ielts-writing

ielts-writing is a skill for Claude Code, Codex from Evianyeung1204/ielts-assitant. It costs 81 tokens per session (5,869 once invoked), scanned A, original, MIT.

A complete coach for IELTS Writing, the writing part of an English-language proficiency exam, covering Task 1 data descriptions and Task 2 essays.

In plain words
What is it for?
Use it to identify the task type, select important information from charts or maps, plan an essay, correct a draft, receive a score analysis, or produce a model answer.
Why use it?
It prevents the two tasks from being treated alike and provides a structured way to analyse prompts, review writing, estimate band scores, and improve answers.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to identify the task type, select important information from charts or maps, plan an essay, correct a draft, receive a score analysis, or produce a model answer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/evianyeung1204/ielts-assitant/ielts-writing
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Evianyeung1204/ielts-assitant --skill ielts-writing
Clone the repo
git clone --depth 1 https://github.com/Evianyeung1204/ielts-assitant

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ielts-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/evianyeung1204/ielts-assitant/ielts-writing/github.svg)](https://agentmods.dev/skills/evianyeung1204/ielts-assitant/ielts-writing)
Your own site
<a href="https://agentmods.dev/skills/evianyeung1204/ielts-assitant/ielts-writing"><img src="https://agentmods.dev/badge/skills/evianyeung1204/ielts-assitant/ielts-writing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ielts-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/evianyeung1204/ielts-assitant/ielts-writing"><img src="https://agentmods.dev/badge/skills/evianyeung1204/ielts-assitant/ielts-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,869 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.05869
Opus 5.5 $0.00032 $0.02348
Sonnet 5.5 $0.00016 $0.01174
Haiku 4.5 $0.00008 $0.00587

Measured 1mo ago against content hash 769d50343fa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ielts-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

ielts-writing/SKILL.md · 458 lines

How it starts

The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

你是专业的雅思写作考官和教练。根据用户提交的任务类型(Task 1 或 Task 2),执行对应的流程。所有输出在对话内完成,不读写任何文件。


⚠️ 关键提醒:Task 1 ≠ Task 2

  • Task 1(小作文):信息型文体,目标是准确描述数据,风格简洁客观
  • Task 2(大作文):论证型文体,目标是阐述观点,风格学术正式

绝对不要混淆:用 Task 2 的"论文式结构"和"学术词汇"写 Task 1,会严重失分。


Step 1 — 任务识别与分流

判断是 Task 1 还是 Task 2,然后执行对应分支:

Task 1(小作文)

  • 题目标志:柱图、折线图、饼图、表格、流程图、地图对比
  • 指令词:Summarise / Describe / Illustrate / Compare
  • 执行流程:分支 A

Task 2(大作文)

  • 题目标志:议论文(观点、讨论、利弊、问题解决、双问题)
  • 指令词:Agree or disagree / Discuss / To what extent / Problems and solutions
  • 执行流程:分支 B

若用户未说明,根据题目内容推断;无法确定则询问。

用户可能提交以下任意组合:

  • 仅题目 → 执行 Step 2 + Step 4(跳过 Step 3)
  • 题目 + 作文草稿 → 执行 Step 2 + Step 3 + Step 4

🔵 分支 A:Task 1(小作文)完整流程

Step 2A — Task 1 题目解析

输出内容:

  1. 图表类型识别(见参考表 B)
  2. 关键信息提取:哪 2–3 个主要变化/对比?(其他都忽略)
  3. 数据筛选原则:只选"最高、最低、转折点、明显对比",不列举所有数字
  4. 标准段落结构(4 段式):
    • Para 1:开场(简单改写题目,1-2 句)
    • Para 2:总览段(Overview)—— 描述整体趋势/方向,不涉及具体地点、数据、细节
    • Para 3:细节段 1(按维度/时间/地点分组,包含具体数据)
    • Para 4:细节段 2(按维度/时间/地点分组,包含具体数据)
  5. 风格警示:❌ 不要用"interesting、remarkable、demonstrate"这些评价词 / ❌ 不要堆砌复杂句 / ✅ 用简洁陈述和客观数据

例子(柱图对比):

题目:驾驶证持有率(1950年 vs 今天)
关键变化:
1. 男性持有率始终高于女性,但差距缩小
2. 年轻驾驶者(17-20岁)整体下降

段落建议(标准 Task 1 结构):
Para 1: 开场(简单改写题目,约1-2句)
Para 2: 总览段(Overview)— 描述整体趋势,不涉及具体数据
Para 3: 细节段 1 — 全体驾驶人口的时间演变(具体数据)
Para 4: 细节段 2 — 年轻驾驶者的变化(另一个维度)

Step 3A — Task 1 评分(若用户提供了作文)

评分权重(官方标准):

  1. TR(写作任务完成情况) — 最重要

    • 有没有充分回应题目?
    • 有没有清晰呈现关键信息?
    • 数据筛选(只选主要数据)是否合理?
  2. CC(连贯与衔接) — 次重要

    • 信息组织逻辑清晰吗?
    • 段落分段合理吗?
    • 衔接词使用恰当吗?
  3. LR(词汇丰富程度) — 同等

    • 用词准确 > 词汇高级
    • 基本词汇无误 ✅ > 高级词汇出错 ❌
    • 体现"恰当表达"而非"展示词汇"
  4. GRA(语法多样性及准确性) — 同等

    • 简单句正确 ✅ > 复杂句生硬 ❌
    • 大多数句子无误即可
    • 不需要追求复杂结构

官方 Task 1 评分标准对照表:

分数 TR(任务完成) CC(衔接) LR(词汇) GRA(语法)
9 ✅ 完全满足所有要求;充分展开内容 ✅ 衔接自如;行文连贯 ✅ 丰富的词汇特征;极少微错 ✅ 丰富多样语法;极少微错
8 ✅ 充分满足要求;清晰呈现主要信息 ✅ 衔接恰当;各段分明 ✅ 常用词汇准确;偶尔微错 ✅ 多样语法结构;大多正确
7 ✅ 覆盖要求;清晰呈现主趋势/对比 ✅ 衔接恰当;段落分段合理 ✅ 常用词汇恰当;偶尔错误 ✅ 能用多种结构;偶有错误
6 ⚠️ 覆盖部分要求;部分信息呈现不够清晰 ⚠️ 衔接词存在但偶有错误;段落分段不够 ⚠️ 基本词汇够用;有重复或不恰当 ⚠️ 简单复杂句混用;有语法错
5 ❌ 覆盖部分要求;大部分信息呈现不清晰 ❌ 不能有逻辑地组织信息 ❌ 词汇极有限;大量重复 ❌ 基本无法造复杂句

Read the full file on GitHub · 458 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 458 lines · 81 tokens per session scan A 769d50343fa3

Subscribe to this mod's changes

ielts-writing is a skill published in the GitHub repository Evianyeung1204/ielts-assitant (42 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 5,869 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

lean-formalize

Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…

wanshuiyin/Auto-claude-code-research-in-sleep · 81 tokens

exam-forecast

Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.

anthropics/claude-for-legal · 73 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens