From diataxis-skills
Convert mixed documentation into separate Diataxis quadrant documents. Use when documentation exists but mixes tutorials, how-tos, reference, and explanation content together, or after a diataxis-audit identifies mixed content.
How this skill is triggered — by the user, by Claude, or both
Slash command
/diataxis-skills:diataxis-convertThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Split mixed documentation into separate, focused documents — one per [Diataxis](https://diataxis.fr/) quadrant.
Split mixed documentation into separate, focused documents — one per Diataxis quadrant.
Practical Theoretical
+----------------+------------------+
Study | TUTORIALS | EXPLANATION |
| (learning) | (understanding) |
+----------------+------------------+
Work | HOW-TO | REFERENCE |
| (problem) | (information) |
+----------------+------------------+
diataxis-audit flagged mixed content that needs splittingdiataxis-audit identifying mixed sectionsThe most frequent mixing patterns and how to resolve them:
| Pattern | Symptom | Resolution |
|---|---|---|
| Tutorial + Explanation | Steps interrupted by long "why" sections | Extract explanations, link from tutorial |
| How-to + Tutorial | Guide that teaches from scratch | Extract learning path into tutorial, keep problem-solving in how-to |
| Reference + How-to | API docs with embedded instructions | Extract procedures into how-to guides |
| README that does everything | Single doc covers setup, usage, API, and rationale | Split into 4 documents, replace README with overview + links |
Read the source document(s) completely. For each section or paragraph, tag it:
[T] — Tutorial content (guided learning, step-by-step, builds to a result)[H] — How-to content (problem-solving, goal-oriented, assumes competence)[R] — Reference content (factual, descriptive, API/config details)[E] — Explanation content (conceptual, "why", design decisions, context)Collect all [T] tagged content. Restructure it into a proper tutorial:
Collect all [H] tagged content. Group by distinct goals, then for each goal:
Collect all [R] tagged content. Restructure into consistent reference format:
Collect all [E] tagged content. Restructure into coherent explanation:
Add cross-references between all generated documents:
Propose what to do with the original mixed document:
# Conversion Report: [source document]
## Content Distribution
| Quadrant | New Document | Lines from Source | Content Summary |
|----------|-------------|-------------------|-----------------|
| Tutorial | tutorials/getting-started.md | 12-45, 78-92 | Setup and first use |
| How-to | how-to/configure-x.md | 50-77 | Configuration steps |
| Reference | reference/api.md | 93-150 | API parameters |
| Explanation | explanation/architecture.md | 1-11, 151-180 | Design rationale |
## Content Not Migrated
- [Any content dropped and why]
## Source Document Recommendation
[Replace / Reduce / Archive] — [rationale]
diataxis-audit: Run first to identify which documents need conversiondiataxis-create: Use templates for the output documentsdiataxis-plan: Plan the target directory structure before convertingnpx claudepluginhub jrjsmrtn/jrjsmrtn-skills --plugin diataxis-skillsFetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Applies a firm's KYC/AML rules grid to parsed onboarding records: assigns risk rating, checks required documents, outputs rule outcomes with citations, and routes for escalation.
Generates daily or weekly digests of activity from connected sources (chat, email, docs, tasks, CRM), highlighting action items, decisions, mentions, and project updates.