/absolute-docs

name: absolute-docs
version: 0.5.0
description: >
  Diátaxis-driven documentation for AI coding agents: write, improve, or audit
  tutorials, how-tos, reference, explanation, and developer docs (README,
  CONTRIBUTING, ADRs). Detects the docs stack; gates on the outline before
  writing prose; verifies every claim against the code before it ships.
  Triggers on "absolute docs", "write docs", "write a tutorial", "write a README",
  "document this", "improve this doc", "audit our docs".
category: workflow
tags:
  - workflow
  - documentation
  - diataxis
  - readme
  - tutorials
  - reference
platforms:
  - claude-code
  - gemini-cli
  - openai-codex
  - mcp
user-invocable: true
argument-hint: "[target]"
license: MIT
maintainers:
  - github: maddhruv

> Start your first response with the 📚 emoji.

Absolute Documentations: Diátaxis-Driven Documentation

Absolute Documentations turns "write some docs" into documentation a reader can actually use. Every document it produces serves exactly one reader need, identified with the Diátaxis framework, written in the project's own voice and docs stack, and verified against the actual codebase before it ships. It writes new docs, rewrites existing ones to their quadrant's standard, and audits whole doc sites for structural rot.

It never writes a full document before the outline is approved, and it never documents behavior it has not verified in the code.

---

The Diátaxis Compass

Every piece of documentation answers exactly one kind of reader need. Classify before writing — a page that mixes quadrants serves nobody.

| | **Serves the reader's STUDY** | **Serves the reader's WORK** | |---|---|---| | **Practical steps** | **Tutorial** — a lesson. Guides a newcomer through a guaranteed-success experience. | **How-to guide** — a recipe. Helps a competent user accomplish a specific goal. | | **Theoretical knowledge** | **Explanation** — a discussion. Deepens understanding of a topic, gives context and reasons. | **Reference** — a dictionary. States facts about the machinery, completely and neutrally. |

To classify, ask two questions:

1. **Is the reader studying (acquiring skill) or working (applying skill)?** 2. **Does the reader need action (steps to follow) or cognition (knowledge to absorb)?**

| Reader situation | Quadrant | |---|---| | "I'm new, show me what this is like" | Tutorial | | "I know the basics, I need to get X done" | How-to guide | | "What exactly does this option/endpoint/flag do?" | Reference | | "Why does it work this way? What's the bigger picture?" | Explanation |

**The cardinal sin is mixing.** A tutorial that stops to explain architecture loses the learner. A reference page that gives advice stops being trustworthy as a pure description. When you feel the urge to mix, that is a signal to *link* to the other quadrant, not to merge into it.

---

Modes

Detect the mode from the request:

| User says | Mode | |---|---| | "write a tutorial / guide / README / docs for X", "document this feature" | **WRITE** | | "improve / rewrite / clean up this doc", "this README is bad" | **IMPROVE** | | "audit our docs", "our docs are a mess", "restructure the documentation" | **AUDIT** |

---

WRITE Mode

Step 1 — Recon (codebase first, questions second)

Before asking the user anything, learn everything the repo can teach:

• **Detect the docs stack** (see Stack Detection below) and load

`references/docs-stacks.md` if writing site pages.

• **Read existing docs** — tone, terminology, heading style, frontmatter schema,

sidebar/nav structure, where each quadrant lives.

• **Read the code being documented** — public API surface, actual option names,

actual defaults, actual error messages. The code is the source of truth, not your memory of similar tools.

• **Check project metadata** — package.json/pyproject/go.mod for the real name,

version, install command, supported runtimes.

Step 2 — Intake

Four things must be pinned down before any outline. Answer them from recon where possible; ask the user **only** what the repo cannot answer, one question at a time (use `AskUserQuestion` where available), always with a recommended answer:

1. **Document type** — which Diátaxis quadrant (or which developer-doc form). 2. **Target audience** — novice end user? experienced operator? contributor? What can you assume they already know? 3. **Reader's goal** — what will the reader be able to do after reading? 4. **Scope** — what is explicitly in, and just as important, what is explicitly out.

Step 3 — Outline gate (hard gate)

Propose, before writing any prose:

• the file path(s) the doc will live at, matching the stack's routing conventions
• a heading-level outline with one line per section describing its content
• the quadrant each page serves (multi-page requests get one quadrant per page)
• any sidebar/nav changes needed

**STOP and wait for explicit approval.** Do not write the document until the user confirms the outline. This is the single gate in the workflow — everything before it is cheap to change, everything after it is expensive.

Step 4 — Write

• Follow the per-quadrant playbook in `references/` (load the matching file).
• Write in the project's established voice; follow `references/style-and-voice.md`.
• Use the stack's components and frontmatter (from `references/docs-stacks.md`);

plain Markdown when no stack is detected.

• Apply the Accuracy Protocol below to every factual claim and code block.

Step 5 — Self-review

Score the draft against the rubric below. Fix anything scoring under 4 before presenting. Present the doc with a one-paragraph summary of what was written, where it lives, and any nav changes made.

---

IMPROVE Mode

For "fix this README" / "improve this page":

1. **Classify** the page's *intended* quadrant from its location, title, and content. If it serves two masters, say so — that is usually the root problem. 2. **Diff against the quadrant's standard** (load its