Repo Structure Navigate logo

Repo Structure Navigate

OrganizationPopular
open-circle
repo-structure-navigate

Navigate the Formisch monorepo structure. Use when finding code locations, understanding architecture, locating source files, or implementing features across packages and frameworks.

Overview

Publisheropen-circle
Repositoryformisch
Skill namerepo-structure-navigate
Stars
1.2K
Forks
36
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

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

Installation

Install the Repo Structure Navigate 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-structure-navigate
  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-structure-navigate .claude/skills/repo-structure-navigate
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Repo Structure Navigate 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 Structure Navigate 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 Structure Navigate 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.

Repository Navigation

Quick reference for understanding and navigating the Formisch repository structure.

Overview

Formisch is a schema-based, headless form library with a framework-agnostic core supporting multiple frameworks (Angular, Preact, Qwik, React, React Native, Solid, Svelte, Vue). Framework-specific reactivity is injected at build time for native performance.

Architecture:

  • Monorepo with pnpm workspaces
  • Framework-agnostic core + framework-specific wrappers
  • TypeScript throughout with Valibot schemas

Directory Structure

formisch/
├── packages/         # Core packages
│   ├── core/         # Framework-agnostic form logic
│   └── methods/      # Form manipulation methods
├── frameworks/       # Framework-specific wrappers (angular, preact, qwik, react, react-native, solid, svelte, vue)
├── playgrounds/      # Testing environments per framework
├── scripts/          # Automation scripts
├── website/          # Documentation site
├── skills/           # Agent skills (this folder)
└── prompts/          # Legacy AI agent guides (deprecated)

Core Packages

/packages/core/ → @formisch/core

Framework-agnostic form logic. Builds to framework-specific outputs via tsdown.config.ts.

Key directories:

  • src/array/ - Array field utilities
  • src/field/ - Field management
  • src/form/ - Form state management
  • src/framework/ - Framework reactivity integration (injected at build time)
  • src/types/ - TypeScript types

/packages/methods/ → @formisch/methods

Form manipulation utilities. Each method in its own directory (src/{method-name}/).

Available methods: focus, getDeepErrorEntries, getDeepErrors, getDirtyInput, getDirtyPaths, getErrors, getInput, handleSubmit, insert, move, pickDirty, remove, replace, reset, setErrors, setInput, submit, swap, validate

Framework Packages

/frameworks/{framework}/ → @formisch/{framework}

Thin wrappers that:

  1. Export framework-specific core build
  2. Provide framework-native components/primitives
  3. Re-export methods

Structure:

frameworks/{framework}/
├── src/
│   ├── components/    # Form, Field components
│   ├── primitives/    # createForm/useForm, useField, useFieldArray
│   ├── types/         # Framework-specific types
│   └── index.tsx      # Main export

Playgrounds

/playgrounds/{framework}/

Minimal apps for testing. Use workspace dependencies (workspace:*). Run with pnpm dev.

Website

/website/

Documentation site built with Qwik. Update when APIs change.

Quick Reference

Finding Code

Looking for...Location
Form state logic/packages/core/src/form/
Field management/packages/core/src/field/
Array utilities/packages/core/src/array/
Methods (submit, reset, etc.)/packages/methods/src/{method-name}/
Framework components/frameworks/{framework}/src/components/
Framework primitives/frameworks/{framework}/src/primitives/
Type definitions/packages/core/src/types/
Usage examples/playgrounds/{framework}/src/
Documentation/website/src/routes/

Commands

bash
pnpm install  # Install dependencies
pnpm build    # Build a package
pnpm test     # Run tests
pnpm lint     # Lint and type check

Common Workflows

Adding a Core Feature

  1. Implement in /packages/core/src/
  2. Add framework-specific code in /packages/core/src/framework/
  3. Update exports in index files
  4. Test in playgrounds
  5. Update docs in /website/

Adding a Method

  1. Create /packages/methods/src/{method-name}/
  2. Export from /packages/methods/src/index.ts
  3. Test in playground and document on website

Adding Framework Support

  1. Create /packages/core/src/framework/{framework}.ts
  2. Configure build in tsdown.config.ts
  3. Create /frameworks/{framework}/ package
  4. Create playground in /playgrounds/{framework}/

Important Rules

Code Style

  • TypeScript throughout
  • Use Prettier and ESLint
  • Add JSDoc for public APIs
  • camelCase for functions/variables, PascalCase for components/types

Imports

  • Relative imports within packages
  • Package imports across packages
  • Prefer named exports

Testing

  • Tests next to implementation (.test.ts)
  • Use Vitest
  • Run: pnpm test

Architecture

Framework-agnostic core - Written once, compiled to framework-specific versions via tsdown.config.ts. Framework reactivity is injected at build time from /packages/core/src/framework/{framework}.ts. This ensures:

  • Native performance per framework
  • Consistent behavior across frameworks
  • Minimal bundle size

Best Practices

  • Code differs between frameworks - always check the target framework
  • Check playgrounds for real-world usage examples
  • TypeScript types are the source of truth
  • Follow existing patterns in the codebase
  • Test incrementally (build → test → playground)
  • Update website docs when changing APIs
  • Use workspace:* dependencies in playgrounds

Frequently asked questions

What does the Repo Structure Navigate AI skill do?

Navigate the Formisch monorepo structure. Use when finding code locations, understanding architecture, locating source files, or implementing features across packages and frameworks.

Why use Repo Structure Navigate on TypingMind?

Because you install it once and use it with any model. Repo Structure Navigate 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 Structure Navigate in TypingMind?

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

Which AI models can use Repo Structure Navigate?

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 Structure Navigate?

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

Is the Repo Structure Navigate 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 👇