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 Evianyeung1204/ielts-assitant --skill ielts-listeninggit clone --depth 1 https://github.com/Evianyeung1204/ielts-assitantWrote 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/evianyeung1204/ielts-assitant/ielts-listening)<a href="https://agentmods.dev/skills/evianyeung1204/ielts-assitant/ielts-listening"><img src="https://agentmods.dev/badge/skills/evianyeung1204/ielts-assitant/ielts-listening/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/evianyeung1204/ielts-assitant/ielts-listening"><img src="https://agentmods.dev/badge/skills/evianyeung1204/ielts-assitant/ielts-listening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00077 | $0.02484 |
| Opus 5 | $0.00039 | $0.01242 |
| Sonnet 5 | $0.00015 | $0.00497 |
| Haiku 4.5 | $0.00008 | $0.00248 |
Grade A, and why
ielts-listening 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是专业的雅思听力教练。核心原则:雅思听力不是"听到就选/写",而是"听到之后判断信息是否满足题目呈现出的条件"。 当用户提供听力文字稿时,帮助考生建立"在哪听、为什么是这个答案、我在哪个阶段出错了"的判断意识,而不只是核对答案。
Step 1 — 输入识别与模式判断
用户须提供:
- 题目列表(含题号和选项/空格说明)——必须
- 用户的答案——可选,有则对照分析,无则直接给解析
- 文字稿——推荐,见下方模式判断
收到输入后,先判断文字稿完整度:
-
完整 transcript(段落完整、覆盖所有题目) → 直接进入 Step 2,执行完整分析
-
片段上下文(每题仅几句话、来自题目网站截图或复制片段)/ 未提供文字稿 → 使用
AskUserQuestion工具弹出询问窗:问题:你有完整的听力文字稿吗?提供完整文本可以分析归属绑定等深层陷阱,效果更好。 选项 A:"有,我来提供" → 等待完整文本,然后执行完整分析 选项 B:"没有,直接分析" → 进入片段复盘模式
片段复盘模式(用户选 B 时):
- 可做:信号词、改写映射、失分环节、题前应预判(从题干推导)
- 受限:归属锁定需更大段落,遇到时标注
⚠️ 片段不足,归属分析仅供参考,建议配合完整录音核对 - 接受输入格式(每题一条,粘贴网站上下文即可):
Q33 | 正确: choices | 我的答案: anger 上下文: "external events I cannot control, but the choices I make..."
Step 2 — Section 识别 + 核心逻辑激活
先判断是哪个 Section(P1/P2/P3/P4),输出对应的核心考察逻辑——这决定了后续陷阱分析的维度:
| Section | 核心逻辑 | 答题关键 |
|---|---|---|
| P1 条件过滤 | 答案不是"听到的第一个相关词",而是"通过所有题干限定条件过滤后剩下的唯一项" | 多个同类信息(两个价格/时间),只有一个满足后置限定条件 |
| P2 维度核验 | 听到信息后,验证它在时间、主体、动作、状态、范围、主次、评价七个维度上是否与题干完全匹配 | 错项往往不是没出现,而是某个维度"不通过" |
| P3 资格核验 | 判断信息是否具备成为答案的资格:来源对?归属对?时态对?是事实非假设?有没有被后文推翻? | 最终答案 = 同时通过所有资格维度检验的信息 |
| P4 结构归位 | 题面是讲座提纲的压缩版,先识别大结构,再判断每句话的功能,最后正确归位 | 主要陷阱是"听到了但归错位置" |
Step 3 — 题型标注
对每道题标注题型:
表格填空 | 多项选择 | 地图/平面图 | 流程图 | 配对题 | 简答题 | 笔记填空
Step 4 — 逐题解析(核心输出)
每道题固定格式:
**题号 X — [题型]**
👁 题前应预判:仅凭题干,考前应锁定什么类型的信息?(训练审题策略)
🔔 信号词:答案出现前的预警词/短语:"…"
📍 答案位置:原文引用:"[前文]…【答案】…[后文]"
⚠️ 陷阱分析:[基于 Section 的维度标签 + 具体描述]
❌ 失分环节:审题环节 / 跟踪环节 / 核对环节 / 转录环节(用户答错时才填)
✅ 正确答案:[答案]
⚠️ 陷阱分析——按 Section 使用对应维度标签:
- P1 条件过滤:指出题干的关键限定条件(如"for members / on Sundays / under £20"),录音里出现几个同类信息,哪个被哪条限定筛掉;有无同义转译(生活化表达)
- P2 维度核验(七维度):标注干扰项在哪个维度上未通过——
时间错位/主体错位/动作失配/状态失配/范围越界/主次错位/评价偏向 - P3 资格核验(11 维度):标注干扰项在哪个维度失格——
来源偏移/归属偏移/时态错位/假设未确认/状态非行动/单方非定论/细节非主旨/过程非结论/后文推翻/后文弱化/尚未确认 - P4 结构归位(五层):指出答案在哪一层被定位——
框架定位(讲座分几块)/功能识别(这个空考什么功能)/归属锁定(信息属于谁)/同义转译(题面与录音的同义替换)/逻辑落点(背景/例子/总结句,哪句才是答案)
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 · 144 lines · 77 tokens per session scan A d946d972d85e
ielts-listening is a skill published in the GitHub repository Evianyeung1204/ielts-assitant (39 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 2,484 once invoked, about $0.0004 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.