Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Jobo16/ielts-buddynpx agentmods add skills/jobo16/ielts-buddy/ielts-listening-reviewWrote 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/jobo16/ielts-buddy/ielts-listening-review)<a href="https://agentmods.dev/skills/jobo16/ielts-buddy/ielts-listening-review"><img src="https://agentmods.dev/badge/skills/jobo16/ielts-buddy/ielts-listening-review/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/jobo16/ielts-buddy/ielts-listening-review"><img src="https://agentmods.dev/badge/skills/jobo16/ielts-buddy/ielts-listening-review.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 | $0.00037 | $0.00974 |
| Opus 5 | $0.00018 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
ielts-listening-review 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 2d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IELTS Buddy 听力结果接口
本 Skill 只说明已提交练习数据的读取方式。需要账号数据时，先按Agent API 配置绑定并检查能力。
接口
| 能力 | 数据 | 调用约束 |
|---|---|---|
ielts_review_read_snapshot |
已提交 session 的题目编号、题型、题干、用户作答、答案 key 与可选材料快照 | 只读取当前账号已提交的 session；仅需要原始材料时传 includeMaterial:true。 |
ielts_review_recent_activity |
已提交普通练习和已完成模考科目的摘要及复盘引用 | 先查列表，再将返回的 reviewTarget 作为详情工具的 target。 |
ielts_practice_read_session |
session 状态和浏览器入口 | 仅需核实未提交普通练习时使用。 |
ielts_dictation_search_materials |
可逐句精听的听力素材、分组标签、句段数和计划 contentRef |
只读目录；不会创建精听运行或打开页面。 |
python3 scripts/ielts_buddy_api.py capabilities
python3 scripts/ielts_buddy_api.py call ielts_review_read_snapshot --json '{"target":{"kind":"practice","sessionId":123},"scope":"incorrect","includeMaterial":false}'
边界
- 服务端返回事实数据，不定位证据、不判断错因、不生成训练建议。
- 正式作答、播放和提交在浏览器练习页完成。
workflows/是独立的可选推荐层，不属于本 Skill 的接口契约。
列表与详情
查询学习记录分两步：先读取列表摘要，再按需用返回的 reviewTarget 调用 ielts_review_read_snapshot 查看某次练习或某个已完成模考科目的详情；精听使用 attemptId 调用 ielts_dictation_read_attempt，未提交普通练习使用 sessionId 调用 ielts_practice_read_session。不要为了列出记录逐条展开详情。使用前以当前账号的 capabilities 为准。
列表中的 sessionId 是练习次数，partId 是不同篇目；区分零作答、已作答未提交和已提交，不从部分题目的正确率推算 IELTS 分数。需要完整记录时按 nextOffset、nextCursor 或 nextPage 翻页，直到 hasMore=false；空页有后续游标时仍需继续。observationTruncated=true 或 coverage.sourceTruncated=true 表示数据仍不完整，不得声称查全。计划列表只含摘要，用 planId 调用 ielts_study_plans_get 获取任务页。
足迹与学习统计
跨产品活动使用 ielts_footprints_list。直接读取服务端 summary、dailyCounts、todayCounts 和 total；activities 只是本页，不能用它的长度或日期分布重算历史总量、热力图、连续天数及本周次数。只查询统计时无需拉完时间线。
足迹优先将 nextCursor 原样作为下一次请求的 cursor，保持 kinds/query/timeRange 不变。统计范围是 statisticsScope=filtered_history，时区是 Asia/Shanghai，每日计数覆盖截至 asOf 所在日的 28 天。同章节同日的视频进度折叠为一次展示活动，原始事件保留。
ielts_learning_pull_events 同步的是原始学习证据，数字 cursor 与足迹的字符串 cursor 不可互换，两者条数也不应直接比较。网页未显示记录时，先核对分页和覆盖范围，不用 ielts_learning_push_events 补写已经存在的事实。返回缺失字段或 coverage.sourceTruncated=true 时保持“不完整”的结论，以当前部署的足迹接口文档为准。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +8 lines 54ad88b5c89f
- 3d ago Changed · +7 lines 90c48f028edc
- 12d ago First seen · 28 lines · 37 tokens per session scan A 1b519e743b5a
ielts-listening-review is a skill published in the GitHub repository Jobo16/ielts-buddy (21 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 974 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
ielts-speaking-coach
Run repeatable IELTS speaking practice with ChatGPT Voice or a supported voice conversation. Use when a learner wants to import IELTS Speaking questions, choose Part 1, Part 2, Part 3, or a full mock test, create a 7-day, 14-day, or 30-day practice plan, conduct examiner-style practice, generate a fixed-format…
google-agents-cli-onboarding
Onboarding entrypoint for agents-cli in Agent Platform. It should be used when the user wants to "create a new agent", "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "evaluate an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs…
edu-math-tutorial
A Chinese-language guide for turning a maths problem into a step-by-step teaching video. It explains how to break down the solution, write narration, format equations, and structure scenes.
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
rust-learner
Learn Rust language features and crate updates. Use when user asks about Rust version changelog, what's new in Rust, crate updates, Cargo.toml dependencies, tokio/serde/axum features, or any Rust ecosystem questions.
81-pipecat
Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter.