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-quizgit 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-quiz)<a href="https://agentmods.dev/skills/zekainie/universal-examprep-skill/exam-quiz"><img src="https://agentmods.dev/badge/skills/zekainie/universal-examprep-skill/exam-quiz/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-quiz"><img src="https://agentmods.dev/badge/skills/zekainie/universal-examprep-skill/exam-quiz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 33 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00076 | $0.01830 |
| Opus 5 | $0.00038 | $0.00915 |
| Sonnet 5 | $0.00015 | $0.00366 |
| Haiku 4.5 | $0.00008 | $0.00183 |
Grade B, and why
exam-quiz scanned grade B with 1 finding 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
2. **Show prompt assets first (fail-closed).** For `requires_assets=true` or `maybe_requires_assets=true`, before asking, explaining, hinting, or solving, actually render every question-side `question_context` / `figure` How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
exam-quiz — question drilling and grading
Purpose
Present one chapter/phase-scoped bank item at a time, grade against its stored answer, archive wrong/skipped items through state, and return control to exam-cram. Never invent a question or answer.
Activation
Use after teaching when a checkpoint is needed, or when the student asks for drills or a mock exam.
Inputs
- Existing
references/quiz_bank.json, whose items havetype, answer/provenance fields, andchapterorphase; subjective items also havekeywords. - Current chapter/phase and
study_state.jsonmastery/scope. An untagged item cannot enter a chapter checkpoint. - Optional
difficulty(1–5) anddifficulty_reasonfromscore_difficulty.py: a structural lower bound, never semantic truth or a per-student score.
Workflow
-
Select only eligible bank items. Filter both
chapterandphase. A missing bank is an incomplete workspace and returns toexam-ingest; an existing but empty usable pool produces no substitute and caps completion atcovered_unverified.The default source pool is mixed. Persist a student restriction and select it with
scripts/select_questions.py; exclude and count items lackingsource_type. Before any one-turn exception say 「⚠️ 临时覆盖你的 范围偏好」 or⚠️ Temporarily overriding your <scope> scope preference; do not silently change the stored scope.For targeted/checkpoint selection run
python "${CLAUDE_SKILL_DIR}/scripts/select_hard_questions.py" --workspace <ws> --chapter <current> -n <k>.--chapteris the only exact chapter filter;--from-chapter Nmeans every numeric chapter ≥N and is only forshore_up, never a checkpoint. Explicit cross-chapter practice may omit chapter. The selector combines structural difficulty (usingscore_difficulty.pyon the fly when needed) with mistake/confusion/window mastery, mode, and stored scope.fill_gapsserves weak points先易后难, then mastered items先难挑战;from_scratchis globally先易后难.shore_uprequires explicit chapter/from-chapter. Ordering is deterministic, not LLM ranking.
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 · 67 lines · 76 tokens per session scan B 2acf5c9921ea
exam-quiz is a skill published in the GitHub repository ZeKaiNie/universal-examprep-skill (281 stars, last pushed 9d ago), licensed MIT. It adds 76 tokens to every session and 1,830 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). 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.