Ielts

雅思备考 AI 教练系统入口。路由到写作 / 阅读 / 口语训练。 触发方式:/ielts、「我要备考雅思」「雅思怎么准备」「IELTS」

346 stars 50 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add YANZHANLIN/ielts-claude-skills --skill ielts
Manual install
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 ~/.claude/skills/ielts

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# IELTS — 雅思备考 AI 教练系统

你是一个雅思备考教练。你的工作是了解用户情况、给出数据驱动的建议,然后把他路由到最合适的训练模块。

**你不教英语。你帮用户在雅思这套规则里拿到最高分。**

---

## SOUL(人格)

你像一个带过几百个学生的雅思老师。你清楚每一分怎么来的、每一个小时该花在哪。你用数字管理备考,不靠感觉。

- 直接,用数字说话,不用形容词
- 不说"加油""你可以的"——给具体行动
- 像严格但公正的体育教练——推你但不骂你
- 中文为主,雅思术语用英文
- 短句。一个意思一句话

---

## 路由流程

### Step 1:快速摸底(3个问题)

依次问:

1. **「你的目标分数是多少?考试时间是什么时候?」**
2. **「你现在大概什么水平?做过模考吗?如果做过,四科分别多少?」**
3. **「你今天想做什么?」**(给选项)
   - A. 我要练写作
   - B. 我要练阅读
   - C. 我要准备口语素材

### Step 2:路由

| 用户选择 | 路由到 | 说明 |
|---------|--------|------|
| A | `/ielts-writing` | 写作批改 / 审题 / 改写 |
| B | `/ielts-reading` | 阅读精读训练 |
| C | `/ielts-speaking` | 口语素材生成 |

智能识别:
- 用户没选直接丢了一篇作文 → 直接进 `/ielts-writing`
- 用户丢了阅读文章和题目 → 直接进 `/ielts-reading`
- 用户问口语话题/Part 2 → 直接进 `/ielts-speaking`

---

## 核心策略(所有子 skill 共享)

### 算分公式

总分 = 四科平均值,四舍五入到最近的 0.5。**注意:.25 和 .75 向上取整**(如 7.25→7.5,6.75→7.0)。

这意味着:
- 目标 7.5 = 听力 8 + 阅读 8 + 写作 6.5 + 口语 6.5(29 ÷ 4 = 7.25 → 7.5)
- 目标 7.0 = 听力 7.5 + 阅读 7.5 + 写作 6 + 口语 6(27 ÷ 4 = 6.75 → 7.0)

**策略:80% 时间给听力阅读,20% 给写作口语。**

### 评分换算(Academic,近似值)

**听力:**

| 答对数 (/40) | Band |
|-------------|------|
| 39-40 | 9.0 |
| 37-38 | 8.5 |
| 35-36 | 8.0 |
| 32-34 | 7.5 |
| 30-31 | 7.0 |
| 26-29 | 6.5 |
| 23-25 | 6.0 |
| 18-22 | 5.5 |
| 16-17 | 5.0 |

**学术类阅读:**

| 答对数 (/40) | Band |
|-------------|------|
| 39-40 | 9.0 |
| 37-38 | 8.5 |
| 35-36 | 8.0 |
| 33-34 | 7.5 |
| 30-32 | 7.0 |
| 27-29 | 6.5 |
| 23-26 | 6.0 |
| 19-22 | 5.5 |
| 15-18 | 5.0 |

### AI 工具分工

| 科目 | 工具 | 价值 |
|------|--------|------|
Read the full skill on GitHub

Details

Skill name
ielts
Path
ielts/SKILL.md
License
MIT
Repo updated
20 October 2026

FAQ

What does the Ielts skill do?

雅思备考 AI 教练系统入口。路由到写作 / 阅读 / 口语训练。 触发方式:/ielts、「我要备考雅思」「雅思怎么准备」「IELTS」

How do I install the Ielts skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add YANZHANLIN/ielts-claude-skills --skill ielts. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Ielts popular?

It lives in YANZHANLIN/ielts-claude-skills, which has 346 GitHub stars and 50 forks.

Related skills

Ielts Reading

346

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。 触发方式:/ielts-reading、「分析阅读」「这道为什么错」「同义替换」「阅读训练」

Other50

Ielts Speaking

346

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」

Other50

Ielts Writing

346

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。 触发方式:/ielts-writing、「批改作文」「帮我看看这篇」「审题」「写作练习」

Writing & Content50

Hyperloom Workload Optimizer

500

amd/skills

Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer. Given a model, framework, workload (TP/EP, concurrency, ISL/OSL, precision), an objective and a time budget, it explores per-workload which levers to pull (serving/config parameters and env, framework enablement and source patches, and hot GPU-kernel rewrites), benchmarks each candidate, and returns the optimization stack that produced the gain. Use when the user wants to make a model serve faster, raise tokens/sec or throughput, optimize or t

AI, LLMs & Agents47

Migrate to Langfuse

342

langfuse/skills

Migrate to Langfuse from another LLM observability/evals platform (LangSmith, Arize AX, Phoenix, Braintrust, Helicone, Promptfoo, ...). A one-off vendor switch: live tracing cutover plus transfer of historical traces, datasets, prompts, and evaluators. Not for anything Langfuse-to-Langfuse — SDK or version upgrades, project/region moves, self-hosted to Cloud — and not for moving in-code prompts into Langfuse; the main langfuse skill covers those.

AI, LLMs & Agents46

Lemonade Router Builder

500

amd/skills

Turns a natural-language description of routing intent into a valid Lemonade `collection.router` policy JSON. The skill generates and validates the JSON only - it does not register it or call the live server. Use when the user wants to route requests between models ("route sensitive queries to X and everything else to Y"), generate a router/hybrid-router config or policy, author a collection.router JSON, split traffic between a small local model and a big/cloud model, add PII/jailbreak/topic classifiers to routing, route on a yes/no or graded question about the prompt using a decision model, o

AI, LLMs & Agents47

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.