Pipefy Relations logo

Pipefy Relations

Organization
pipefy
pipefy-relations

Use this skill when the user wants to link pipes, tables, or cards across workflows — creating or managing pipe relations, table relations, or card relations.

Overview

Publisherpipefy
Repositoryai-toolkit
Skill namepipefy-relations
Stars
52
Forks
24
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Pipefy Relations 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/pipefy/ai-toolkit/tree/main/plugins/pipefy/skills/pipefy-relations
  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/pipefy/ai-toolkit.git /tmp/ai-toolkit
mkdir -p .claude/skills
cp -r /tmp/ai-toolkit/plugins/pipefy/skills/pipefy-relations .claude/skills/pipefy-relations
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pipefy Relations 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 Pipefy Relations 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 Pipefy Relations 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.

Connections & Relations

MCP clients: read references/mcp.md. CLI users: read references/cli.md. Examples below describe shared operation arguments.

Link processes and cards across workflows.


Key concepts

  • Pipe relations define parent/child structure between pipes (who connects to whom, constraints, auto-fill). Use get_pipe_relations on a pipe to list relation IDs and metadata.
  • Card relations connect individual cards through an existing pipe relation: pass source_id = the pipe relation's ID (from get_pipe_relations). Default sourceType is PipeRelation; use extra_input (e.g., sourceType: Field) when the API requires a field-based link — see introspect_type on CreateCardRelationInput.
  • Table relations in GraphQL are loaded by table-relation ID, not by database table ID: get_table_relations takes a non-empty list of those IDs.
  • Connector fields are card fields (connection type), not pipe relations for writes. Prefer update_card + field_updates with operation ADD/REMOVE (related card ids, or record ids when the field connects to a database table). An id from any other pipe or table is dropped without an error: ADD keeps the existing links, and update_card_field with no valid id clears them all. Read the links back after a write. update_card_field is replace-all of the full id list; get_card value is display titles only — do not rebuild from it. This skill's get_card_relations still reads connector-field links (with card ids). create_card_relation / delete_card_relation write links through a pipe relation and are incremental — pick the surface that matches the link type. delete_card_relation removes only a link made through a pipe relation, never a connector-field link, and needs permission to edit the parent card.

Tools

OperationRead-onlyPurpose
get_pipe_relationsYesList pipe-to-pipe relations for a pipe.
create_pipe_relationNoCreate a new pipe-to-pipe relation.
update_pipe_relationNoChange relation config (auto-fill, constraints). Pass every constraint flag; see Failure modes.
delete_pipe_relationNoDestructive; review and approve first.
get_table_relationsYesLoad table relations by relation ID.
get_card_relationsYesList all card-to-card relations on a card.
create_card_relationNoLink two cards through an existing pipe relation.
delete_card_relationNoDestructive; review and approve first.

Steps — link two cards via an existing pipe relation

  1. Get the pipe relation ID:

    Operation: get_pipe_relations(pipe_id=67890)

    Note the id field on the relation (not the pipe ID).

  2. Create the card relation:

    Operation: create_card_relation(parent_id=<PARENT_CARD_ID>, child_id=<CHILD_CARD_ID>, source_id=<PIPE_RELATION_ID>)

  3. Verify:

    Operation: get_card_relations(card_id=<CHILD_CARD_ID>)


Steps — create a new pipe relation

  1. Create the relation between two pipes:

    Operation: create_pipe_relation(parent_id=111, child_id=222, name="Support Escalation")

  2. Use the relation — cards in the parent pipe can now be linked to cards in the child pipe using create_card_relation.


Success criteria

  • get_pipe_relations returns the new relation with both pipe IDs.
  • get_card_relations shows the linked card ID after create_card_relation.

Failure modes

  • create_card_relation fails with "relation not found": source_id must be the pipe relation ID (from get_pipe_relations), not the pipe ID. These are different values.
  • Table relations return empty: get_table_relations requires table-relation IDs, not table IDs. Get table-relation IDs from the table's connection config.
  • update_pipe_relation resets the flags you leave out. Pipefy requires all eight constraint flags on every update (allChildrenMustBeDoneToFinishParent, allChildrenMustBeDoneToMoveParent, autoFillFieldEnabled, canConnectExistingItems, canConnectMultipleItems, canCreateNewItems, childMustExistToFinishParent, childMustExistToMoveParent). A flag you do not pass is sent with a default: the three canConnect…/canCreateNewItems flags true, the other five false. So even a rename changes the relation's constraints. Read the relation with get_pipe_relations and pass every flag's current value. Leave ownFieldMaps out to keep the auto-fill mappings: sending it replaces the whole list.
  • Deletion: show the affected relation and obtain approval before removing it.

See also

  • pipefy-pipes-and-cards — create the pipes and cards before linking them; connector field updates and update_card_field replace-all live there.
  • docs/mcp/tools/identifiers.md — which args expect slug vs numeric id for field and relation tools.
  • pipefy-introspection — discover CreateCardRelationInput when non-standard sourceType is needed.

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 Pipefy Relations AI skill do?

Use this skill when the user wants to link pipes, tables, or cards across workflows — creating or managing pipe relations, table relations, or card relations.

Why use Pipefy Relations on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pipefy/ai-toolkit/tree/main/plugins/pipefy/skills/pipefy-relations. 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 Pipefy Relations?

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 Pipefy Relations?

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

Is the Pipefy Relations AI skill free?

Yes. It is published on GitHub by pipefy 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 👇