- Home
- Skills
- Vishalsachdev
- Claude Skills
- Glossary Generator
glossary-generator_skill
- Python
1
GitHub Stars
3
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 glossary-generator- INSTALL.md5.9 KB
- README.md7.4 KB
- SKILL.md10.8 KB
Overview
This skill automatically generates a comprehensive glossary from a finalized learning graph concept list, producing ISO 11179-compliant definitions that are precise, concise, distinct, non-circular, and free of business rules. It creates an alphabetized docs/glossary.md, adds examples and cross-references, and produces a quality report to validate compliance and readability.
How this skill works
The skill reads the reviewed concept list and course context files to understand audience and objectives, then validates input quality (duplicates, formatting, length, clarity) and computes a quality score. For each concept it generates a short ISO 11179-style definition, optionally adds a brief example and 1–3 cross-references, then verifies alphabetical order, cross-reference integrity, and absence of circular definitions. Finally it emits docs/glossary.md and a learning-graph/glossary-quality-report.md and can optionally produce a cross-ref JSON and update mkdocs navigation.
When to use it
- After the learning graph concept list has been finalized and reviewed
- When preparing an intelligent textbook or course glossary
- If you need ISO 11179-compliant metadata-style definitions
- When you want consistent cross-references and example coverage
- Before publishing course docs to ensure term clarity and ordering
Best practices
- Provide a complete, reviewed concept list file (e.g., docs/learning-graph/02-concept-list-v1.md)
- Ensure course description and learning outcomes are available for context
- Resolve major quality issues (duplicates, ambiguous labels) before generation
- Target examples for 60–80% of terms to aid student understanding
- Run the quality report and address any definitions scoring below 70
Example use cases
- Generate a student-facing glossary for an intelligent textbook after concept enumeration
- Standardize terminology across course modules and learning materials
- Validate a concept list for duplicates, formatting, and length before publishing
- Create a cross-reference index for semantic search and visualization
- Produce a compliance report showing ISO 11179 scoring and remediation steps
FAQ
A finalized concept list (typically docs/learning-graph/02-concept-list-v1.md) and the course description; additional docs in /docs/**/*.md improve context and example relevance.
How are definitions evaluated?
Each definition is scored on Precision, Conciseness, Distinctiveness, and Non-circularity (25 points each) and summarized in the glossary-quality-report with length, example coverage, readability, and recommendations.
Can the tool auto-fix formatting or duplicates?
Yes—auto-fix options are offered for common issues, but the skill prompts for user confirmation when changes affect semantics or require merging terms.