Options logo

Options

Organization
greenfield-inc
options

Use when the person asks what to do or for trade-offs, or more than one design is live. Waits for a pick. Never plans.

Overview

Publishergreenfield-inc
RepositoryPane
Skill nameoptions
Stars
529
Forks
227
Bundled files
1
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 greenfield-inc on GitHub. Read the source before you install it.

Installation

Install the Options 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/greenfield-inc/Pane/tree/main/main/src/services/paneChatBundle/skills/options
  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/greenfield-inc/Pane.git /tmp/Pane
mkdir -p .claude/skills
cp -r /tmp/Pane/main/src/services/paneChatBundle/skills/options .claude/skills/options
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Options 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 Options 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 Options 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.

Options

This is the only place alternatives are argued. If the implementation session could still choose the architecture, this step was skipped.

Rules

  • One section per decision. Small decisions can be asked inline and recorded later in the plan (the ticket from create-ticket, or plan.html) instead of getting a document.
  • Two or three real options per decision, plus two that are always present: the smallest version (what ships if everything deferrable is deferred, and what the user loses) and do nothing (what stays wrong, observably).
  • State each option's complexity-ladder rung, and give a reason for every rung above the lowest workable one. The ladder: 1 configuration or copy, 2 reuse an existing pattern, 3 new code inside one module, 4 a new contract between modules, 5 a schema change or migration, 6 a new dependency or new infrastructure.
  • Give every option, including the smallest version and doing nothing, a short complexity statement as described in the template. Cover both the requirements and the implementation: the complexity added compared with today, the likely ways it breaks, and the ongoing maintenance or operating cost. Say which requirements drive that cost, what could be simplified or deferred, and what the user would lose. Back claims with repository evidence where you have it, label assumptions, and describe effort and risk in words rather than scores or probabilities.
  • Meet Presenting decisions in orchestrate-sessions for every key decision. In particular, give each option what users experience and its prior art: what leading apps or products do for the same behaviour, marked verified (with the source) or unverified. Label product decisions, including anything the system does on a user's behalf, and keep them out of technical batches.
  • Recommend one option and say what the person must accept if they take it.
  • A decision blocked on a missing fact becomes a spike or a question answered with the research-web skill.
  • Revise the document in place as the person learns. Record why options changed under "What we learned".

Socrates

When the person says they are ready to pick, send the brief and this document once to a fresh-context Socrates reviewer, briefed as in create-ticket's Socrates reference, with repository access. Also ask it to argue for less (what can be deferred, which schema changes, dependencies, or infrastructure can be avoided, whether the smallest version is really the smallest) and to challenge every ladder rung that lacks a stated reason. Relay its material questions. Record its verdict (pass, clarify, or rethink) against the revision it reviewed. Continue the same Socrates agent through follow-ups, two rounds at most. Socrates investigates facts and asks questions. The person settles product choices. Skip Socrates for small decisions.

Output

An HTML page for the person, laid out as in references/options-template.md and rendered with the page house standard. Save it as options.html in the work's bundle. End with the status line and wait.

Banned

  • Implementation steps, file-level changes, task breakdowns
  • Picking on the person's behalf
  • Starting the plan before there is an explicit pick

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 Options AI skill do?

Use when the person asks what to do or for trade-offs, or more than one design is live. Waits for a pick. Never plans.

Why use Options on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/greenfield-inc/Pane/tree/main/main/src/services/paneChatBundle/skills/options. 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 Options?

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 Options?

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

Is the Options AI skill free?

It is published on GitHub by greenfield-inc. Check the repository for licensing terms. 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 👇