Interaction Contracts logo

Interaction Contracts

Community
kemiljk
interaction-contracts

Define or review the behaviour promised by an interaction before or during implementation: triggers, state changes, persistence, interruption, recovery, and acceptance checks. Use when a mockup or component leaves consequential behaviour unresolved.

Overview

Publisherkemiljk
Repositoryskills
Skill nameinteraction-contracts
Stars
64
Forks
3
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 kemiljk on GitHub. Read the source before you install it.

Installation

Install the Interaction Contracts 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/kemiljk/skills/tree/main/skills/interaction-contracts
  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/kemiljk/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/interaction-contracts .claude/skills/interaction-contracts
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Interaction Contracts 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 Interaction Contracts 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 Interaction Contracts 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.

Interaction Contracts

Make the behaviour of a named interaction explicit enough that designers and engineers can build and verify the same experience. A contract describes observable promises; it does not require a state-machine library or a particular architecture.

Find the unresolved promise

Use the existing brief, interface, component API, and implementation to identify the person, task, starting state, and supported inputs. Preserve established behaviour unless the task calls for changing it. Distinguish a requirement from observed behaviour and a proposed change.

Cover the consequential uncertainty, not every possible event. An already specified local edit needs only the affected promise. Ask when a missing product decision would materially change the contract; otherwise state a reasonable assumption and proceed. A request for a specification authorises a specification; implementation requires an implementation request.

Describe the observable contract

Use a compact table, annotated flow, or the team's existing format. Include what matters for the interaction:

Contract elementResolve
Entry and triggerPreconditions, available inputs, and what initiates the operation
State and feedbackWhat changes immediately, what is pending, and what confirms completion
Ownership and persistenceWhere the authoritative value lives, when it is committed, and what survives leaving or returning
InterruptionWhat cancel, Escape, navigation, another input, or a second submission means where supported
Failure and recoveryWhat remains intact, how failure is explained, and how the person can continue
Focus and accessControl meaning, supported keyboard or assistive input, focus movement, and a reduced-motion equivalent where relevant

Separate cancelling an edit from cancelling a request and undoing a committed change. If cancellation cannot reverse a remote effect, do not promise that it does. Optimistic feedback needs an account of failure and reconciliation. Distinguish local acceptance from server confirmation or later processing when that difference matters to the task.

Inspect plausible overlapping actions: repeated submission, editing during a pending save, leaving and returning, or an older response arriving after a newer one. Include a sequence only when supported use can reach it. Resolve which result may update the UI without prescribing an unnecessary implementation mechanism.

Example: editing a project title

This is a hypothetical contract, not a product finding. Suppose the existing product uses explicit Save and Cancel:

Starting state and actionRequired resultAcceptance check
Open the editorCurrent title appears; committed value is unchangedOpen an existing project and inspect the input
Change the title, then CancelDraft is discarded; original title remainsReopen and confirm the original value
Submit a valid titleShow pending feedback; confirm saved only after successObserve a successful save and revisit the project
Save failsPreserve the draft, explain failure, and offer a useful retryCause a failed save, then retry without retyping

Decide validation, navigation during saving, and focus return from product context. Do not infer that every editor should use this save model.

Carry the contract into the work

For design, represent the needed states and transitions and annotate requirements the medium cannot demonstrate. For code, map the contract to existing state ownership, controls, and service boundaries. Avoid replacing an architecture merely to make the specification look tidy.

Verify representative sequences against observable results. Use behavioural tests for consequential state or persistence changes; visual inspection alone cannot establish those promises. A mock service proves only the behaviour it simulates. Disclose unavailable checks and unresolved decisions.

When reporting a bug, identify the affected consumer and task, prerequisites and reproduction steps, expected and actual behaviour, and impact. Keep unexecuted concerns as hypotheses; do not report an imagined event sequence as a reproduced failure.

Deliver the requested contract, review, or scoped implementation, with the decisions made, acceptance checks performed, and remaining limits. This skill defines behaviour; it does not expand a local interaction into a whole-product hardening pass.

Frequently asked questions

What does the Interaction Contracts AI skill do?

Define or review the behaviour promised by an interaction before or during implementation: triggers, state changes, persistence, interruption, recovery, and acceptance checks. Use when a mockup or component leaves consequential behaviour unresolved.

Why use Interaction Contracts on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kemiljk/skills/tree/main/skills/interaction-contracts. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Interaction Contracts?

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 Interaction Contracts?

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

Is the Interaction Contracts AI skill free?

Yes. It is published on GitHub by kemiljk 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 👇