Tutor
Design fair diagnostic and review quizzes with a zero-hint policy so agents or tutors actually measure what learners know.
Overview
tutor is a journey-wide agent skill that designs unbiased quizzes with a zero-hint policy—usable whenever a solo builder needs to assess knowledge without giving away answers in the prompt.
Install
npx skills add https://github.com/roundtable02/tutor-skills --skill tutorWhat is this skill?
- Zero-hint policy: option descriptions must not reveal correctness; no Recommended tags on answers
- Five question-type patterns: factual, conceptual, behavioral prediction, comparison, and debugging scenarios
- Difficulty recipes for diagnostic (40/40/20 easy/medium/hard), weak-area drill, and review modes
- Rules for rephrasing unresolved concepts without repeating identical questions
- Randomize correct answer position across items
- Five defined question-type categories
- Diagnostic difficulty split: 40% easy, 40% medium, 20% hard
Adoption & trust: 1.5k installs on skills.sh; 933 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent-generated quizzes telegraph correct answers in descriptions or question wording, so scores do not reflect real understanding.
Who is it for?
Builders authoring diagnostic quizzes, tutor agents, or course checks where integrity of assessment matters more than speed.
Skip if: Open-ended tutoring dialogue or copywriting marketing landing pages where no scored multiple-choice structure is needed.
When should I use this skill?
Designing or regenerating quizzes, diagnostics, weak-area drills, or review sets where questions must not reveal answers in options or stems.
What do I get? / Deliverables
You get a balanced question set with neutral options, varied difficulty, and rephrased drills on weak concepts that only knowledgeable users can pass.
- Quiz item set following zero-hint and difficulty recipes
- Rephrased drill questions targeting unresolved concepts
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Run an easy-heavy diagnostic before committing to a Cloud Run curriculum so gaps show up without answer leakage.
Generate module-end quizzes for an internal API course with randomized correct positions and neutral option blurbs.
Peer-review generated question banks against the zero-hint checklist before publishing onboarding docs.
Drill red-flag concepts from concept files with hard-weighted items rephrased in new scenarios.
How it compares
Methodology for writing quiz items, not a live LMS integration or flashcard app generator.
Common Questions / FAQ
Who is tutor for?
Solo creators and devs who use agents to generate quizzes for onboarding, certifications, or concept drills and need items that do not spoil the answer.
When should I use tutor?
While drafting training docs in Build, before validating team readiness in Validate, when refreshing support playbooks in Grow, or anytime you run diagnostic vs review quiz modes.
Is tutor safe to install?
Use the Security Audits panel on this Prism page and review SKILL.md in the repo; the skill is rule text without built-in network or shell access.
SKILL.md
READMESKILL.md - Tutor
# Quiz Design Rules ## Zero-Hint Policy (CRITICAL) Every question must be answerable ONLY by someone who actually knows the material. 1. **Option descriptions**: NEVER reveal correctness - BAD: `label: "stderr"`, `description: "Error output stream used by Cloud Run for error classification"` - GOOD: `label: "stderr"`, `description: "Standard error stream"` 2. **No "(Recommended)" tag** on any option 3. **Randomize** correct answer position — never always first or last 4. **Question phrasing**: Ask about behavior/purpose/output, don't hint at the answer - BAD: "Which error stream does error() use?" - GOOD: "Where does error() method output go?" 5. **Plausible distractors**: Wrong options must be real concepts from the domain, representing common misconceptions ## Question Types 1. **Factual recall**: "What HTTP status code is returned when...?" 2. **Conceptual understanding**: "Why does the system use X pattern?" 3. **Behavioral prediction**: "What happens when X fails?" 4. **Comparison/distinction**: "What is the difference between X and Y?" 5. **Debugging scenario**: "Given this error, what is the most likely cause?" ## Difficulty Balancing - Diagnostic: easy 40%, medium 40%, hard 20% - Weak-area drill: medium 30%, hard 70% - Review: all levels evenly ## Drilling Unresolved Concepts When targeting 🔴 concepts from concept files: - Do NOT repeat the exact same question — rephrase in a new context - Test the same underlying knowledge from a different angle - E.g., if user confused "400 vs 422", ask a scenario question where they must choose the correct status code for a new situation ## AskUserQuestion Format - 4 questions per round, 4 options each, single-select - Header: max 12 chars, "Q1. Topic" ## File Update Protocol After grading: 1. Update `concepts/{area}.md` — add/update concept rows + error notes 2. Update dashboard — recalculate area stats from concept files 3. Badges: 🟥 0-39% · 🟨 40-69% · 🟩 70-89% · 🟦 90-100% · ⬜ no data ## Language Rule All file content and output in the user's detected language. Badge emojis are universal. --- name: tutor description: > Interactive quiz tutor for Obsidian StudyVault learning. Use when the user wants to: (1) Take a diagnostic assessment of their knowledge, (2) Study or review specific sections/topics, (3) Drill weak areas identified in previous sessions, (4) Check their learning progress or dashboard, or says things like "quiz me", "test me", "let's study", "/tutor", "학습", "퀴즈", "평가". --- # Tutor Skill Quiz-based tutor that tracks what the user knows and doesn't know at the **concept level**. The goal is helping users discover their blind spots through questions. ## File Structure ``` StudyVault/ ├── *dashboard* ← Compact overview: proficiency table + stats └── concepts/ ├── {area-name}.md ← Per-area concept tracking (attempts, status, error notes) └── ... ``` - **Dashboard**: Only aggregated numbers. Links to concept files. Stays small forever. - **Concept files**: One per area. Tracks each concept with attempts, correct count, date, status, and error notes. Grows proportionally to unique concepts tested (bounded). ## Workflow ### Phase 0: Detect Language Detect user's language from their message → `{LANG}`. All output and file content in `{LANG}`. ### Phase 1: Discover Vault 1. Glob `**/StudyVault/` in project 2. List section directories 3. Glob `**/StudyVault/*dashboard*` to find dashboard 4. If found, read it. Preserve existing file path regardless of language. 5. If not found, create from template (see Dashboard Template below) If no StudyVault exists, inform user and stop. ### Phase 2: Ask Session Type **MANDATORY**: Use AskUserQuestion to let the user choose what to do. Analyze the dashboard to build context-aware options, then present them. Read the dashboard proficiency table and build options based on current state: 1. If unmeasured areas (⬜) exist → include "Diagnostic" option targ