create-docs

A workflow for creating a complete documentation website for a software project using Docus, with features such as search, dark mode, an MCP server, and llms.txt. It also detects package managers and monorepo layouts; a monorepo is one repository containing multiple related packages or applications.

In plain words
What is it for?
Use it to initialize or expand a docs site, generate documentation pages, detect the project's package manager, and configure AI-related documentation access.
Why use it?
It turns project information into an organized documentation site and sets up the project-specific configuration needed to run it.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nuxt-content/docus/create-docs
Any agent
npx skills add nuxt-content/docus --skill create-docs
Clone the repo
git clone --depth 1 https://github.com/nuxt-content/docus

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,158 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00079 $0.03158
Opus 5 $0.00039 $0.01579
Sonnet 5 $0.00016 $0.00632
Haiku 4.5 $0.00008 $0.00316

Measured 2d ago against content hash 3236e6d0c547, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-docs 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 2d ago.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

docs/skills/create-docs/SKILL.md · 500 lines

How it starts

The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Docs

Generate a complete, production-ready documentation site for any project.

Workflow

  1. Analyze - Detect package manager, monorepo structure, read context
  2. Initialize - Create docs directory with correct setup
  3. Generate - Write documentation pages using templates
  4. Configure - Set up AI integration (MCP, llms.txt)
  5. Finalize - Provide next steps with correct commands

Package Manager Reference

Detect from lock files, default to npm if none found:

Lock File PM Install Run Add
pnpm-lock.yaml pnpm pnpm install pnpm run pnpm add
package-lock.json npm npm install npm run npm install
yarn.lock yarn yarn install yarn yarn add
bun.lockb bun bun install bun run bun add

Use [pm] as placeholder in commands below.


Step 1: Analyze Project

Detect Project Structure

Check for:
├── pnpm-workspace.yaml   → pnpm monorepo
├── turbo.json            → Turborepo monorepo
├── lerna.json            → Lerna monorepo
├── nx.json               → Nx monorepo
├── apps/                 → Apps directory (monorepo)
├── packages/             → Packages directory (monorepo)
├── docs/                 → Existing docs (avoid overwriting)
├── README.md             → Main documentation source
└── src/ or lib/          → Source code location

Determine Docs Location

Project Type Target Directory Workspace Entry
Standard project ./docs N/A
Monorepo with apps/ ./apps/docs apps/docs
Monorepo with packages/ ./docs docs
Existing docs/ folder Ask user or ./documentation

Read Context Files

File Extract
README.md Project name, description, features, usage examples
package.json Name, description, dependencies, repository URL
src/ or lib/ Exported functions, composables for API docs

Read the full file on GitHub · 500 lines

Files

What ships with it

3 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.

Changes

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.

  1. 2d ago First seen · 500 lines · 79 tokens per session scan A 3236e6d0c547

Subscribe to this mod's changes

create-docs is a skill published in the GitHub repository nuxt-content/docus (3,017 stars, last pushed 4d ago), licensed MIT. It adds 79 tokens to every session and 3,158 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.