Packages Documentation logo

Packages Documentation

OrganizationPopular
reactive
packages-documentation

Write, update, and format documentation for @data-client public APIs - API reference (Docusaurus/MDX), README files, JSDoc/TSDoc docstrings, usage examples, migration guides, deprecation notices, changelog entries. Use when changing exported APIs (docs must update in the same PR), writing new package docs, or updating the dataclient.io site.

Overview

Publisherreactive
Repositorydata-client
Skill namepackages-documentation
Stars
2K
Forks
98
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by reactive on GitHub. Read the source before you install it.

Installation

Install the Packages Documentation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/reactive/data-client/tree/master/.agents/skills/packages-documentation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/reactive/data-client.git /tmp/data-client
mkdir -p .claude/skills
cp -r /tmp/data-client/.agents/skills/packages-documentation .claude/skills/packages-documentation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Packages Documentation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Packages Documentation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Packages Documentation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Package Documentation Writing Guidelines

This guide covers how to write and format documentation for public library interfaces.

Documentation Structure

The /docs folder is organized by package:

  • docs/core/ - Documentation for @data-client/core, @data-client/react and @data-client/vue
  • docs/rest/ - Documentation for @data-client/rest
  • docs/graphql/ - Documentation for @data-client/graphql

Each package documentation has subdirectories:

  • api/ - API reference documentation (one file per public class/function/hook)
  • guides/ - How-to guides and tutorials
  • concepts/ - Conceptual documentation
  • getting-started/ - Getting started guides

React and Vue (single source)

docs/core renders twice: React at /docs, Vue at /vue. Never copy a page to make a Vue version. Wrap framework-specific content instead, so shared prose and resources stay in one place:

  • :::react / :::vue blocks (use :::: on an outer admonition that contains them)
  • :react[...] / :vue[...] for inline words or links
  • <FrameworkPlayground> instead of <HooksPlayground>, with shared resource code blocks directly inside and component code blocks in :::react / :::vue
  • framework-imports on a code fence for framework-agnostic code (managers, middleware): write @data-client/react imports and Vue pages show @data-client/vue. Examples never import @data-client/core; apps only install the react or vue package
  • vue_title:, vue_description: (any vue_<key>:) front matter overrides
  • frameworks: [react] front matter for pages with no Vue equivalent
  • foo.vue.md replaces foo.md for Vue; only for Vue-only pages or when nothing is shareable

When changing a page, update both framework blocks in the same edit. See website/framework-docs/README.md.

Documentation File Naming

API documentation files should match the exported name:

  • useSuspense.ts → docs/core/api/useSuspense.md
  • RestEndpoint.js → docs/rest/api/RestEndpoint.md
  • Controller.ts → docs/core/api/Controller.md
  • Entity.ts → docs/rest/api/Entity.md (or docs/core/api/Entity.md)

Documentation Format

All API documentation files should include:

  1. Frontmatter with metadata:
markdown
---
title: API Name
sidebar_label: Display Name
---
  1. Description - What the API does

  2. Usage examples - Code examples showing how to use it

  3. Parameters/Options - Document all parameters, options, and return types

  4. Type information - TypeScript types and examples

  5. Related APIs - Links to related documentation

Finding the Right Documentation File

  1. Identify the package: Check which package the code belongs to (packages/core, packages/rest, etc.)
  2. Check exports: Look at the package's index.ts or main entry point to see what's exported
  3. Match the name: Find the corresponding file in docs/{package}/api/
  4. Check guides: If it's a workflow change, also check docs/{package}/guides/

Examples

Example 1: Adding a new hook

  • File: packages/react/src/hooks/useNewFeature.ts
  • Action: Create docs/core/api/useNewFeature.md with usage examples and API reference

Example 2: Changing a method signature

  • File: packages/rest/src/RestEndpoint.js (changing extend() method)
  • Action: Update docs/rest/api/RestEndpoint.md with new signature, migration notes, and updated examples

Example 3: Deprecating an API

  • File: packages/core/src/SomeClass.ts (deprecating oldMethod())
  • Action:
    • Update docs/core/api/SomeClass.md with deprecation notice
    • Document the replacement API
    • Add migration guide if needed

Example 4: Adding a new option

  • File: packages/rest/src/RestEndpoint.js (adding newOption parameter)
  • Action: Update docs/rest/api/RestEndpoint.md to document the new option with examples

Checklist

Before completing changes to public APIs in /packages:

  • Identified all affected public APIs (exports from package entry points)
  • Located or created corresponding documentation files in /docs/{package}/api/
  • Updated API reference documentation with changes
  • Added/updated code examples
  • Updated related guides if workflow changed
  • Added migration notes for breaking changes
  • Updated TypeScript examples in documentation
  • Verified documentation builds correctly (if applicable)
  • Updated agent skills in .agents/skills that cover the API: references.json for added/renamed/deleted pages, and SKILL.md examples (see .cursor/rules/skills-sync.mdc)

Important Notes

  • Public APIs are anything exported from the package's main entry point (typically index.ts or src/index.ts)
  • Internal/private APIs (prefixed with _, not exported, or marked as @internal) don't require documentation updates
  • When in doubt, err on the side of documenting - it's better to have extra documentation than missing documentation
  • Documentation should be updated in the same commit or PR as the code changes

Frequently asked questions

What does the Packages Documentation AI skill do?

Write, update, and format documentation for @data-client public APIs - API reference (Docusaurus/MDX), README files, JSDoc/TSDoc docstrings, usage examples, migration guides, deprecation notices, changelog entries. Use when changing exported APIs (docs must update in the same PR), writing new package docs, or updating the dataclient.io site.

Why use Packages Documentation on TypingMind?

Because you install it once and use it with any model. Packages Documentation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Packages Documentation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/reactive/data-client/tree/master/.agents/skills/packages-documentation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Packages Documentation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Packages Documentation?

As many as you like. As long as a model supports skills, you can use Packages Documentation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Packages Documentation AI skill free?

Yes. It is published on GitHub by reactive under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇