Configuring Connections logo

Configuring Connections

Organization
rejot-dev
configuring-connections

Set up any Backoffice integration, connection, or named provider. Always use for setup requests such as ‘help me set up Reson8’, even when a provider-specific skill also applies; also use when required configuration is missing or connection status must be verified.

Overview

Publisherrejot-dev
Repositoryfragno
Skill nameconfiguring-connections
Stars
62
Forks
6
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 rejot-dev on GitHub. Read the source before you install it.

Installation

Install the Configuring Connections 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/configuring-connections .claude/skills/configuring-connections
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Configuring Connections 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 Configuring Connections 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 Configuring Connections 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.

Configuring Connections

Treat connection setup as a handshake: inspect → collect → configure → verify.

Required process

  1. Read "/static/codemode/providers/connections.d.ts", then inspect the catalog and selected connection:

    js
    async () => {
      const connectionList = await connections.list({});
      const status = await connections.get({ id: "telegram" });
      const schema = await connections.schema({ id: "telegram" });
      const setup = await connections.setup({ id: "telegram" });
      return { connectionList, status, schema, setup };
    };

    Read the matching capability skill from the available skills, such as /static/skills/telegram-connection/SKILL.md, for provider-specific fields, webhook behavior, events, and tools. Complete when configurability, current status, required fields, masked existing values, and provider-specific setup steps are known.

  2. Prefer a durable, generated setup form when required values remain missing. Read /static/skills/workflows/SKILL.md and /static/skills/generating-backoffice-uis/SKILL.md, then define an inline workflow whose completed step.do returns a $ui form and whose following step.waitForEvent collects the submission. Build controls only for missing fields, label them from the live schema and provider skill, bind them under one response object, and submit that object with one WorkflowEventButton. Continue configuration and verification inside durable step.do calls so the user can finish the handshake through the rendered interface. When every required value was already supplied in the request, proceed directly without an input workflow.

    Treat the live fields list as the complete set of user inputs. Providers generate managed values such as webhook secrets during configuration, so do not add controls or payload properties that are absent from that list. Use submitted values only as the configuration payload; keep secrets out of labels, summaries, final output, and follow-up prose. Complete when a waiting workflow displays controls for every missing required field, or every required field already has a user-supplied or configured value.

  3. Configure with a payload that matches the live schema, inside the setup workflow when step 2 created one:

    js
    async () => {
      return await connections.configure({
        id: "telegram",
        payload: {
          botToken: "...",
        },
      });
    };

    When schema/setup exposes no configurable fields or identifies a managed connection, follow its manual steps and status nextSteps instead of calling configure. Complete when the configure call succeeds or the managed setup path is explicit.

  4. Verify and re-read status in the same setup workflow when one is active. connections.verify always returns a required verification result; treat verification.ok as the single authoritative verification signal. Return a generated final UI that presents the connection status, verification result, and actionable next steps while preserving the raw results as ordinary sibling fields:

    js
    async () => {
      const result = await connections.verify({ id: "telegram" });
      const finalStatus = await connections.get({ id: "telegram" });
      return {
        result,
        finalStatus,
        verified: result.verification.ok,
        verificationMessage: result.verification.message,
      };
    };

    Complete only when result.verification.ok is true and the rendered final result confirms the configured connection. If it is false, present result.verification.message, missing fields, and nextSteps in the generated UI; start another input handshake only when those next steps require another user-supplied value.

Use connections.reset({ id, confirm: id }) only for an explicit reset request, then re-read status so the cleared state is visible.

Frequently asked questions

What does the Configuring Connections AI skill do?

Set up any Backoffice integration, connection, or named provider. Always use for setup requests such as ‘help me set up Reson8’, even when a provider-specific skill also applies; also use when required configuration is missing or connection status must be verified.

Why use Configuring Connections on TypingMind?

Because you install it once and use it with any model. Configuring Connections 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 Configuring Connections 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/configuring-connections. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Configuring Connections?

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 Configuring Connections?

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

Is the Configuring Connections 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 👇