Automated summary
Generates multiple-choice quiz questions based on the current conversation context to test understanding.
Strengths
- Questions tailored to discussed content
- Plausible distractors with detailed explanations
- JSON export for external quiz runner
Limitations
- Requires sufficiently rich conversation content
- User must run an external script for interactive quiz
- Only supports single-answer questions
Use after a work session to verify key concepts are understood.
Avoid if the conversation lacks enough technical or factual substance to generate meaningful questions.
Security analysis
SafeThe skill only uses Bash to retrieve a timestamp with 'date +%s', writes a JSON question file to /tmp, and instructs the user to run a separate external Python script manually. It does not execute or modify its own code, access sensitive files, or transmit data. No risk of command injection or destructive actions.
No concerns found
How this analysis is madeExamples
Create a 5-question multiple choice quiz about the Docker concepts we discussed in this conversation.Based on our conversation about Kubernetes networking, generate 3 quiz questions to test my understanding.name: quiz description: Generates multiple choice quiz questions based on current conversation context. Use when testing understanding, reviewing what was discussed, or wanting a knowledge check on the session. allowed-tools: Bash(date *), Read, Write
Conversation Quiz
Generate multiple choice questions testing understanding of the current conversation.
Instructions
-
Analyze the conversation context for quizzable content:
- Technical concepts discussed
- Decisions made
- Code patterns or implementations
- Key facts or configurations
-
Generate 3-10 questions with 4 options each (default 5, or as many as the user/arguments request)
-
Question Quality Guidelines
- Questions should test understanding, not memorization of exact wording
- Include plausible distractors (wrong answers that could seem right)
- Vary difficulty: mix straightforward recall with deeper comprehension
- Descriptions should explain WHY the option is correct/incorrect (shown only after answering)
- If conversation lacks substance for 3 questions, generate what's reasonable and note the limitation
-
Write questions to file and launch external quiz runner:
- Generate a unix timestamp:
date +%svia Bash - Write questions JSON to
/tmp/quiz_questions_$TIMESTAMP.jsonusing the format below - Tell the user to run in a separate terminal:
python3 ~/.claude/skills/quiz/quiz.py /tmp/quiz_questions_$TIMESTAMP.json - The quiz runner writes results to
/tmp/quiz_results_$TIMESTAMP.json(same timestamp, auto-derived from questions filename) - Wait for user to report back that they finished
- Read results from
/tmp/quiz_results_$TIMESTAMP.json - Provide feedback: celebrate correct answers, explain wrong ones with the description from the correct option
- Generate a unix timestamp:
Questions JSON Format
[
{
"question": "What network mode allows containers to share the host's network namespace?",
"options": [
{"label": "bridge", "correct": false, "description": "Bridge creates an isolated network — containers get their own namespace"},
{"label": "host", "correct": true, "description": "Host mode removes network isolation — container shares the host's network stack"},
{"label": "overlay", "correct": false, "description": "Overlay enables multi-host networking, but still uses separate namespaces"},
{"label": "macvlan", "correct": false, "description": "Macvlan assigns a MAC address to the container — separate namespace with direct network access"}
]
}
]
Important
- Each question MUST have exactly ONE option with
"correct": true - The
descriptionfield is NOT shown during the quiz — only used for post-quiz feedback - Options are shuffled automatically by the quiz runner — no need to randomize in the JSON
- The quiz runner handles: display, input, timing, scoring, and writes results to file
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/conversation-quiz-generator-mm5t8ali/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/conversation-quiz-generator-mm5t8ali' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/conversation-quiz-generator-mm5t8ali/download' --output '.skill-downloads/conversation-quiz-generator-mm5t8ali/SKILL.md.part' && mv '.skill-downloads/conversation-quiz-generator-mm5t8ali/SKILL.md.part' '.skill-downloads/conversation-quiz-generator-mm5t8ali/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Bash(date *), Read, Write
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/conversation-quiz-generator-mm5t8ali/SKILL.md' && test -s '.skill-downloads/conversation-quiz-generator-mm5t8ali/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/quiz' && cp -R '.skill-downloads/conversation-quiz-generator-mm5t8ali' '.claude/skills/quiz'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/conversation-quiz-generator-mm5t8ali'openskills read 'conversation-quiz-generator-mm5t8ali'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/conversation-quiz-generator-mm5t8ali/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.