Generate accurate, semantic frontmatter for markdown files based on content-type schemas and tag taxonomy. Use when analyzing documents to create frontmatter, enriching vault content, or when user mentions tags/metadata/frontmatter. Specializes in Fabric patterns, blog posts, research notes, client projects.
How this skill is triggered — by the user, by Claude, or both
Slash command
/frontmatter-generation:frontmatter-generationThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
This is a Standard Operating Procedure for analyzing markdown documents and generating accurate, semantic frontmatter.
This is a Standard Operating Procedure for analyzing markdown documents and generating accurate, semantic frontmatter.
Before analyzing ANY document, read these files in order:
Read schemas.yaml (in this skill directory)
Read taxonomy.yaml (in this skill directory)
You now have the knowledge needed to analyze documents correctly.
Read the FULL target document and answer these questions:
What is this document ACTUALLY about?
What is the document's PURPOSE?
What is the document's NATURE?
Critical Rule: Base your answers on ACTUAL CONTENT, not filename or structure.
Based on your semantic understanding AND the loaded schemas:
Based on your semantic understanding AND the loaded taxonomy:
Select 5-7 tags from EXISTING taxonomy
Tag Selection Criteria:
Strongly prefer existing taxonomy tags
Quality Validation (CRITICAL):
Examples of WRONG vs RIGHT:
output/email, output/essay, domain/health
logical-fallacies, critical-thinking, argumentation, analysis
Following the schema for detected content-type, extract:
When analyzing Fabric patterns:
outputs field: What pattern ACTUALLY produces (not structure, actual content type)inputs: What it expects (read INPUT section)domains: Field/industry based on ACTUAL content, not directory structurecomplexity: low|medium|high based on logic complexitymechanics: extraction|synthesis|analysis|critique|transformation (what it DOES)Before writing frontmatter, validate:
Do tags match actual semantic content? (not structure or filename)
Is description accurate and specific? (not generic)
Are all required fields present for content-type?
Is this better than automated pattern matching?
If any answer is "no", REVISE before writing.
See the examples/ directory for properly formatted frontmatter by content-type.
tags: [tag1, tag2, tag3]❌ WRONG: Generic tags based on filename or structure
output/email, domain/health, type/markdown❌ WRONG: Too many tags (18 tags instead of 5-7)
❌ WRONG: New tags that duplicate existing tags with different naming
✅ RIGHT: Semantic tags that describe actual document content
logical-fallacies, critical-thinking, argumentation for fallacy detection pattern✅ RIGHT: 5-7 tags that all directly relate to document purpose
✅ RIGHT: Tags from existing taxonomy when available
npx claudepluginhub cmgramse/skill-development --plugin frontmatter-generationGenerates brand assets: logos (55+ styles, Gemini AI), CIP mockups, HTML slides (Chart.js), banners (22 styles), SVG icons (15 styles), and social media photos. Routes to sub-skills for design tokens and UI styling.