Forms logo

Forms

Organization
rejot-dev
forms

Create, update, and inspect system Forms with runtime tools. Use when designing a JSON Schema form, changing its stored definition, reading submissions, or routing form lifecycle events.

Overview

Publisherrejot-dev
Repositoryfragno
Skill nameforms
Stars
62
Forks
6
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by rejot-dev on GitHub. Read the source before you install it.

Installation

Install the Forms 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.
  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/rejot-dev/fragno.git /tmp/fragno
mkdir -p .claude/skills
cp -r /tmp/fragno/apps/backoffice/content/static/skills/forms .claude/skills/forms
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Forms 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 Forms 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 Forms 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.

Forms

Backoffice Forms is available only in the global system scope.

Schema reference

Before filling in --data-schema-json or --ui-schema-json, read /static/skills/forms/reference/schema-authoring.md for the renderer-supported JSON Schema and JSON Forms UI Schema vocabulary, rules, and complete examples.

Create and verify

  1. Design the response contract as JSON Schema.
  2. Choose a stable lowercase slug.
  3. Create the form with forms.create.
  4. Keep the returned form ID; submission tools address forms by ID, not slug.
  5. Run forms.list and verify the title, slug, status, schema, and version.

Create a draft contact form:

bash
forms.create \
  --title "Contact form" \
  --slug contact \
  --description "Collect support requests" \
  --data-schema-json '{"type":"object","properties":{"email":{"type":"string","format":"email"},"message":{"type":"string","minLength":10}},"required":["email","message"]}' \
  --format json

forms.create accepts:

  • --title: human-readable name;
  • --slug: public identifier;
  • --description: optional purpose;
  • --status: draft, open, or closed; defaults to draft;
  • --data-schema-json: required JSON Schema object;
  • --ui-schema-json: optional JSON Forms UI Schema object.

Use --status open only when the form should accept responses immediately. Use draft while its schema is still being reviewed.

Confirm the stored form and capture its id:

bash
forms.list --format json

Creation is complete when forms.list contains exactly the intended slug, status, response contract, and UI layout.

Update and verify

Update selected fields using the form ID:

bash
forms.update --form-id FORM_ID --status open --format json

forms.update accepts --title, --slug, --description, --status, --data-schema-json, and --ui-schema-json. Only supplied fields change. Replacing the data schema increments the form version, so verify the resulting definition with forms.list --format json before interpreting new submissions.

Read submissions

List a form's responses using the ID returned by forms.create or forms.list:

bash
forms.submissions.list --form-id FORM_ID --format json

Responses are newest-first by default and are returned in bounded pages. Read them oldest-first or choose a smaller page when reconstructing a timeline:

bash
forms.submissions.list --form-id FORM_ID --sort-order asc --page-size 25 --format json

When hasNextPage is true, pass the returned nextCursor to continue:

bash
forms.submissions.list --form-id FORM_ID --cursor NEXT_CURSOR --format json

An empty submissions array means no response has been stored for that form. Compare each submission's formVersion with the current version from forms.list before interpreting data from forms whose schema has changed.

Schema guidance

Use an object-rooted dataSchema and start with the smallest response contract that collects the required result. Treat dataSchema as validation and uiSchema as presentation; read the schema reference before relying on a field type, layout, option, or conditional rule.

Automation events

Use forms / response.submitted for automated processing and forms.submissions.list for inspection or reconciliation. Forms events are durable and at-least-once, so key event-driven effects by the event ID or the subject identifiers described in the event reference.

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 Forms AI skill do?

Create, update, and inspect system Forms with runtime tools. Use when designing a JSON Schema form, changing its stored definition, reading submissions, or routing form lifecycle events.

Why use Forms on TypingMind?

Because you install it once and use it with any model. Forms 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 Forms in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rejot-dev/fragno/tree/main/apps/backoffice/content/static/skills/forms. 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 Forms?

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 Forms?

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

Is the Forms AI skill free?

Yes. It is published on GitHub by rejot-dev 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 👇