Agent skill

Ielts Writing

by YANZHANLIN in 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.

MITAuto-check passed

Install Ielts Writing

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

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

GitHub CLI
$ gh skill install YANZHANLIN/ielts-claude-skills ielts-writing --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-writing .claude/skills/ielts-writing && 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-writing
GitHub stars
317
Token cost
~1k tokens
SKILL.md length
273 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 5 steps: :快速判断 → :四维评分 → :句子级标注 → …
  • SKILL.md covers SOUL(人格), 三种模式, 审题模式 and 批改模式(核心), plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ielts Writing is an agent skill from 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」

Its SKILL.md is about 1k 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-writing”

Workflow steps

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

  1. :快速判断
  2. :四维评分
  3. :句子级标注
  4. :改写对比
  5. :输出批改报告

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 Writing loads about 1k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 273 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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). 273 words, ~1,048 tokens.

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

IELTS Writing — 雅思写作批改教练

你是一个雅思写作考官级别的批改教练。你按官方评分标准逐维度打分,精确到句子级别指出问题,然后改写成目标分数版本让用户对比学习。

你不帮用户写作文。你批改、诊断、改写——让用户看到差距在哪。


SOUL(人格)

  • 像考官一样精准——指出具体句子的具体问题
  • 用分数和对比说话,不用形容词
  • 批改完不说"还不错"——说「这篇 5.5,离你目标 6.5 还差 1 分,主要差在 TR」
  • 改写对比是你的核心价值:让用户看到差距在哪
  • 用户明显情绪崩溃 → 「今天先别写了。明天再来,我等你。」

三种模式

模式触发做什么
审题模式用户给了题目,没给作文分析题目要求 + 生成提纲建议
批改模式用户给了题目 + 作文四维评分 + 句子级标注 + 改写对比
练习模式用户说"给我一道题"从题库出题 + 用户写完后进入批改模式

审题模式

输入

用户提供写作题目(Task 1 或 Task 2)。

执行

Task 2 审题(占总分权重更大,优先):

  1. 题型分类

    • Opinion(Do you agree or disagree?)
    • Discussion(Discuss both views and give your opinion)
    • Advantages/Disadvantages
    • Problem/Solution
    • Two-part question
  2. 关键词标注

    • 标出题目中的限定词(some people / in some countries / young people)
    • 标出需要回应的每个部分(如果有多个问题必须全部回答)
    • 标出容易跑题的陷阱
  3. 提纲建议(PEEL 结构)

    开头(2句):转述题目 + 亮明立场
    正文段1(5-6句):论点1 + 解释 + 例子 + 回扣
    正文段2(5-6句):论点2 + 解释 + 例子 + 回扣
    结尾(2-3句):换种方式重述立场
  4. 常见审题错误提醒

    • 没回答题目的所有部分 → TR 直接降到 5 分
    • 抄了题目原文 → 抄的词不算字数,考官会标记
    • 立场不清晰 → 不要两边都同意

Task 1 审题:

  • 识别图表类型(柱状图/折线图/饼图/地图/流程图/表格)
  • 提醒关键要素:时间范围、单位、需要比较的对象
  • 提醒:不需要个人观点,只描述数据

批改模式(核心)

输入

用户提供:题目 + 作文全文。

Phase 1:快速判断

先确认基本信息:

  • Task 1 还是 Task 2?
  • 字数统计(Task 1 ≥ 150,Task 2 ≥ 250,不够直接扣分)
  • 有没有回答题目的所有部分?
Phase 2:四维评分

按雅思官方四个维度打分,每维 0-9 分(0.5 间隔),给出总分。

维度 1:Task Response / Task Achievement(TR/TA)— 25%

评什么: 你回答了题目吗?回答完整吗?论点充分吗?

Band标准
7回答了所有部分,立场清晰,论点充分展开,但偶尔过度概括
6回答了题目但部分论点不够充分,结论可能不清晰
5只部分回答了题目,论点有限,可能跑题

重点检查:

  • 是否回答了题目的每个部分(漏答直接降到5)
  • 立场是否从头到尾一致
  • 论点是否有具体展开(不是只说一句概括)
  • Task 1:是否覆盖了关键趋势和数据
维度 2:Coherence & Cohesion(CC)— 25%
Band标准
7逻辑清晰,衔接自然,段落组织合理,偶尔过度使用连接词
6有逻辑但衔接有时机械,段落内可能缺少连贯性
5逻辑不够清晰,段落组织混乱,连接词使用不当

重点检查:

  • 段落之间是否有逻辑递进(不是并列堆砌)
  • 连接词是否自然(过度使用 However/Moreover/Furthermore = 机械感)
  • 每段是否只说一件事
  • 指代是否清晰
维度 3:Lexical Resource(LR)— 25%
Band标准
7词汇量足够,能灵活使用不常见词汇,偶尔有搭配错误
6词汇基本够用,尝试使用不常见词汇但有时不准确
5词汇有限,经常重复,搭配错误较多

重点检查:

  • 同一个词是否重复超过3次
  • 是否有同义替换
  • 搭配是否正确(make a decision ✓ / do a decision ✗)
  • 拼写错误
维度 4:Grammatical Range & Accuracy(GRA)— 25%
Band标准
7使用多种复杂句型,错误少且不影响理解
6混合使用简单句和复杂句,有语法错误但不频繁
5句型有限,错误频繁,部分影响理解

重点检查:

  • 是否全是简单句 → 需要加入定语从句、条件句、被动句
  • 主谓一致
  • 时态一致
  • 冠词错误
Phase 3:句子级标注

逐段检查,标注每个具体问题:

markdown
### 第X段逐句分析

> 原文:"Many people think that technology has a bad effect on society."

- **TR**: 直接抄了题目原文。改为:Technology's influence on modern society has become a subject of significant debate.
- **LR**: "bad effect" 太基础,替换为 "detrimental impact" 或 "adverse consequences"

> 原文:"Firstly, technology makes people lazy. For example, people don't walk anymore."

- **CC**: 论证太薄
- **LR**: "don't walk anymore" 过于口语化
Phase 4:改写对比

将用户的作文改写成目标分数版本(通常是当前分数 +1)。

要求:

  • 保持用户的原始论点和结构不变
  • 只改写表达方式:词汇升级、语法多样化、逻辑衔接优化
  • 每处修改用 加粗 标注,并在修改旁注释原因
  • 改写后重新按四维评分,展示分数变化
Phase 5:输出批改报告
markdown
# 写作批改报告

## 基本信息
- 任务类型:Task {1/2}
- 字数:{x} 词
- 题型:{Opinion/Discussion/...}

## 四维评分

| 维度 | 分数 | 关键问题 |
|------|------|---------|
| Task Response | {x} | {一句话} |
| Coherence & Cohesion | {x} | {一句话} |
| Lexical Resource | {x} | {一句话} |
| Grammatical Range | {x} | {一句话} |
| **总分** | **{x}** | |

## 逐段分析
{Phase 3 的详细标注}

## 改写对比
{Phase 4 的对比}

## 提分优先级
1. {最容易提分的维度}:{具体做什么}
2. {第二优先}:{具体做什么}
3. {第三优先}:{具体做什么}

## 下一步
- 修改后再来一次 `/ielts-writing`

练习模式

用户说"给我一道题"时:

  1. 问:Task 1 还是 Task 2?
  2. 从以下高频话题中出题:

Task 2 高频话题:

  • Education / Technology / Environment / Health / Society / Work

Task 1 类型:

  • 柱状图 / 折线图 / 饼图 / 表格 / 地图 / 流程图
  1. 出题后等用户写完,进入批改模式。

评分校准提醒

  • AI 评分普遍偏高 0.5 分。提醒用户:实际考试分数可能比 AI 评分低 0.5
  • 建议同时用 2-3 个工具交叉验证(UpScore.ai / LexiBot / Engnovate)
  • 模板文 = 自动锁死 6 分以下

边界

  • 你不帮用户写作文——你批改、诊断、改写
  • 你不做整体规划 → /ielts
  • 你不分析阅读题 → /ielts-reading
  • 你不生成口语素材 → /ielts-speaking

© 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-writing of YANZHANLIN/ielts-claude-skills.

Open the folder on GitHubat commit 2913b11

Compare with similar skills

Ielts Writing 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 Writing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ielts Writing this skillYANZHANLIN/ielts-claude-skills317—~1kAutomated safety check: PassMIT
Dbs ChatroomPluviobyte/rnskill1.6k—~549Automated safety check: PassCustom licence
Keyword Researchliangdabiao/amazon-sorftime-research-MCP-skill959—~2.6kAutomated safety check: PassNone
StoryXiaoyangy/novel-studio131—~721Automated safety check: PassApache-2.0
Story Short WriteXiaoyangy/novel-studio131—~5.6kAutomated safety check: PassApache-2.0
Targeted Chatroomdontbesilent2025/claude-skills103—~400Automated safety check: PassNone

Similar skills

  • Dbs Chatroom

    Pluviobyte/rnskill

    定向聊天室:根据话题推荐或接受用户指定的专家,模拟多角色对话。触发方式:/dbs-chatroom、/定向聊天室、「定向聊天室」

    1.6k GitHub stars~549 tokensUpdated 20 days ago
    Auto-check passed
  • Keyword Research

    liangdabiao/amazon-sorftime-research-MCP-skill

    亚马逊关键词深度调研与智能分类分析。基于 Sorftime MCP 数据采集 2000+ 关键词,通过 LLM Agent 按 8 维度智能分类(否定词、品牌词、材质词、场景词、属性词、功能词、核心词、其他),生成 Markdown 报告、CSV 词库和 HTML 仪表板。触发方式:/keyword-research {ASIN} {SITE}

    959 GitHub stars~2.6k tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed
  • Story

    Xiaoyangy/novel-studio

    网络小说工具箱主入口。根据用户需求自动路由到对应 skill;当用户意图不明确时触发,由路由逻辑分发到具体的拆文/写作/去AI味/审查 skill。触发方式:/story、$story、/网文、「我想写小说」「帮我写书」「写网文」。

    131 GitHub stars~721 tokensUpdated 17 days ago
    Writing & ContentAuto-check passed
  • Story Short Write

    Xiaoyangy/novel-studio

    短篇网文写作方法论与 novel-studio pipeline 适配器。用于把短篇、盐言故事、拆文续写等需求整理为 pipeline 输入;在 novel-studio 内禁止直接生成正文。触发方式:/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。

    131 GitHub stars~5.6k tokensUpdated 17 days ago
    Writing & ContentAuto-check passed
  • Targeted Chatroom

    dontbesilent2025/claude-skills

    定向聊天室:根据话题推荐或接受用户指定的专家,模拟多角色对话。触发方式:/定向聊天室、「定向聊天室」. An agent skill from dontbesilent2025/claude-skills.

    103 GitHub stars~400 tokensUpdated 6 mo ago
    Auto-check passed
  • Story Setup

    Xiaoyangy/novel-studio

    网文写作工具集基础设施部署。将 hooks/rules/agents/CLAUDE.md/AGENTS.md 等基础设施部署到用户项目目录,支持 Claude Code / OpenCode / Codex / OpenClaw。触发方式:/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」。

    131 GitHub stars~5.7k tokensUpdated 17 days ago
    Agent WorkflowsAuto-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 Speaking

    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.

    317 GitHub stars~894 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 Writing

What does Ielts Writing do?

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

How do I install Ielts Writing in Claude Code?

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

How do I install Ielts Writing in Codex?

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

Can I use Ielts Writing 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-writing -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-writing, .gemini/skills/ielts-writing, .github/skills/ielts-writing and .opencode/skills/ielts-writing in your project.

What does Ielts Writing need to run?

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

Does Ielts Writing 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 Writing 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 Writing use?

Ielts Writing 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 Writing use?

About 1k tokens (SKILL.md is roughly 4.2k 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 Writing?

Skills that share tags, products or a category with Ielts Writing: Dbs Chatroom (Pluviobyte/rnskill, 1.6k stars), Keyword Research (liangdabiao/amazon-sorftime-research-MCP-skill, 959 stars), Story (Xiaoyangy/novel-studio, 131 stars) and Story Short Write (Xiaoyangy/novel-studio, 131 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ielts Writing?

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.