examples/typescript-langchain-quiz-agent/skills/quiz-generation/SKILL.md
--- id: quiz-generation-v1 name: quiz-generation version: 1.0.0 author: [email protected] tags: - quiz-generation - education - mcq-creation - assessment - langchain - openrouter input_modes: - text/plain - application/json output_modes: - text/plain - application/json --- # Quiz Generation Skill Educational assessment expert that generates high-quality multiple-choice quizzes from any provided text. Creates exactly 10 MCQs with 4 options each, correct answer identification,
npx skillsauth add getbindu/bindu quiz-generationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Educational assessment expert that generates high-quality multiple-choice quizzes from any provided text. Creates exactly 10 MCQs with 4 options each, correct answer identification, and concise explanations.
Each quiz follows this standardized structure:
# 📝 Quiz: Knowledge Check
---
### Question 1
[Question text here]
A) [Option A]
B) [Option B]
C) [Option C]
D) [Option D]
**Correct Answer:** [A/B/C/D]
**Explanation:** [Brief explanation]
---
(Repeat for questions 2 through 10)
| Metric | Value | |--------|-------| | Average response time | 3-8s (model dependent) | | Max concurrent requests | 5 | | Context window | Up to 128k tokens | | Questions per quiz | Exactly 10 |
This skill is used by the TypeScript LangChain Quiz Agent:
import { ChatOpenAI } from "@langchain/openai";
const llm = new ChatOpenAI({
model: "openai/gpt-oss-120b",
temperature: 0.3,
configuration: {
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
},
});
bindufy({
skills: ["skills/quiz-generation"],
}, async (messages) => {
const response = await llm.invoke([
{ role: "system", content: QUIZ_SYSTEM_PROMPT },
{ role: "user", content: userInput },
]);
return response.content;
});
quiz, test, assessment, questions, mcq, multiple-choice, generate, create, questions, knowledge, check, exam, evaluate
Avoid requests for:
development
--- id: question-answering-v1 name: question-answering version: 1.0.0 author: [email protected] tags: - question-answering - conversation - assistant - general-purpose - multi-model input_modes: - text/plain - application/json output_modes: - text/plain - application/json --- # Question Answering Skill General-purpose question answering capability powered by OpenRouter. Access 300+ LLM models (GPT-4o, Claude, Llama, Gemini, Mistral, etc.) through a single unified API. Handles c
development
--- id: research-v1 name: research version: 1.0.0 author: [email protected] tags: - research - question-answering - analysis - summarization - langchain input_modes: - text/plain - application/json output_modes: - text/plain - application/json --- # Research Skill Research and information retrieval capability powered by LangChain.js. Uses GPT-4o to answer questions, summarize information, provide detailed analysis, and generate structured research outputs. ## Capabilities ###
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.