faq-generator_skill
- Python
1
GitHub Stars
2
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill vishalsachdev/claude-skills --skill faq-generator- README.md12.0 KB
- SKILL.md19.0 KB
Overview
This skill generates a comprehensive, categorized FAQ set from course descriptions, learning graphs, glossary terms, and chapter content to support student understanding and chatbot integration. It requires the course description, a learning graph, a glossary, and at least 30% of chapter content before producing high-quality FAQs. The output includes markdown FAQs, a RAG-ready JSON export, and quality and coverage reports to guide improvements.
How this skill works
The skill assesses content completeness using a multi-factor scoring rubric (course description, learning graph DAG, glossary size, word count, and concept coverage). It analyzes source documents to identify question opportunities, produces questions organized into six standard categories, and writes answers that follow Bloom's Taxonomy distribution, include examples and links when available. Finally, it exports docs/faq.md, faq-chatbot-training.json, a quality report, and a coverage-gaps report.
When to use it
- After the course description, learning graph, glossary, and at least 30% of chapters exist
- When building initial FAQs for a new textbook
- When preparing content for chatbot or RAG integration
- After significant content additions to refresh FAQs
- To identify knowledge gaps and prioritize new content
Best practices
- Run assessment and address content completeness warnings before full generation
- Preserve manually curated FAQ items and deduplicate intelligently
- Prioritize high-centrality concepts from the learning graph for Core Concept questions
- Include examples for roughly 40% of answers and links to source sections when available
- Keep questions concise, searchable, and aligned with glossary terminology
Example use cases
- Generate a starter FAQ pack for a new course once 30% of chapters are drafted
- Produce chatbot-ready JSON to seed a RAG system with Q/A pairs and metadata
- Create a quality report highlighting coverage, Bloom distribution, and improvements
- Identify high-priority concept gaps for curriculum authors to address
FAQ
Run the generator after you have a finalized course description, a validated learning graph, a generated glossary, and at least 30% of chapter content. These prerequisites provide sufficient context to produce meaningful questions, support links to source material, and ensure good concept coverage. If the content completeness score is low, the tool will prompt you to proceed with a disclaimer about limited quality.
How are questions organized and balanced?
Questions are grouped into six categories: Getting Started, Core Concepts, Technical Details, Common Challenges, Best Practices, and Advanced Topics. The generator targets specific Bloom's Taxonomy distributions per category to ensure a mix of Remember, Understand, Apply, Analyze, Evaluate, and Create-level items, and reports actual vs target distributions in a quality report.
What outputs does the skill produce for integration?
It writes docs/faq.md with markdown-structured Q/A, docs/learning-graph/faq-chatbot-training.json formatted for RAG ingestion (with IDs, categories, bloom_level, difficulty, concepts, keywords, source_links, example flags, and word counts), and generates quality and coverage-gaps reports to guide iterative improvements.
