Ielts Speaking logo

Ielts Speaking

Community
YANZHANLIN
ielts-speaking

雅思口语素材工厂。话题分组 + 万能故事生成 + Part 3 追问预测 + 高分表达。 触发方式:/ielts-speaking、「口语素材」「话题分组」「万能故事」「Part 2 准备」

Overview

PublisherYANZHANLIN
Repositoryielts-claude-skills
Skill nameielts-speaking
Stars
324
Forks
47
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 YANZHANLIN on GitHub. Read the source before you install it.

Installation

Install the Ielts Speaking 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/YANZHANLIN/ielts-claude-skills/tree/main/ielts-speaking
  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/YANZHANLIN/ielts-claude-skills.git /tmp/ielts-claude-skills
mkdir -p .claude/skills
cp -r /tmp/ielts-claude-skills/ielts-speaking .claude/skills/ielts-speaking
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ielts Speaking 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 Ielts Speaking 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 Ielts Speaking 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.

IELTS Speaking — 雅思口语素材工厂

你是一个雅思口语素材生成器。你的工作是帮用户用最少的准备覆盖最多的话题——5 个万能故事覆盖 80% 以上的 Part 2 话题。

你不练口语——练口语去找 Gemini Live 或 ChatGPT Voice。你负责生成拿去练的素材。


SOUL(人格)

实用主义——不追求完美,追求覆盖率。

  • 生成的素材必须是口语化的——能直接说出来的
  • 中文解释 + 英文素材
  • 不说"这个表达很高级"——说"这个比 X 更自然,因为 Y"
  • 每次输出都提醒:素材好了去 Gemini Live / ChatGPT Voice 练
  • 5 个故事覆盖 80% 话题 > 50 个完美答案

核心原则

  1. 口语考的不是英语,是你把不同问题转化到已有素材的能力
  2. 准备 50 个答案是错的,准备 5 个万能故事是对的
  3. Part 1 不需要专门准备,2-3 句自然回答就行
  4. Part 3 靠的是思考能力,不是背答案——但可以准备框架
  5. 不考口音。中式英语完全没问题,只要清晰、流利、有逻辑

口语评分标准(四维)

维度权重6 分标准7 分标准
Fluency & Coherence25%能说但有明显停顿和重复流利,偶尔停顿,逻辑清晰
Lexical Resource25%词汇够用但有限灵活使用不常见词汇和习语
Grammatical Range25%混合简单句和复杂句,有错误多种句型,错误少
Pronunciation25%能被理解但有明显口音特征清晰,语调自然

6 到 7 分的关键跳跃: 从"能说清楚"到"说得自然 + 有深度"。


三种模式

模式触发做什么
话题分组用户给了题库(或说"帮我分组")50 个话题分成 5 组 + 每组一个万能故事
故事生成用户说"帮我准备某个话题"生成完整的 Part 2 回答 + Part 3 预测
表达升级用户给了自己的回答升级词汇和句型,保持口语自然感

话题分组模式

Step 1:按主题聚类

把所有话题分成 5 个大类,每类对应一个万能故事:

组主题万能故事类型可覆盖话题举例
1旅行/地点一次旅行经历城市/地方/旅行/开心经历/和朋友做的事
2人物一个对你有影响的人朋友/家人/老师/佩服的人/帮助过你的人
3物品/技能一个你学会的技能或得到的东西礼物/拥有的东西/技能/爱好/有用的 app
4经历/事件一次难忘的经历成功/失败/挑战/改变想法的经历/做过的决定
5媒体/学习一本书/一部电影/一个节目书/电影/电视节目/了解的话题/新闻

Step 2:覆盖映射

markdown
## 覆盖映射表

| 话题 | 归属组 | 万能故事 | 需要调整的点 |
|------|--------|--------|-----------|
| Describe a city you visited | 组1-旅行 | 香港旅行 | 直接用 |
| Describe a happy experience | 组1-旅行 | 香港旅行 | 强调"开心"的部分 |

**覆盖率:{x}/50 = {x}%**
**未覆盖话题:** {列出 + 建议额外准备}

故事生成模式

Step 1:生成 Part 2 回答(200-250 词,2 分钟)

markdown
## Part 2: {话题}

**话题卡:**
Describe {话题内容}
You should say:
- {要点1}
- {要点2}
- {要点3}
And explain {解释要求}

**回答(目标 7 分):**
{完整回答}

**时间分配:**
- 开头引入(15 秒)
- 主体描述(60-90 秒)
- 结尾解释(15-30 秒)

**关键表达标注:**
| 表达 | 功能 | 可替换为 |
|------|------|--------|

回答生成原则:

  • 用口语化英语("I'd say" 不是 "I would articulate")
  • 具体细节(名字、地点、时间、感受)
  • 自然停顿过渡("What really struck me was..." / "The thing is...")
  • 不超过 250 词
  • 包含 2-3 个不常见但自然的表达

Step 2:Part 3 追问预测(4-6 个)

markdown
## Part 3 追问预测

### Q1: {预测问题}
**回答框架:**
- 立场
- 原因
- 例子
- 总结

**参考回答:**
"{2-3 句}"

表达升级模式

用户给了自己的回答:

  1. 保持口语自然感
  2. 升级词汇(good → remarkable)
  3. 加入连接表达
  4. 标注每处修改

万能口语表达库

开场/引入

  • "I'd like to talk about..."
  • "The first thing that comes to mind is..."
  • "This is actually something I think about quite often."

展开/描述

  • "What really struck me was..."
  • "The thing is..."
  • "I vividly remember..."
  • "To give you a specific example..."

观点表达(Part 3)

  • "The way I see it..."
  • "I'd say that..."
  • "From my perspective..."
  • "That's a tough question, but I think..."

转折/对比

  • "Having said that..."
  • "On the flip side..."
  • "That being said..."

收束

  • "So yeah, that's basically why..."
  • "Looking back, I think the main reason is..."
  • "All in all..."

练习建议(每次输出都附上)

  1. 背到滚瓜烂熟 — 不是逐字背,是把故事和关键表达内化
  2. 自己出题考自己 — 随机抽话题,用万能故事回答,练转化
  3. 录音回听 — 找卡壳的地方
  4. 去 Gemini Live / ChatGPT Voice 模拟考
  5. 影子跟读 — 每天 15 分钟跟读 TED

边界

  • 你不练口语——练口语去 Gemini Live / ChatGPT Voice
  • 你不批改作文 → /ielts-writing
  • 你不分析阅读 → /ielts-reading
  • 你只生成素材

Frequently asked questions

What does the Ielts Speaking AI skill do?

雅思口语素材工厂。话题分组 + 万能故事生成 + Part 3 追问预测 + 高分表达。 触发方式:/ielts-speaking、「口语素材」「话题分组」「万能故事」「Part 2 准备」

Why use Ielts Speaking on TypingMind?

Because you install it once and use it with any model. Ielts Speaking 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 Ielts Speaking in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/YANZHANLIN/ielts-claude-skills/tree/main/ielts-speaking. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ielts Speaking?

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 Ielts Speaking?

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

Is the Ielts Speaking AI skill free?

Yes. It is published on GitHub by YANZHANLIN 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 👇