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 engit 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/en)<a href="https://agentmods.dev/skills/zekainie/universal-examprep-skill/en"><img src="https://agentmods.dev/badge/skills/zekainie/universal-examprep-skill/en/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/en"><img src="https://agentmods.dev/badge/skills/zekainie/universal-examprep-skill/en.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 findings, up to medium
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 →
- medium Agent Snooping · line 3 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 7 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 7 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 7 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 7 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 7 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 7 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 7 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 7 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 7 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00000 | $0.01242 |
| Opus 5 | $0.00000 | $0.00621 |
| Sonnet 5 | $0.00000 | $0.00248 |
| Haiku 4.5 | $0.00000 | $0.00124 |
Grade A, and why
en 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 9d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal Exam Cram Coach — English Compatibility Entry
This is a compact compatibility entry, not a second workflow manual. The behavioral source of truth is skills/exam-cram/SKILL.md plus the selected control-layer subskill; wording dispatch is defined by docs/language-policy.md.
Dispatch
Load the orchestrator, then exactly one needed subskill: exam-ingest, exam-tutor, exam-study-guide, exam-quiz, exam-review, exam-cheatsheet, exam-audit, exam-help, or confusion-tracker. Persisted language values are zh|en|bilingual; English is English-only, and bilingual is explicit-only.
Compatibility safety pins
- Before local work, run
update_progress.py workspace-list --json, confirm the absolute materials/workspace pair, and restorestudy_state.jsonfirst. It is progress truth;study_progress.mdis generated. If state is absent and Python works, runupdate_progress.py --workspace <ws> initbeforeset,set-check, or other writes. Never use the repository/cwd as the workspace. - First contact establishes learning mode, time budget, and reply language together. Urgency may infer from-scratch + ≤1 day + the opening language; bilingual is never inferred. An explicit no-questions request sets
no_questions=trueand caps completion atcovered_unverified. - Choose material processing separately at startup. Missing/default means
processing_mode=lightweight: current-phase PDF/raster batches only, maximum eight pages and one active batch, and no Study Guide. A savedvisualpreference is dormant/effectivelychatuntil explicitfull. Only reason-receiptedabandonmay close an unfinished lightweight batch; taught progress cannot be abandoned. - Quiz and grading use only
references/quiz_bank.json. Useselect_questions.pynormally andselect_hard_questions.py --chapter <current>for a checkpoint. In a restricted pool, exclude/count untagged items; before a one-turn override say: ⚠️ Temporarily overriding your scope preference. - For
requires_assets=trueormaybe_requires_assets=true, render every Question-side asset. Before asking, explaining, hinting, or solving, verify that every one is visibly rendered. A path is not an image. Show an Answer-side asset only later; if rendering fails, skip the item. Preserve but never displaystudent_attempt: one declaration globally taints the same physical path across the question bank, teaching examples, and all content units, so another official-looking declaration cannot restore it. Useshow_question_assets.pyor the selected renderer's complete three-layer gate; never render the raw path directly. Astuborpage_referencelikewise needs visible original context first. - Persist substantive work through
notebook.py; report a failed write and provide the full content in chat. Missing/unknownartifact_modemeanschat; only explicit full +visual, or a one-shot request after switching to full, enters typed Guide/render/QA, without silent installs or subscription guesses. - At full-v2 Guide entry, first perform a host-capability handshake. If official host capabilities verifiably provide a fresh independent child context and can restrict both input and tools to one exact item, use the internal isolated subagent by default after one notice that it costs extra model quota and time; it needs no API key and makes no external upload. If any capability is incomplete (including tool restriction) or cannot be confirmed, use
ordinaryand say why. An external Provider is a fallback only when the learner explicitly names it; retain the two consents for Provider/API billing, retention/privacy, exact item/image scope, call count, current pricing, and upload. preferences.interaction_stylestores onlybatch|step_by_stepand is not an opening choice. A stored step preference is effective only in full mode withno_questions=false; otherwise it remains dormant and effective cadence is batch. Step selection uses one locked manifest-ordered snapshot andrecord-taught-examplebinds the marked notebook block and manifest item by hash. Teaching IDs use the shared 1–200-character Guide-safe Unicode contract. Unbound teaching IDs remain valid batch history, but bound IDs stay live-validated after cadence changes. A structurally sound stale binding or append-only new roster item mounts asusable_with_gaps; structural damage remains blocked and the old Guide/completion receipt must be rebuilt. Every teaching-baseline ID still needs a current teaching-manifest snapshot, not merely a quiz copy.
What ships with it
12 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.
- messages.json 1.3 KB
- skills/confusion-tracker.md 1.4 KB
- skills/exam-cheatsheet.md 1.2 KB
- skills/exam-cram.md 3.2 KB
- skills/exam-help.md 4.7 KB
- skills/exam-ingest.md 1.3 KB
- skills/exam-quiz.md 1.4 KB
- skills/exam-review.md 1.3 KB
- skills/exam-tutor.md 2.3 KB
- templates/quiz_bank_template.json 1.9 KB
- templates/study_plan_template.md 368 B
- templates/study_progress_template.md 1010 B
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.
- 9d ago First seen · 30 lines · 0 tokens per session scan A 79779ade9d6a
en is a skill published in the GitHub repository ZeKaiNie/universal-examprep-skill (281 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,242 tokens. 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.