Agent skill

Ielts Speaking

by YANZHANLIN in YANZHANLIN/ielts-claude-skills

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. An agent skill from YANZHANLIN/ielts-claude-skills.

MITAuto-check passed

Install Ielts Speaking

skills CLI
$ npx skills add YANZHANLIN/ielts-claude-skills --skill ielts-speaking -a claude-code

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

GitHub CLI
$ gh skill install YANZHANLIN/ielts-claude-skills ielts-speaking --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/YANZHANLIN/ielts-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ielts-speaking .claude/skills/ielts-speaking && 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
ielts-speaking
GitHub stars
317
Token cost
~894 tokens
SKILL.md length
315 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

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. An agent skill from YANZHANLIN/ielts-claude-skills.

  • Works in 4 steps: :按主题聚类 → :覆盖映射 → :生成 Part 2 回答(200-250 词,2 分钟) → …
  • SKILL.md covers SOUL(人格), 核心原则, 口语评分标准(四维) and 三种模式, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ielts Speaking is an agent skill from YANZHANLIN/ielts-claude-skills. 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」

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 雅思备考 AI 教练 Claude Code skills · 4 个无状态 skill · 写作/阅读/口语训练. The licence is MIT.

Example prompts

  • “/ielts-speaking”

Workflow steps

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

  1. :按主题聚类
  2. :覆盖映射
  3. :生成 Part 2 回答(200-250 词,2 分钟)
  4. :Part 3 追问预测(4-6 个)

What it can do on your machine

Read from SKILL.md and the folder at commit 2913b11. 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 (its code samples are markdown).

    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

Ielts Speaking loads about 894 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 315 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~894

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 YANZHANLIN/ielts-claude-skills at commit 2913b11, republished under its MIT licence (© YANZHANLIN). 315 words, ~894 tokens.

Download SKILL.mdSave it as .claude/skills/ielts-speaking/SKILL.md (or your agent's skills folder).
name
ielts-speaking
description
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」
metadata.version
1.0.0

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

© YANZHANLIN, 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 ielts-speaking of YANZHANLIN/ielts-claude-skills.

Open the folder on GitHubat commit 2913b11

Compare with similar skills

Ielts Speaking 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.

Ielts Speaking compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ielts Speaking this skillYANZHANLIN/ielts-claude-skills317—~894Automated safety check: PassMIT
Speakingsteipete/agent-scripts7.3k—~1.2kAutomated safety check: PassMIT
Step Partsearthtojake/text-to-cad19k1 repos~1.5kAutomated safety check: PassMIT
Canopy Part Title Blockheygen-com/hyperframes60k1 repos~1kAutomated safety check: PassApache-2.0
Speak Summarygithub/awesome-copilot40k—~1.6kAutomated safety check: PassMIT
Speak Observabilityjeremylongshore/tons-of-skills-marketplace2.8k—~653Automated safety check: PassMIT

Similar skills

  • Speaking

    steipete/agent-scripts

    Speaking ops: invites, keynotes, panels, Gmail/calendar, conferences.

    7.3k GitHub stars~1.2k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Step Parts

    earthtojake/text-to-cad

    Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers…

    19k GitHub starsUsed in 1 repo~1.5k tokens
    Backend & APIsAuto-check passed
  • Canopy Part Title Block

    heygen-com/hyperframes

    A HyperFrames video block in which a canopy of leaves sweeps across the frame and parts to reveal two headlines, rendered at 1920×1080 for 12 seconds.

    60k GitHub starsUsed in 1 repo~1k tokens
    Media & CreativeAuto-check passed
  • Speak Summary

    github/awesome-copilot

    Official

    Convert text, markdown, or a summary produced by another skill into a listenable MP3 using local CPU-only neural text-to-speech.

    40k GitHub stars~1.6k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Speak Observability

    jeremylongshore/tons-of-skills-marketplace

    Monitor Speak API health, assessment latency, session metrics, and pronunciation score distributions.

    2.8k GitHub stars~653 tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Speak At The Council

    mohitagw15856/pm-claude-skills

    Summarise what Speak At The Council does in one line. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~243 tokensUpdated yesterday
    Auto-check passed

More from YANZHANLIN/ielts-claude-skills

  • Ielts Reading

    YANZHANLIN/ielts-claude-skills

    雅思阅读精读教练。同义替换提取 + T/F/NG 逻辑拆解 + 段落结构分析 + 错题诊断. An agent skill from YANZHANLIN/ielts-claude-skills.

    317 GitHub stars~871 tokensUpdated 2 mo ago
    Auto-check passed
  • Ielts Writing

    YANZHANLIN/ielts-claude-skills

    雅思写作批改教练。四维评分 + 句子级标注 + 改写对比 + 审题检查. An agent skill from YANZHANLIN/ielts-claude-skills.

    317 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed
  • Ielts

    YANZHANLIN/ielts-claude-skills

    雅思备考 AI 教练系统入口。路由到写作 / 阅读 / 口语训练. An agent skill from YANZHANLIN/ielts-claude-skills.

    317 GitHub stars~551 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Ielts Speaking

What does Ielts Speaking 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. An agent skill from YANZHANLIN/ielts-claude-skills. Ielts Speaking is an agent skill from YANZHANLIN/ielts-claude-skills.

How do I install Ielts Speaking in Claude Code?

Run `npx skills add YANZHANLIN/ielts-claude-skills --skill ielts-speaking -a claude-code`. Or copy the skill folder (ielts-speaking in YANZHANLIN/ielts-claude-skills) into .claude/skills/ielts-speaking in your project. Claude Code loads it when a task matches its description.

How do I install Ielts Speaking in Codex?

Run `npx skills add YANZHANLIN/ielts-claude-skills --skill ielts-speaking -a codex`. Or copy the skill folder (ielts-speaking in YANZHANLIN/ielts-claude-skills) into .agents/skills/ielts-speaking in your project. Codex loads it when a task matches its description.

Can I use Ielts Speaking 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 YANZHANLIN/ielts-claude-skills --skill ielts-speaking -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ielts-speaking, .gemini/skills/ielts-speaking, .github/skills/ielts-speaking and .opencode/skills/ielts-speaking in your project.

What does Ielts Speaking need to run?

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

Does Ielts Speaking 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 Ielts Speaking 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 Ielts Speaking use?

Ielts Speaking 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 Ielts Speaking use?

About 894 tokens (SKILL.md is roughly 3.6k 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 Ielts Speaking?

Skills that share tags, products or a category with Ielts Speaking: Speaking (steipete/agent-scripts, 7.3k stars), Step Parts (earthtojake/text-to-cad, 19k stars), Canopy Part Title Block (heygen-com/hyperframes, 60k stars) and Speak Summary (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ielts Speaking?

YANZHANLIN (a GitHub user) maintains it in YANZHANLIN/ielts-claude-skills, which has 317 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on July 20, 2026.

Source: YANZHANLIN/ielts-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.