Repo Website Api Create logo

Repo Website Api Create

OrganizationPopular
open-circle
repo-website-api-create

Create new API documentation routes for the Formisch website. Use when adding documentation for new exported functions, types, components, or methods that don't yet have website documentation.

Overview

Publisheropen-circle
Repositoryformisch
Skill namerepo-website-api-create
Stars
1.2K
Forks
36
Bundled files
3
LicenseMIT
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by open-circle on GitHub. Read the source before you install it.

Installation

Install the Repo Website Api Create 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/open-circle/formisch/tree/main/.agents/skills/repo-website-api-create
  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/open-circle/formisch.git /tmp/formisch
mkdir -p .claude/skills
cp -r /tmp/formisch/.agents/skills/repo-website-api-create .claude/skills/repo-website-api-create
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Repo Website Api Create 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 Repo Website Api Create 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 Repo Website Api Create 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.

Adding New API Documentation

This skill provides instructions for adding new API reference routes to the Formisch website. Consistency and uniformity across all API documentation is critical.

Key Principle: Source code is the single source of truth. All documentation is derived directly from the source code.

Quick Overview

Each API function or type needs its own folder containing:

  • index.mdx - The main documentation file with MDX content
  • properties.ts - TypeScript definitions that map to the Property component

Step-by-Step Process

Step 1: Identify the API

Before creating documentation:

  1. Category: Is it a core type, framework primitive/hook/composable/rune, framework type, component, or method?
  2. Name: The exact function/type name (camelCase for functions, PascalCase for types/components)
  3. Source file: Path to the source code in the monorepo
  4. Dependencies: Related types, primitives, or methods

Step 2: Read the Source Code

This is the most critical step. Read the entire source file and extract:

  1. Interfaces and Types - Exported type definitions with generic parameters
  2. Function Signatures - All overloads (not implementations)
  3. JSDoc Comments - Descriptions, param tags, hints
  4. Generic Constraints - extends clauses
  5. Return Types - Interface names with generics

Step 3: Create the Documentation Folder

Create folder in the appropriate category:

/website/src/routes/(docs)/{framework}/api/(category)/{ApiName}/
├── index.mdx
└── properties.ts

Categories by framework:

  • core/api/(types) - Core/shared type definitions
  • methods/api/ - Global methods (focus, validate, reset, etc.)
  • solid/api/(primitives) - SolidJS primitives (createForm, useField)
  • solid/api/(components) - SolidJS components (Field, Form)
  • solid/api/(types) - SolidJS-specific types
  • qwik/api/(hooks) - Qwik hooks (useForm$, useField)
  • preact/api/(hooks) - Preact hooks
  • react-native/api/(hooks) - React Native hooks (useForm, useField)
  • angular/api/(functions) - Angular functions (injectForm, injectField)
  • angular/api/(directives) - Angular directives (formischForm, formischField)
  • angular/api/(types) - Angular-specific types (FormStore, FieldStore, SignalOrValue)
  • svelte/api/(runes) - Svelte 5 runes
  • vue/api/(composables) - Vue composables

Step 4: Create properties.ts

See references/property-component.md for the Property component specification and type mapping patterns.

typescript
import type { PropertyProps } from '~/components';

export const properties: Record<string, PropertyProps> = {
  // 1. GENERICS - always with modifier: 'extends'
  TSchema: {
    modifier: 'extends',
    type: {
      type: 'custom',
      name: 'FormSchema',
      href: '/core/api/FormSchema/',
    },
  },

  // Generics without a constraint in the source default to `extends unknown`
  TValue: {
    modifier: 'extends',
    type: 'unknown',
  },

  // 2. PARAMETERS - matching function signature
  config: {
    type: {
      type: 'custom',
      name: 'FormConfig',
      href: '../FormConfig/',
      generics: [{ type: 'custom', name: 'TSchema' }],
    },
  },

  // 3. RETURN TYPE
  Store: {
    type: {
      type: 'custom',
      name: 'FormStore',
      href: '../FormStore/',
      generics: [{ type: 'custom', name: 'TSchema' }],
    },
  },
};

Step 5: Create index.mdx

See references/mdx-patterns.md for detailed MDX structure and patterns.

mdx
---
title: createForm
description: Creates a reactive form store from a form configuration.
source: /frameworks/solid/src/primitives/createForm/createForm.ts
contributors:
  - fabian-hiller
---

import { ApiList, Property } from '~/components';
import { properties } from './properties';

# createForm

Creates a reactive form store from a form configuration.

\`\`\`ts
const form = createForm<TSchema>(config);
\`\`\`

## Generics

- `TSchema` <Property {...properties.TSchema} />

## Parameters

- `config` <Property {...properties.config} />

### Explanation

With `createForm` you can create a reactive form store...

## Returns

- `form` <Property {...properties.Store} />

## Examples

The following examples show how `createForm` can be used.

### Basic form

\`\`\`ts
import { createForm } from '@formisch/solid';
import \* as v from 'valibot';

const LoginSchema = v.object({
email: v.pipe(v.string(), v.email()),
password: v.pipe(v.string(), v.minLength(8)),
});

const loginForm = createForm({ schema: LoginSchema });
\`\`\`

## Related

### Primitives

<ApiList
  items={[
    { text: 'useField', href: '../useField/' },
    { text: 'useFieldArray', href: '../useFieldArray/' },
  ]}
/>

### Components

<ApiList
  items={[
    { text: 'Form', href: '../Form/' },
    { text: 'Field', href: '../Field/' },
  ]}
/>

Step 6: Update menu.md

Add to the appropriate menu.md file in alphabetical order:

markdown
## Primitives

- [createForm](/solid/api/createForm/)
- [useField](/solid/api/useField/)

Documentation Types

Function Documentation

  • Function signature code block
  • Generics section (if applicable)
  • Parameters section (use "Parameters" heading)
  • Explanation section (required)
  • Returns section (if not void)
  • Examples section (required, 2-4 progressive examples)
  • Related section

Component Documentation

  • Component signature code block
  • Generics section (if applicable)
  • Properties section (use "Properties" heading)
  • Explanation section (required)
  • NO Returns section
  • NO Examples section
  • Related section

Type Documentation

  • Type name and description
  • Generics section (if applicable)
  • Definition section listing properties
  • Explanation section (only if semantically important)
  • NO Examples section
  • Related section (Primitives/Components/Methods only, never Types)

Important Rules

URL Patterns

Parentheses folders don't appear in URLs:

  • /solid/api/createForm/ (not /solid/api/(primitives)/createForm/)

Link Patterns

  • Relative paths within same section: ../FormStore/
  • Absolute paths for cross-package: /core/api/FormSchema/
  • External links for Valibot: https://valibot.dev/api/InferInput/

Framework-Specific Terminology

FrameworkCategory TermExample API
SolidPrimitivescreateForm, useField
QwikHooksuseForm$, useField
PreactHooksuseForm, useField
React NativeHooksuseForm, useField
AngularFunctions / DirectivesinjectForm, formischField
VueComposablesuseForm, useField
SvelteRunescreateForm, useField

References

For detailed patterns and examples, see:

Checklist

Before submitting:

  • Read source file completely
  • All generics documented with correct constraints
  • All parameters documented with correct types
  • Return type documented
  • Custom types link to their documentation (href)
  • Function signature matches source exactly
  • Examples are realistic and follow naming conventions
  • Related section uses correct framework terminology
  • menu.md updated in alphabetical order
  • No typos or grammatical errors

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Repo Website Api Create AI skill do?

Create new API documentation routes for the Formisch website. Use when adding documentation for new exported functions, types, components, or methods that don't yet have website documentation.

Why use Repo Website Api Create on TypingMind?

Because you install it once and use it with any model. Repo Website Api Create 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 Repo Website Api Create in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/open-circle/formisch/tree/main/.agents/skills/repo-website-api-create. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Repo Website Api Create?

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 Repo Website Api Create?

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

Is the Repo Website Api Create AI skill free?

Yes. It is published on GitHub by open-circle under the MIT 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 👇