diataxis:plan
Use when a documentation request is ambiguous, involves planning a docs structure, or a page seems to mix multiple purposes. Classifies content into Diátaxis quadrants (tutorial, how-to, reference, explanation), proposes a documentation map, and produces a writing plan with ordering. Triggers on phrases like "plan my docs", "what docs do I need", "help me organise my documentation", "docs architecture", "I need to write docs for my project", or when a user asks for a README and a full docs set together.
What this skill does
# Diátaxis documentation planner ## Purpose Use this skill when a request is about "docs", "documentation", "README", "guides", "reference", or "improving the docs" but the correct form is unclear. This skill classifies the work using the Diátaxis model, proposes the right document types, and creates a practical writing plan. ## Core model Diátaxis separates documentation into four kinds: - Tutorial: a lesson for learning by doing - How-to guide: directions to achieve a specific goal - Reference: factual description of the machinery - Explanation: conceptual background and reasoning The first classification question is not "what topic is this?" but "what does the reader need right now?" Use this decision table: - If the content guides action and supports acquiring skill, it is a **tutorial** - If the content guides action and supports applying skill, it is a **how-to guide** - If the content informs cognition and supports applying skill, it is **reference** - If the content informs cognition and supports acquiring understanding, it is **explanation** ## When to use Use this skill when: - the user asks for a docs plan or docs overhaul - a page seems to mix multiple purposes - the user asks for a README and docs architecture together - the correct doc type is uncertain - a large docs set needs to be reorganised Do not use this skill when the target format is already obvious and the user wants the content written immediately. In that case route directly to the specific writing skill. ## Inputs to gather Collect or infer: - product or library name - audience segments - user maturity level: beginner, competent practitioner, advanced user, maintainer - major jobs to be done - key concepts that need explaining - major interfaces or surfaces that need reference - current docs inventory, if any - whether the request is for a single page or an entire docs set ## Workflow 1. Identify the primary user need behind the request. 2. Classify each requested artifact into one Diátaxis form. 3. Split mixed requests into multiple artifacts rather than forcing one page to do everything. 4. Propose a docs map with landing pages where needed. 5. For large sets, keep top-level lists short and group long lists into smaller clusters. 6. Recommend an iterative order of work: - README / landing page - one reliable tutorial - top how-to guides - minimum viable reference - explanation pages for key concepts 7. State what should not be included in each artifact. ## README routing rules Treat README as a landing page, not a quadrant. A README may include: - project summary - value proposition - audience - install / quickstart entry - minimal example - link map into tutorial, how-to, reference, explanation - contribution and support entry points A README must not try to fully replace all four quadrants. ## Output format Return: 1. Classification table - requested item - assigned type - user need served - must include - must avoid 2. Proposed docs structure 3. Writing order 4. Risks and likely boundary violations ## Boundary checks Flag and fix these: - tutorial drifting into explanation - how-to drifting into training - reference drifting into advice or opinion - explanation drifting into procedures - README becoming a dumping ground ## Quality bar A good plan should make it obvious: - where a beginner starts - where a competent user goes to get work done - where exact facts live - where the "why" lives If that is not obvious, the docs map is still wrong.
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.