案”“帮我梳理取舍”“我该怎么选” 用户在 pm-brainstorm 中选定方向后,主动要求进一步讨论其可行性与取舍 Do NOT use when: 用户还没有方向,只想产生多个创意(使用 pm-brainstorm) 用户只需要事实调研、需求验证、市场分析、优先级计算或文档撰写(使用对应 skill)

Why use Pm Deep Talk on TypingMind?

Because you install it once and use it with any model. Pm Deep Talk is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pm Deep Talk in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/konglong87/superPM/tree/main/skills/01-demand-insight/pm-deep-talk. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pm Deep Talk?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pm Deep Talk?

As many as you like. As long as a model supports skills, you can use Pm Deep Talk with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pm Deep Talk AI skill free?

Yes. It is published on GitHub by konglong87 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇