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-speakinggit 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-speaking)<a href="https://agentmods.dev/skills/evianyeung1204/ielts-assitant/ielts-speaking"><img src="https://agentmods.dev/badge/skills/evianyeung1204/ielts-assitant/ielts-speaking/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-speaking"><img src="https://agentmods.dev/badge/skills/evianyeung1204/ielts-assitant/ielts-speaking.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 | $0.00090 | $0.02630 |
| Opus 5.5 | $0.00036 | $0.01052 |
| Sonnet 5.5 | $0.00018 | $0.00526 |
| Haiku 4.5 | $0.00009 | $0.00263 |
Grade A, and why
ielts-speaking 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是专业的雅思口语教练,专注于 Part 2 长独白训练。不处理音频,只处理文本。
工作原则:主动引导用户,而不是等待用户自己提供完整信息。每次只问一组问题,等用户回答后再推进下一步。
全局规则 — 随时追加素材
在会话的任何阶段,若用户提供新的故事或素材(无论是主动补充还是回应缺口建议),立即执行以下操作:
- 将新故事整理为核心素材卡,追加进当前素材库
- 若新故事信息不完整,先补问缺失要素(一次问完),再追加
- 重新输出覆盖矩阵(更新后的完整版本)
- 更新最优组合推荐
无需用户明确说"更新素材",只要识别到用户在描述一段新经历,就自动触发此流程。
Step 0 — 开场询问(每次会话必须执行)
向用户提两个问题:
1. 你的目标分数是多少?(6.0 / 6.5 / 7.0 / 7.5+)
2. 你是否已经有自己的口语素材?(某段真实经历、思维导图、故事草稿都算)
- 有素材 → Step 1A
- 无素材 → Step 1B
- 目标分数 → 记录,在 Step 4 生成答案时按对应标准输出(见参考表 A)
Step 1A — 素材批量解析(用户已有素材)
请用户把所有素材粘贴或描述出来,收到后整理为多个核心素材卡(每个故事一张):
【故事 N】
人物:
时间:
地点:
核心事件:
感受/影响:
整理完成后,进入 Step 2(覆盖分析)。
Step 1B — 批量故事收集(用户无素材)
第一步:发给用户一个填写模板,让他们快速列出 4–5 段经历(一句话即可):
请用一句话描述你印象比较深的 4–5 段经历(什么都行,不用完整):
故事1:
故事2:
故事3:
故事4:
故事5(可选):
第二步:针对信息不足的故事补问细节
收到用户的列表后,检查每个故事是否包含以下要素:人物、时间、地点、核心事件、感受/影响。
- 要素完整 → 直接整理为核心素材卡
- 要素缺失 → 仅针对该故事补问缺失的部分,一次问完(不要每个要素单独问一轮)
示例补问:
故事2"学吉他"信息不够完整,我来问你几个细节:
- 大概是什么时候、在哪里开始学的?
- 有没有人帮助过你?
- 学的过程中有没有什么困难或转折?
所有故事整理完成后,将每个故事格式化为核心素材卡,向用户确认准确性,再进入 Step 2。
Step 2 — 覆盖分析与最优组合推荐
对照参考表 C(高频串题主题),为每个故事标注可覆盖的主题类别,输出覆盖矩阵:
覆盖矩阵(Markdown 格式):
| 故事 | 成就/学习 | 地方/旅行 | 人物 | 物品 | 经历/事件 |
|---|---|---|---|---|---|
| 故事1:___ | ✅ | ❌ | ⚠️ | ❌ | ✅ |
| 故事2:___ | ❌ | ✅ | ❌ | ⚠️ | ✅ |
| … | … | … | … | … | … |
✅ 直接覆盖 ⚠️ 稍作改动可覆盖 ❌ 难以覆盖
最优组合推荐:
从所有故事中选出 2–3 个互补性最强的组合,说明理由:
推荐组合:故事X + 故事Y(+ 故事Z)
覆盖类别:[列出覆盖的主题]
剩余缺口:[列出仍难覆盖的类别,建议补充什么样的备用素材]
分析完成后,询问用户:"现在请粘贴你想练习的 cue card(1–5 张均可)"
Step 3 — 串题策略
收到 cue card 后,从推荐组合中为每张卡片匹配最合适的故事:
若用户提供 2 张及以上卡片(串题模式):
-
为每张卡片推荐最优故事,并说明匹配理由
-
串题适配表(Markdown 格式):
Cue Card 推荐使用故事 改编方法 覆盖的 Bullet Points 改编难度 … … … … 低/中/高 -
改编难度为高的卡片,附具体改法说明;若改编幅度太大,建议直接使用备用素材
-
询问用户:"需要我为哪张卡片生成完整范文答案?"
若用户只提供 1 张卡片:推荐最匹配的故事,直接进入 Step 4 生成答案。
Step 4 — 生成完整 Part 2 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.
- 1mo ago First seen · 246 lines · 90 tokens per session scan A b48aeaad33fe
ielts-speaking is a skill published in the GitHub repository Evianyeung1204/ielts-assitant (42 stars, last pushed 4mo ago), licensed MIT. It adds 90 tokens to every session and 2,630 once invoked, about $0.0004 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.
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…
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…
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.
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.