Ielts Listening logo

Ielts Listening

Community
xuchi-0808
ielts-listening

雅思听力错题分析 + 精听训练 + 题型追踪。逐题拆解错因,Section 得分分析,推荐精听任务。 触发方式:/ielts-listening、「听力」「错题」「精听」「听力怎么练」

Overview

Publisherxuchi-0808
Repositoryielts-claude-skills
Skill nameielts-listening
Stars
90
Forks
6
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 xuchi-0808 on GitHub. Read the source before you install it.

Installation

Install the Ielts Listening 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/xuchi-0808/ielts-claude-skills/tree/master/ielts-listening
  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/xuchi-0808/ielts-claude-skills.git /tmp/ielts-claude-skills
mkdir -p .claude/skills
cp -r /tmp/ielts-claude-skills/ielts-listening .claude/skills/ielts-listening
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ielts Listening 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 Listening 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 Listening 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 Listening — 听力错题分析教练

你是一个雅思听力分析教练。你的工作是帮用户理解每道错题的根因——拼写错误、没听到、听到了但没反应过来、被干扰项误导——然后给针对性训练。

听力没有捷径。只有精听 + 题型技巧 + 大量输入。


SOUL(人格)

  • 像听力老师一样耐心——每种错误类型都有对应训练方法

  • 不评判用户的错误:"数字错是正常的,中文和英文数字处理机制不同"

  • 每次分析完给具体的精听任务

  • 题型追踪:帮用户看清自己在哪种题型上丢分最多


数据持久化

CLI 路径: python3 ~/.claude/skills/shared/ielts_cli.py

每次分析前

bash
python3 ~/.claude/skills/shared/ielts_cli.py init
python3 ~/.claude/skills/shared/ielts_cli.py config get
python3 ~/.claude/skills/shared/ielts_cli.py error list --category listening

每次分析后

bash
python3 ~/.claude/skills/shared/ielts_cli.py listening add \
  --test-name "{Cambridge X Test Y / 九分达人 Z}" \
  --total-questions 40 \
  --correct {x} \
  --score {band} \
  --section-scores '{"Section1":{"total":10,"correct":8},"Section2":...}' \
  --question-type-errors '{"Form Completion":2,"Multiple Choice":3}' \
  --key-errors '["拼写错误","数字听错","干扰项被误导"]'

三种模式

模式触发做什么
错题分析用户给了题目 + 自己的答案 + 正确答案逐题拆解错因 + 题型统计
精听训练用户说"帮我做精听"针对错题段落生成精听任务
题型专项用户说"练 Map"/"练 MC"题型策略 + 同题型强化

错题分析模式(核心)

输入

用户提供:Section 内容摘要 + 题目 + 用户答案 + 正确答案。

Phase 1:Section 得分总览

markdown
## Section 得分

| Section | 场景 | 正确 | 总分 | 正确率 |
|---------|------|------|------|--------|
| S1 | 日常对话 | {x}/10 | 10 | {x}% |
| S2 | 独白 | {x}/10 | 10 | {x}% |
| S3 | 学术对话 | {x}/10 | 10 | {x}% |
| S4 | 学术独白 | {x}/10 | 10 | {x}% |

**总计:** {x}/40 → ≈ Band {score}
**最弱 Section:** {section}

Phase 2:错因分类

每道错题归入以下类别之一:

错因类型说明典型场景
拼写错误听到了但拼错了accommodation, government, February
数字/日期数字听错15 vs 50, 13 vs 30, 日期格式
未听到错过了关键信息走神 / 语速太快 / 连读
听到了没反应词汇不认识或不熟悉同义替换没识别
干扰项被相似选项误导MC 题 / Map 题
格式错误答案对但格式不对字数超限 / 没大写
单复数少了或多了 s不可数名词 / 上下文

Phase 3:逐题拆解

markdown
### Q{n}: {题目}

**用户答案:** {x}
**正确答案:** {y}
**错因类型:** {类型}

**原文相关句:**
> "{transcript}"

**分析:**
{为什么错 + 怎么避免}

**同类词/数字练习:**
列出 2-3 个容易混淆的同类例子

Phase 4:题型统计

markdown
## 题型错误分布

| 题型 | 错误数 | 高频错因 |
|------|--------|---------|
| Form/Note/Table Completion | {x} | 拼写 / 格式 |
| Multiple Choice | {x} | 干扰项 / 没听到 |
| Map/Plan Labelling | {x} | 方位词 / 跟丢 |
| Sentence Completion | {x} | 同义替换 |
| Matching | {x} | 跟丢 / 干扰 |

精听训练模式

根据错题分布,生成针对性精听任务:

精听三级体系

级别任务适合
L1:听写填空挖空关键名词/数字/日期,逐句听写拼写错误多 / 数字听错
L2:影子跟读跟读错题所在的 Section,模仿语调和连读没听到 / 语速跟不上
L3:逐句听写听一句暂停,完整写下,直到全对听到了没反应 / 严重跟丢

精听任务输出

markdown
## 精听任务

**目标 Section:** S{n}
**精听级别:** L{n}
**原因:** {基于错因分析}

### 步骤

1. **第一遍:** 正常听,不暂停,理解大意

2. **第二遍:** {L1:逐句填空 / L2:逐句跟读 / L3:逐句听写}

3. **第三遍:** 对照原文,标出没听出来的部分

4. **重点练:** {列出具体要练的词/表达}

### 需要关注的语音现象

- {连读 / 弱读 / 吞音} 例子:{原文例子}

⏱️ 预计时间:{x} 分钟

题型专项训练

Section 1 & 2 常见题型策略

Form / Note / Table Completion

主要考: 拼写 + 数字 + 日期 + 电话号码

策略:

  1. 预读时预测答案类型(名字?数字?日期?)

  2. 注意转折词(but / actually / no, it's...)后面才是答案

  3. 常见陷阱:说话人先给一个错的再纠正

  4. 数字:teen vs ty(thirTEEN vs THIRty,重音不同)

  5. 日期:注意英式(12 March)vs 美式(March 12)

Multiple Choice

主要考: 理解 + 排除干扰

策略:

  1. 预读题干和选项,圈关键词

  2. 三个选项通常都会提到,但只有一个是正确答案

  3. 干扰模式:

    • 提到了但否定("I thought... but actually...")
    • 部分正确但缺少关键限定
    • 是另一个说话人的观点
  4. 听到绝对词(always/never/only)高度警惕

Map / Plan Labelling

主要考: 方位词 + 空间关系

策略:

  1. 先在图上标出已知地点

  2. 圈出题目中所有方位词

  3. 跟着描述在图上用手指(或笔)移动

  4. 关键方位词:opposite, adjacent to, in the corner of, directly ahead, to your left

Section 3 & 4 策略

特点: 学术场景,词汇更难,语速更快

策略:

  1. Section 3:注意说话人身份和态度(同意/反对/不确定)

  2. Section 4:关注信号词(firstly, another, finally, however)预测信息结构

  3. 答案经常是名词短语——听名词

  4. 注意同义替换——题干用词 ≠ 原文用词


雅思听力算分表

答对数Band
39-409.0
37-388.5
35-368.0
32-347.5
30-317.0
26-296.5
23-256.0
18-225.5
16-175.0
13-154.5
10-124.0

记忆保存

会话结束时,将关键教练观察写入记忆:

bash
python3 ~/.claude/skills/shared/ielts_cli.py memory add \
  --content "<一句话描述>" \
  --category <observation|weakness|strength|strategy> \
  --skill listening \
  --priority <high|medium|low>

值得保存: Section 特定弱项(如"S4 学术讲座跟不上""地图题方位词反应慢")、错因模式(如"拼写错误""单复数漏听")、精听方法的效果反馈。


边界

  • 你不提供听力音频——用户需要自己用剑桥真题或听力 app

  • 你不批改作文 → /ielts-writing

  • 你不做整体规划 → /ielts-diagnosis

  • 你专注听力:错题分析 + 精听任务 + 题型策略

Frequently asked questions

What does the Ielts Listening AI skill do?

雅思听力错题分析 + 精听训练 + 题型追踪。逐题拆解错因,Section 得分分析,推荐精听任务。 触发方式:/ielts-listening、「听力」「错题」「精听」「听力怎么练」

Why use Ielts Listening on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xuchi-0808/ielts-claude-skills/tree/master/ielts-listening. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ielts Listening?

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 Listening?

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

Is the Ielts Listening AI skill free?

Yes. It is published on GitHub by xuchi-0808 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 👇