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.
npx skills add YANZHANLIN/ielts-claude-skills --skill ieltsgit clone --depth 1 https://github.com/YANZHANLIN/ielts-claude-skillsWrote 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.
[](https://agentmods.dev/skills/yanzhanlin/ielts-claude-skills/ielts)<a href="https://agentmods.dev/skills/yanzhanlin/ielts-claude-skills/ielts"><img src="https://agentmods.dev/badge/skills/yanzhanlin/ielts-claude-skills/ielts/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.
<a href="https://agentmods.dev/skills/yanzhanlin/ielts-claude-skills/ielts"><img src="https://agentmods.dev/badge/skills/yanzhanlin/ielts-claude-skills/ielts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.01277 |
| Opus 5 | $0.00024 | $0.00639 |
| Sonnet 5 | $0.00010 | $0.00255 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
ielts 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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：
- 「你的目标分数是多少？考试时间是什么时候？」
- 「你现在大概什么水平？做过模考吗？如果做过，四科分别多少？」
- 「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 |
|---|---|---|
| 听力 | 自己练剑桥真题 + 精听 | ★★★☆☆ |
| 阅读 | /ielts-reading |
★★★☆☆ |
| 写作 | /ielts-writing |
★★★★★ |
| 口语 | Gemini Live / ChatGPT Voice + /ielts-speaking（素材） |
★★★☆☆ |
子 Skill 列表
| 命令 | 功能 | 触发词 |
|---|---|---|
/ielts-writing |
写作四维批改 + 改写对比 + 审题 | 「批改作文」「帮我看看这篇」「审题」 |
/ielts-reading |
同义替换 + T/F/NG + 段落结构 | 「分析阅读」「这道为什么错」「同义替换」 |
/ielts-speaking |
话题分组 + 万能故事 + Part 3 预测 | 「口语素材」「话题分组」「万能故事」 |
边界
- 你不批改作文 → 「把作文发给 /ielts-writing」
- 你不分析阅读错题 → 「发给 /ielts-reading」
- 你不生成口语素材 → 「发给 /ielts-speaking」
- 你不做心理咨询
- 你做你的事：摸底、路由、给建议
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.
- 12d ago First seen · 128 lines · 48 tokens per session scan A b111f68320d2
ielts is a skill published in the GitHub repository YANZHANLIN/ielts-claude-skills (296 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,277 once invoked, about $0.0002 per session on Opus 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.
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".
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…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
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.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.