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 ZeKaiNie/universal-examprep-skill --skill exam-reviewgit clone --depth 1 https://github.com/ZeKaiNie/universal-examprep-skillWrote 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/zekainie/universal-examprep-skill/exam-review)<a href="https://agentmods.dev/skills/zekainie/universal-examprep-skill/exam-review"><img src="https://agentmods.dev/badge/skills/zekainie/universal-examprep-skill/exam-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/zekainie/universal-examprep-skill/exam-review"><img src="https://agentmods.dev/badge/skills/zekainie/universal-examprep-skill/exam-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 | $0.00067 | $0.01103 |
| Opus 5 | $0.00034 | $0.00551 |
| Sonnet 5 | $0.00013 | $0.00221 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
exam-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 11d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
exam-review — mistake and confusion review
Purpose
Clear recorded mistakes/confusions before the exam. Replay only existing records; teach no new chapter and invent no question.
Activation
Use at final review or when the student explicitly asks to replay mistakes/find gaps.
Inputs
study_state.json'smistake_archiveandconfusion_logwhen state exists; otherwise generated 「❌ 错题档案」 and confusion compatibility rows.references/quiz_bank.json, used to fetch each recorded mistake by exact ID.
Workflow
-
Replay recorded mistakes. Reload state (or
update_progress.py show), fetch each exact bank item, and ask it again. Never add an unrecorded/bank-external question.For
requires_assets=trueormaybe_requires_assets=true, before asking, explaining, hinting, or solving, render every question-sidequestion_context/figure/diagram/tableasset, labelled题面图orQuestion-side asset. Only later may solution/review show答案图/Answer-side asset. A path is not an image. Preserve but never displaystudent_attempt; its physical path is tainted across the complete quiz, teaching, and content-unit layers, including duplicate official-looking declarations. Missing/unreadable or UI-unrenderable prompt assets cause a fail-closed skip;stub/page_referencealso require the original prompt page first. Usescripts/show_question_assets.pyfor every replay and treat a nonzero result as a skip; do not render a raw bank path directly. Seeexam-quizanddocs/file-format.md§4. -
Update mistakes. Correct replay →
已订正; still wrong → explain from the stored explanation and retain it. -
Replay confusions. Reload
confusion_log; ask the student to restate what/why/how. Correct restatement →已回顾; vague → explain once and retain待回顾. -
Persist the open list first. Compile unresolved mistakes plus
待回顾confusions for the final sprint/exam-cheatsheet. Pipe each conclusion/list topython "${CLAUDE_SKILL_DIR}/scripts/notebook.py" --workspace <ws> add-entry --chapter <ch> --type review --id <slug> --title <gist>; same IDs replace and rebuild the index. Then send a digest and language-pack notebook link. If writing fails, say so and give the full list in chat; file-less clients use chat/text breakpoints.
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.
- 11d ago First seen · 57 lines · 67 tokens per session scan A f37eb02764a1
exam-review is a skill published in the GitHub repository ZeKaiNie/universal-examprep-skill (281 stars, last pushed 9d ago), licensed MIT. It adds 67 tokens to every session and 1,103 once invoked, about $0.0003 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
bq-skill
A coaching workflow for building a reusable library of truthful stories for behavioral job interviews. It uses structures such as STAR—Situation, Task, Action, Result—and can connect stories to a job description and résumé.
PersonaLingo
A guided tool for creating personalised IELTS speaking practice materials. IELTS is an English exam, and the tool turns a learner’s answers and conversation into a personal profile and a static study website.
learning-mode
Guide active, hands-on learning without completing the chosen learning target for the learner. Use when the user explicitly wants to learn, practice, master, or build something themselves with guidance, especially when a technology or concept is new to them. Diagnose the smallest missing prerequisite, guide prediction…
html-effectiveness-research
A guide for explaining how a feature works in a code repository or how an abstract technical idea works. It can structure the explanation with a summary, expandable steps, code views, questions and answers, or an interactive visual.
teach
Use when the user wants to learn or be taught a topic interactively over multiple turns, with the agent acting as tutor rather than answer-giver. Triggers on phrases like "teach me", "tutor me", "quiz me", "let's learn", "help me understand X by working through it step by step", or any request framed around learning a…
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.