Talk Text Review logo

Talk Text Review

Community
webkubor
talk-text-review

讲稿/分享稿的文本验收——查的不是错别字,是**姿态**:这份稿子读起来是「我教你们」还是「我跟你们聊」。用心理逆反、自我暴露、认识论谦逊这几条机制,逐句找出会把听众推到对立面的表达并给出改写。触发词:讲稿验收、分享稿检查、这么讲会不会得罪人、居高临下、技术分享、演讲稿、内部分享、会不会太说教、口吻检查。适用于对内技术分享、公众号、文档开篇、PR 描述等任何「同级或高手在场」的表达场景。

Overview

Publisherwebkubor
Repositorywriting-standard-skills
Skill nametalk-text-review
Stars
6
Forks
1
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 webkubor on GitHub. Read the source before you install it.

Installation

Install the Talk Text Review 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/webkubor/writing-standard-skills/tree/main/skills/talk-text-review
  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/webkubor/writing-standard-skills.git /tmp/writing-standard-skills
mkdir -p .claude/skills
cp -r /tmp/writing-standard-skills/skills/talk-text-review .claude/skills/talk-text-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Talk Text Review 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 Talk Text Review 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 Talk Text Review 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.

讲稿文本验收:先验姿态,再验内容

什么时候用

在同级同事、领域高手、或比你资深的人面前讲东西之前跑一遍。内容再对,姿态错了也会招敌人——尤其讲「最佳实践」类主题时。

一句话判据:这份稿子里,听众是「需要被教育的人」还是「我想请教的人」?

核心机制(为什么姿态比内容更容易惹人)

  1. 心理逆反(reactance):人感到自主权被侵犯时会本能反驳,与内容对错无关。「你应该加 AGENTS.md」是规范性陈述,触发逆反;「我加了 AGENTS.md,然后发现……」是经验陈述——经验无法被反驳,只能被补充。这是全篇最重要的一条。
  2. 自我暴露(self-disclosure)降低威胁感:讲自己的失败会触发亲近感而非防御。翻车经历的价值远超它的信息量,因为它同时说明「我不是来立牌坊的」。
  3. 出丑效应(pratfall effect):有能力的人展示小失误,好感度上升;无能力的人这么做才下降。对在场有产出的人是正向的。
  4. 认识论谦逊 → 站位转换:说「这是我拍的,想听听你们怎么排」,把强者从审判席请到同盟席。人一旦进入「帮你想」的角色,就不会再进入「挑你错」的角色。站位是讲者分配的。
  5. 叙事传输(narrative transportation):故事比结论更容易被接受,因为听众在跟随情节时不会同时启动反驳。

分级判据

🔴 致命(必改,这几处最招敌人)

症状为什么致命改法
标题含「如何/怎样/必须/正确姿势/最佳实践」第一秒就把讲者架上讲台换成叙述性:「我做了 X,结果 Y」
结尾是「结论」「总结」你凭什么下结论换成「我还没想清楚的几个问题」
行动项主语是听众(「今天就能做的三件事」)给同级布置作业主语换成自己:「我接下来打算做的三件事」
「你的 X 可能……而不自知」字面意思是「你不知道,我知道」换成「我的 X 就是这样,我自己完全没发现」
拿自己的标准给知名项目/他人工作打分最容易被攻击的一页保留数据,前面加自我限定(见下)

🟡 重要(建议改)

  • 第二人称祈使句密度过高:「你要」「你应该」「记住」「别忘了」「一定要」
  • 规范词:应该 / 必须 / 正确的做法是 / 大家都知道 / 显然 / 其实
  • 隐含优越:「很多人不知道」「大部分项目都没做」「这是个常见误区」
  • 无出处的判断:把个人判断说成客观事实,没标记「我的判断是」

🟢 加分(有就更好)

  • 开篇 30 秒内出现一次自己的失败
  • 数据旁标注来源与局限(样本量、时间、适用范围)
  • 至少一处「这点我不确定」
  • 结尾的开放问题是真开放(你确实没答案),不是明知故问的引导题

可执行扫描

bash
F=<稿子路径>

# 🔴 第二人称祈使 + 规范词密度
grep -nE "你(的|们)?(应该|必须|要|得|需要)|记住|别忘了|一定要|正确的做法" "$F"

# 🔴 隐含优越
grep -nE "而不自知|很多人(不知道|没有)|大部分[项目人]|常见误区|显然|其实很简单" "$F"

# 🔴 布道式标题与结构
grep -nE "^#+ .*(如何|怎样|必须|正确|最佳实践|三件事|结论|总结)" "$F"

# 🟢 反向检查:有没有自我暴露(应该 ≥1 处,最好在前 30%)
grep -nE "我(踩|翻车|以为|没想到|搞错|不知道|完全没发现)|第一刀砍在自己身上" "$F"

# 🟢 反向检查:有没有认识论谦逊标记
grep -nE "我(的判断|自己拍的|不确定|还没想清楚)|想听听|可能不对|只是我的" "$F"

前三条命中越多越危险;后两条一条都没有才是最危险的信号。

改写对照(同一事实,两种姿态)

布道交流
你的站可能被默认屏蔽而不自知我的站就被默认屏蔽了,我自己完全没发现
应该给仓库加 AGENTS.md我给仓库加了 AGENTS.md,这是我的写法
今天就能做的三件事我接下来打算做的三件事 / 如果你也想自查,一条命令
结论:别让站被屏蔽我还没想清楚的:放行 AI 爬虫对商业站有没有风险
这九个维度是……这九个维度和权重都是我自己拍的,想听听你们觉得该怎么排
常见误区是……我一开始也是这么想的,后来发现……

结尾开放问题怎么设计

这是全场成败点。合格的开放问题满足三条:

  1. 你确实没答案(假问题会被一眼看穿,比不问更糟)
  2. 在场的人有可能答得上(问一个没人懂的问题等于炫技)
  3. 答案会改变你接下来的做法(说明你真的在征询,不是走过场)

反例:「大家还有什么问题吗?」——把责任推给听众,且默认自己讲完了。 正例:「AGENTS.md、CLAUDE.md、.cursorrules 各写一份,最后是不是在维护五份同样的东西?有没有人趟过这个,怎么收敛的?」

输出格式

按 🔴/🟡/🟢 分级列出,每条给:位置 → 原文 → 为什么 → 改写。不要只说「语气偏说教」这种没法执行的话;也不要为了凑数把中性表达标成问题——姿态问题通常集中在标题、结尾、行动项三处,正文的技术描述一般不需要动。

最后给一句整体判断:这份稿子现在是「分享」还是「交流」,以及改完之后是什么。

边界

  • 只验姿态与结构,不改技术内容、不核查事实正确性
  • 不要把稿子改弱:谦逊 ≠ 删掉观点。判断该留,只是要标记成「我的判断」而不是「客观事实」
  • 对外营销稿、对下培训材料不适用(那些场景本来就该是布道姿态)

Frequently asked questions

What does the Talk Text Review AI skill do?

讲稿/分享稿的文本验收——查的不是错别字,是**姿态**:这份稿子读起来是「我教你们」还是「我跟你们聊」。用心理逆反、自我暴露、认识论谦逊这几条机制,逐句找出会把听众推到对立面的表达并给出改写。触发词:讲稿验收、分享稿检查、这么讲会不会得罪人、居高临下、技术分享、演讲稿、内部分享、会不会太说教、口吻检查。适用于对内技术分享、公众号、文档开篇、PR 描述等任何「同级或高手在场」的表达场景。

Why use Talk Text Review on TypingMind?

Because you install it once and use it with any model. Talk Text Review 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 Talk Text Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/webkubor/writing-standard-skills/tree/main/skills/talk-text-review. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Talk Text Review?

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 Talk Text Review?

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

Is the Talk Text Review AI skill free?

Yes. It is published on GitHub by webkubor 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 👇