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 wpsnote/wpsnote-skills --skill note-review-coachgit clone --depth 1 https://github.com/wpsnote/wpsnote-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/wpsnote/wpsnote-skills/note-review-coach)<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/note-review-coach"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/note-review-coach/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/wpsnote/wpsnote-skills/note-review-coach"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/note-review-coach.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 | $0.00087 | $0.02072 |
| Opus 5.5 | $0.00035 | $0.00829 |
| Sonnet 5.5 | $0.00017 | $0.00414 |
| Haiku 4.5 | $0.00009 | $0.00207 |
Grade A, and why
note-review-coach 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.
What it actually says
Note Review Coach
设计原则
这个 skill 只负责让复习闭环更可靠,不负责替模型套题型。默认保持高自由度:先读笔记和用户意图,再自然决定出什么题。
硬约束只用于防止明显失败:
- 不读材料就出题。
- 把“笔记回忆”误标成阅读、翻译、写作等能力训练。
- 自测题提前泄露答案。
- 题卷内部不自洽,例如题目规则、材料、选项、答案空间互相冲突。
- 批改不回到笔记证据。
不要为了满足本文件而牺牲自然判断。好的输出可以像一套真实模拟卷,也可以像逐题教练,取决于用户目标和笔记内容。
工作方式
1. 读材料
先确定复习范围,再读取材料。
- 当前笔记或用户引用的笔记优先。
- 范围不清、候选过多、或需要用户选择时,用
ask_user。 - 小文档可直接
read_note;大文档先get_note_outline,再读相关章节。
读取时区分两类信息:
- 可练内容:原文、段落、概念、例子、词库、题目要求、评分标准、流程、案例、错题、结论。
- 设计线索:考试分值、题型名称、单元编号、passage 编号、材料来源、目录、页码、老师提示。
两类都重要,但用途不同。设计线索可以帮助构造题卷;是否直接考它,取决于本轮复习契约。
2. 判断复习契约
在心里先判断用户到底要什么;只有不清楚且会显著影响输出时才问。
常见契约:
- 笔记回忆:目标是记住笔记本身、考试范围、分值、题源、关键事实。
- 概念掌握:目标是理解笔记中的概念、关系、边界、例子。
- 能力训练:目标是练某种真实任务,需要给用户可操作的材料、情境或输出要求。
- 考试/任务模拟:目标是贴近真实题型,形成一套可作答的模拟测试。
- 混合诊断:少量范围回忆 + 主要理解/能力题,用来发现薄弱点。
如果笔记同时包含范围清单和可练材料,而用户只说“复习/考考我”,可以用 ask_user:
A. 笔记回忆:考范围、结构、关键事实和易忘点
B. 能力训练:按笔记材料练阅读、翻译、写作、推理、应用或输出
C. 混合诊断:少量范围回忆 + 主要理解/能力题,答完批改
用户已经明确要“模拟卷”“按真实考试来”“练翻译/阅读/写作”等,不要再追问,直接按该契约生成。
3. 生成题目
题型由契约和材料自然决定,不要先套模板。
- 笔记回忆:可以考目录、分值、范围、题源、关键事实,但要标成范围/结构回忆。
- 概念掌握:多用解释、比较、辨析、例子、反例、短答。
- 能力训练:必须给可操作的任务载体和明确输出要求。
- 考试/任务模拟:尽量复现真实输入、题型说明、作答约束和评分关注点;材料不足时可以生成模拟材料,但必须标注“模拟/改写/基于笔记生成”。
- 混合诊断:允许少量范围回忆,但主体应检查理解、推理、输出和迁移。
完整试卷预览可以用普通文本呈现选择题选项。逐题交互作答时,选择题优先用 ask_user 收集答案;如果当前是在生成整套预览,不要因为 ask_user 打断试卷结构。
题型参考只在需要自检或用户指定复杂题型时读取:references/question-types.md。不要读完 reference 后机械套用。
4. 输出前自检
输出前做一次快速质量闸门:
- 契约一致:题目标签和题干一致。标成阅读/翻译/写作/应用的题,不能只问来源、分值、单元名。
- 来源清楚:哪些来自笔记原文,哪些是基于笔记生成的模拟材料,要说清。
- 题卷自洽:题量、材料、选项、作答规则和答案空间一致。
- 自测不泄题:用户要“考我/自测”时,先不给答案、解析、评分点;用户明确要答案版或试卷预览带答案时才给。
- 材料足够:能力训练必须有可操作的材料、情境或输出约束。材料不足时请求补充,或明确降级为基于笔记的有限练习。
5. 批改和总结
用户作答后,按题号批改。必要时回读笔记,不要只依赖隐藏答案。
每题批改应包含:
- 判定:正确 / 部分正确 / 错误 / 未作答。
- 依据:来自哪篇笔记、章节、block 或题目材料。
- 缺口:漏了什么概念、证据、条件、步骤或表达要求。
- 修正答案:给出精简可学的版本。
总结时输出掌握情况、错因地图、建议重读位置和下一轮练习方向。
写入复习记录
默认不改原笔记。只有用户明确要求保存,或通过 ask_user 确认后,才创建新笔记。
推荐标题:
复习记录 - <原笔记标题或主题> - <日期>
保存后可添加 复习 标签;用户要求同步时调用 sync_note。
What ships with it
1 file 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.
- 1mo ago First seen · 148 lines · 87 tokens per session scan A 854b8b8b7731
note-review-coach is a skill published in the GitHub repository wpsnote/wpsnote-skills (183 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 2,072 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.
Other skills, from other repositories
promentor
A tool that turns a software project into a hands-on course in the style of an MIT course. It can produce lessons, code walkthroughs, practical labs, behavior tests, grading, explanations, and AI reviews.
learn
Learn a source together with the user and record only what they understood as a new page in this Scraps wiki. Explains the source with a diagram anchored on the pages the wiki already has, checks comprehension with questions, then writes one page from the points that passed; when understanding is not reached, nothing…
teach-zh
A teaching workflow for helping a user learn a subject over multiple sessions. It stores the learner’s goals, reference material, lessons, notes, and learning records in the current workspace.
quantum-error-correction
A clear and practical skill guide for learning and running a PennyLane-based qLDPC tutorial, from classical LDPC basics to CSS and Hypergraph Product code construction. Skill-first for covered code generation, runnable examples, execution, debugging, validation, and fixed workflows.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
growth-log
Use after a complex task, failure, or when reviewing what was learned. Teaches how to write growth logs that extract reusable patterns — not diary entries.