Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/webmcp-org/docs/_diataxisnpx skills add WebMCP-org/docs --skill _diataxisgit clone --depth 1 https://github.com/WebMCP-org/docsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.01510 |
| Opus 5 | $0.00022 | $0.00755 |
| Sonnet 5 | $0.00009 | $0.00302 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
diataxis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to diataxis — 33 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diataxis Documentation Framework
Complete reference for the Diataxis framework — a systematic approach to technical documentation authoring by Daniele Procida. All content sourced verbatim from diataxis.fr.
When to Use This Skill
This skill should be triggered when:
- Writing documentation: Creating new docs pages of any type
- Reviewing documentation: Checking if content is in the right place and follows the right form
- Restructuring documentation: Reorganizing existing docs into proper Diataxis categories
- Deciding content type: Determining whether something should be a tutorial, how-to, reference, or explanation
- Resolving confusion: Distinguishing tutorials from how-to guides, or reference from explanation
The Diataxis Compass
Use this decision table when you need to classify content:
| If the content... | ...and serves the user's... | ...then it belongs in... |
|---|---|---|
| informs action | acquisition of skill | a tutorial |
| informs action | application of skill | a how-to guide |
| informs cognition | application of skill | reference |
| informs cognition | acquisition of skill | explanation |
Two questions to ask:
- Action or cognition? Is this about doing something or knowing something?
- Acquisition or application? Is the user learning or working?
Full compass guidance: references/compass.md
The Four Documentation Types
Tutorials (learning-oriented)
- An experience guided by a tutor, where the learner acquires skills by doing
- Teacher holds nearly all responsibility — learner just follows directions
- Concrete steps, no choices, no branching, ruthlessly minimal explanation
- Language: "We will...", "First, do X. Now, do Y.", "Notice that...", "You have built..."
Full reference: references/tutorials.md
How-to Guides (goal-oriented)
- Directions that guide a competent user through a real-world problem
- Assumes the user already knows the basics and has a specific goal
- Can branch ("If this, do that"), addresses real-world conditions
- Language: "If you want X, do Y." Conditional imperatives.
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/application.md 1.7 KB
- references/colophon.md 2.8 KB
- references/compass.md 2.4 KB
- references/complex-hierarchies.md 8.3 KB
- references/explanation.md 7.3 KB
- references/foundations.md 4.1 KB
- references/how-to-guides.md 11 KB
- references/how-to-use-diataxis.md 7.1 KB
- references/index.md 3.2 KB
- references/map.md 5.6 KB
- references/quality.md 11 KB
- references/reference-explanation.md 3.4 KB
- references/reference.md 5.7 KB
- references/start-here.md 8.2 KB
- references/theory.md 1.4 KB
- references/tutorials-how-to.md 14 KB
- references/tutorials.md 16 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 135 lines · 44 tokens per session scan A 501d4711024e
diataxis is a skill published in the GitHub repository WebMCP-org/docs (2 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,510 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to diataxis, differing in 33 lines, and is treated as a copy.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
creating-skills
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…