doc-export
Create comprehensive, self-contained documentation for a codebase. Use when asked to prepare documentation for external consumption, export docs for AI tools, consolidate scattered documentation, or create a documentation package that can stand alone without source code access. Triggers include "prepare docs for", "export documentation", "consolidate docs", "create documentation package", or requests to make docs suitable for tools that cannot access source code.
What this skill does
# Documentation Export Create self-contained documentation packages from codebases. ## Goal Produce a minimal, accurate, well-organized documentation set that fully describes a system without requiring source code access. ## Process ### 1. Audit Existing Documentation Inventory current docs: ```bash find ./docs -name "*.md" -type f ls -la ./docs/ ``` For each file, assess: - **Purpose**: What does it document? - **Currency**: Does it reflect current implementation? - **Overlap**: Does it duplicate other docs? - **Completeness**: What's missing? ### 2. Explore the Codebase Understand what needs documenting: - **Domain model**: Core types, entities, relationships - **Architecture**: Packages, layers, key design decisions - **Commands/API**: User-facing interfaces - **Data model**: Database schema, storage Use grep/glob to find domain types, command definitions, schema files. ### 3. Plan Document Structure Target 3-5 focused documents: | Document | Purpose | Content | |----------|---------|---------| | **SPEC.md** | Product specification | Goals, data model, command reference, behaviors | | **DOMAIN-MODEL.md** | Conceptual model | Business concepts, relationships, terminology | | **CLI-REFERENCE.md** or **API-REFERENCE.md** | Usage reference | Commands/endpoints, examples, workflows | | **ARCHITECTURE.md** | Technical architecture | Package structure, design decisions, patterns | Adjust based on project type (CLI, library, service, etc.). ### 4. Consolidate and Rename Apply consistent naming: - Use `SCREAMING-KEBAB-CASE.md` (e.g., `CLI-REFERENCE.md`) - Delete sparse/outdated files - Merge related content into focused documents - Remove duplicate information ### 5. Update Content For each document: **Spec/Reference docs:** - Verify all commands/endpoints documented - Update field lists to match current schema - Fix incorrect states, types, enums - Add missing features (check recent commits) - Remove deprecated/unimplemented features **Architecture docs:** - Document actual package structure - Explain key design decisions - Cover data model and storage - Note what's implemented vs planned **Domain model:** - Define all core concepts - Show relationships between entities - Clarify terminology - Note implementation status ### 6. Verify Cross-References Check for broken references: ```bash grep -r "docs/[A-Z]" ./docs/ grep -rn "\.md" ./docs/ | grep -v "^Binary" ``` Update all internal links to match renamed files. ### 7. Final Review Checklist: - [ ] Each document has a clear, single purpose - [ ] No duplicate information across documents - [ ] All cross-references valid - [ ] Naming convention consistent - [ ] Outdated content removed - [ ] Missing features documented - [ ] Implementation status noted where relevant - [ ] Documents are self-contained (no broken image refs, etc.) ## Document Guidelines ### SPEC.md - Comprehensive product specification - Include: goals, data model, command/API reference, behaviors - This is the authoritative reference - 30-50KB typical ### DOMAIN-MODEL.md - Conceptual, not implementation-focused - Define business terms and relationships - Include diagrams (Mermaid) if helpful - Note what's implemented vs aspirational - 10-15KB typical ### CLI-REFERENCE.md / API-REFERENCE.md - Feature-oriented, not exhaustive - Include common workflows and examples - Group by task, not alphabetically - 15-20KB typical ### ARCHITECTURE.md - Technical decisions and rationale - Package/module structure - Key patterns and conventions - Design decisions explained - 10-15KB typical ## Anti-patterns - Creating README.md or CHANGELOG.md (not useful for external consumption) - Keeping sparse files (< 20 lines of content) - Duplicating content across documents - Referencing non-existent files or images - Including implementation details in conceptual docs - Documenting aspirational features as implemented
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.