Agent skill

Documentation Diataxis

by canonical in canonical/workshop

Analyzes documentation against Diataxis framework (Tutorial, How-to, Reference, Explanation).

GPL-3.0Auto-check passed

Install Documentation Diataxis

skills CLI
$ npx skills add canonical/workshop --skill documentation-diataxis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install canonical/workshop documentation-diataxis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/canonical/workshop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/documentation-diataxis .claude/skills/documentation-diataxis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
documentation-diataxis
GitHub stars
114
Token cost
~1.6k tokens
SKILL.md length
683 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
GPL-3.0

At a glance

Analyzes documentation against Diataxis framework (Tutorial, How-to, Reference, Explanation).

  • Works in 7 steps: Identify intended category: Determine… → Infer actual category: Analyse the… → Check user need alignment → …
  • Reviewing documentation structure
  • SKILL.md covers Scope, Inputs, Actions and Constraints, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Documentation Diataxis is an agent skill from canonical/workshop. Analyzes documentation against Diataxis framework (Tutorial, How-to, Reference, Explanation). Use when reviewing documentation structure or classifying content type. Identifies misalignments between declared category and actual content.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Workshops are secure, fast, and composable development environments that come agent-ready. The licence is GPL-3.0.

When your agent uses it

  • Reviewing documentation structure
  • Classifying content type

Example prompts

  • “Use the documentation-diataxis skill to analyz documentation against Diataxis framework (Tutorial, How-to, Reference, Explanation)”
  • “/documentation-diataxis”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Identify intended category: Determine the declared category
  2. Infer actual category: Analyse the text's structure, tone,
  3. Check user need alignment
  4. Note hard-to-fit genres: Some documentation types do not align
  5. Evaluate quality
  6. Document misalignments: Explicitly identify where the document
  7. Verify completion: Confirm the analysis completed

What it can do on your machine

Read from SKILL.md and the folder at commit 0b41ee9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • diataxis.fr

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Documentation Diataxis loads about 1.6k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 683 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from canonical/workshop at commit 0b41ee9, republished under its GPL-3.0 licence (© canonical). 683 words, ~1,550 tokens.

Download SKILL.mdSave it as .claude/skills/documentation-diataxis/SKILL.md (or your agent's skills folder).
name
documentation-diataxis
description
Analyzes documentation against Diataxis framework (Tutorial, How-to, Reference, Explanation). Use when reviewing documentation structure or classifying content type. Identifies misalignments between declared category and actual content.

Diataxis Classification Review

Scope

Diataxis classification only: identify whether each page is a tutorial, how-to guide, explanation, or reference; note structural mismatches between content type and declared category, and suggest improvements where real issues exist. Ground classification in the Diataxis foundations: the two axes of craft (action vs cognition, acquisition vs application) define four user needs (learning, goals, information, understanding).

This skill identifies flaws and provides actionable recommendations; it does not enforce compliance or apply pass/fail criteria.

Inputs

  • Documentation file(s) under review.
  • Diataxis framework principles (embedded in classification criteria below).

Actions

  1. Identify intended category: Determine the declared category based on directory location (tutorial/, how-to/, explanation/, reference/) and file metadata (front matter keys such as category, type, diataxis, or reST .. meta:: entries).

  2. Infer actual category: Analyse the text's structure, tone, and progression to determine which quadrant it actually resembles. Use these classification criteria:

    • Tutorial indicators:

      • Step-by-step progression building a complete project
      • Imperative mood ("Create a file", "Run this command")
      • Learning-focused language ("you will learn", "by the end")
      • Safe, controlled environment (specific versions, no branching)
      • Frequent reassurance and checkpoints
      • Teaches by doing, not explaining
    • How-to guide indicators:

      • Problem-solution format with clear goal
      • Assumes existing knowledge and competence
      • Clearly states prerequisites and applicability scope
      • Action-oriented ("To achieve X, do Y")
      • Flexible, allows for variation
      • Focuses on results, not learning
      • Omits explanations unless critical to success
    • Reference indicators:

      • Descriptive, declarative statements
      • Comprehensive coverage of subject
      • Neutral, technical tone
      • Structured for lookup (tables, lists, alphabetical)
      • Parameters, options, API signatures
      • Accuracy over narrative
    • Explanation indicators:

      • Conceptual focus ("why" and "how it works")
      • Discursive, exploratory tone
      • Comparative analysis
      • Context, background, relationships
      • Illuminates understanding, not action
      • May include history, design decisions, alternatives
      • May contain subjective opinions and personal perspectives
  3. Check user need alignment:

    Map the page to the user need implied by the action/cognition and acquisition/application axes (learning, goals, information, understanding).

    • Tutorials: Is it a learning-oriented lesson? Does it build confidence through doing? Is it linear and safe?
    • How-to guides: Is it a task-oriented recipe? Does it help a competent user solve a specific problem? Is it goal-focused?
    • Reference: Is it information-oriented? Does it describe things accurately and completely? Is it structured for lookup?
    • Explanation: Is it understanding-oriented? Does it clarify concepts, context, and relationships? Is it discursive?
  4. Note hard-to-fit genres: Some documentation types do not align cleanly with a single quadrant (for example, release notes or contributing guides). Flag these cases explicitly, reference the Diataxis guidance on complex hierarchies (https://diataxis.fr/complex-hierarchies/), and choose the closest fit category for reporting.

  5. Evaluate quality:

    • Functional quality: Is the content accurate, complete, consistent, useful, and precise?

      • Missing prerequisites or dependencies
      • Incomplete steps or procedures
      • Inconsistent terminology or naming
      • Outdated information (version mismatches, deprecated features)
    • Deep quality: Does the content have good flow? Does it anticipate user questions? Is the cognitive load appropriate? Is the experience clear?

      • Paragraph length (>4 sentences may suggest need for breaking)
      • Sentence complexity (nested clauses, dense jargon)
      • Transition quality (abrupt topic changes, missing connectives)
      • Progressive disclosure (introducing too much too soon)
      • User journey mapping (gaps in expected flow)
  6. Document misalignments: Explicitly identify where the document fails to meet the needs of its category, jumps between categories, or where quality breaks down. For each issue, provide:

    • Specific location (section, paragraph)
    • Nature of the problem
    • Impact on user experience
    • Concrete suggestion for improvement
  7. Verify completion: Confirm the analysis completed:

    • Category classification completed (declared vs inferred)
    • User need alignment analyzed
    • Quality assessment performed (functional and deep quality)
    • Misalignments documented with recommendations

    State the completion status:

    • ✓ Diataxis analysis complete: [declared category] → [inferred category], [N] issues found
    • OR ✓ Diataxis analysis complete: Content aligns well with [category]
Show full SKILL.md (83 more words)Show less

Constraints

  • Do not ignore the Diataxis framework.
  • Assign each page to exactly one quadrant.
  • Do not introduce categories beyond the four quadrants.

Output

A Diataxis Analysis Report detailing:

  • Declared category (from metadata/directory structure).
  • Inferred category (from content analysis).
  • User need alignment analysis (which quadrant best serves the user).
  • Functional quality findings (with specific examples).
  • Deep quality findings (with specific examples).
  • Identified issues and actionable recommendations for improvement.

If no significant issues are found, state that the documentation aligns well with its intended category.

© canonical, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/documentation-diataxis of canonical/workshop.

Open the folder on GitHubat commit 0b41ee9

Compare with similar skills

Documentation Diataxis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Documentation Diataxis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Documentation Diataxis this skillcanonical/workshop114—~1.6kAutomated safety check: PassGPL-3.0
Agent Code Analyzerruvnet/ruflo74k3 repos~1.5kAutomated safety check: PassMIT
Agent Pagerank Analyzerruvnet/ruflo74k3 repos~2.9kAutomated safety check: PassMIT
Agent Performance Analyzerruvnet/ruflo74k2 repos~1.3kAutomated safety check: PassMIT
TutorialQ00/ouroboros6.2k—~1.6kAutomated safety check: PassMIT
Diff Analyzeruvnet/ruflo74k—~450Automated safety check: NotesMIT

Similar skills

  • Agent skill for code-analyzer - invoke with $agent-code-analyzer

    74k GitHub starsUsed in 3 repos~1.5k tokens
    DevelopmentAuto-check passed
  • Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer

    74k GitHub starsUsed in 3 repos~2.9k tokens
    Auto-check passed
  • Agent skill for performance-analyzer - invoke with $agent-performance-analyzer

    74k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check passed
  • Tutorial

    Q00/ouroboros

    Interactive tutorial teaching Ouroboros hands-on. An agent skill from Q00/ouroboros.

    6.2k GitHub stars~1.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Diff Analyze

    ruvnet/ruflo

    Analyze git diffs for risk scoring, reviewer recommendations, and change classification.

    74k GitHub stars~450 tokensUpdated today
    DevelopmentAuto-check: notes
  • Analyze GitHub Flake

    flutter/flutter

    Expertise in analyzing flake github issues in the flutter/flutter repository.

    179k GitHub stars~1.1k tokensUpdated today
    MobileAuto-check passed

More from canonical/workshop

  • Documentation Build

    canonical/workshop

    Validates documentation builds successfully. An agent skill from canonical/workshop.

    114 GitHub stars~762 tokensUpdated today
    Auto-check passed
  • Documentation Review

    canonical/workshop

    Performs comprehensive documentation review including build validation, Diataxis analysis, structure audit, accuracy verification, and style compliance.

    114 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Documentation Style

    canonical/workshop

    Enforces project documentation style guide compliance for tone, voice, terminology, punctuation, and formatting.

    114 GitHub stars~714 tokensUpdated today
    Auto-check passed
  • Documentation Verify

    canonical/workshop

    Verifies documentation accuracy by cross-referencing claims, CLI commands, API signatures, and configuration against source code.

    114 GitHub stars~932 tokensUpdated today
    Auto-check passed
  • Documentation Structure

    canonical/workshop

    Validates documentation structural integrity including heading hierarchy, metadata, file naming, navigation, and cross-references.

    114 GitHub stars~704 tokensUpdated today
    Auto-check passed

Questions about Documentation Diataxis

What does Documentation Diataxis do?

Analyzes documentation against Diataxis framework (Tutorial, How-to, Reference, Explanation). Documentation Diataxis is an agent skill from canonical/workshop. Analyzes documentation against Diataxis framework (Tutorial, How-to, Reference, Explanation).

When should I use Documentation Diataxis?

Documentation Diataxis fits situations like: reviewing documentation structure; classifying content type.

How do I install Documentation Diataxis in Claude Code?

Run `npx skills add canonical/workshop --skill documentation-diataxis -a claude-code`. Or copy the skill folder (.github/skills/documentation-diataxis in canonical/workshop) into .claude/skills/documentation-diataxis in your project. Claude Code loads it when a task matches its description.

How do I install Documentation Diataxis in Codex?

Run `npx skills add canonical/workshop --skill documentation-diataxis -a codex`. Or copy the skill folder (.github/skills/documentation-diataxis in canonical/workshop) into .agents/skills/documentation-diataxis in your project. Codex loads it when a task matches its description.

Can I use Documentation Diataxis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add canonical/workshop --skill documentation-diataxis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/documentation-diataxis, .gemini/skills/documentation-diataxis, .github/skills/documentation-diataxis and .opencode/skills/documentation-diataxis in your project.

What does Documentation Diataxis need to run?

SKILL.md names no scripts, command-line tools or credentials: Documentation Diataxis is instructions for the agent only.

Does Documentation Diataxis access the network?

SKILL.md names 1 domain. As links in the text: diataxis.fr. This is read from the text; nothing was executed.

Is Documentation Diataxis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Documentation Diataxis use?

Documentation Diataxis is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Documentation Diataxis use?

About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Documentation Diataxis?

Skills that share tags, products or a category with Documentation Diataxis: Agent Code Analyzer (ruvnet/ruflo, 74k stars), Agent Pagerank Analyzer (ruvnet/ruflo, 74k stars), Agent Performance Analyzer (ruvnet/ruflo, 74k stars) and Tutorial (Q00/ouroboros, 6.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Documentation Diataxis?

canonical (a GitHub organization) maintains it in canonical/workshop, which has 114 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 8, 2026.

Source: canonical/workshop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.