Idea To Design Doc logo

Idea To Design Doc

Community
AkoliteZA
idea-to-design-doc

Use when turning a rough idea into a focused product/design Markdown doc through guided questions, without moving into implementation too early.

Overview

PublisherAkoliteZA
Repositoryhermes-agent-idea-workflow
Skill nameidea-to-design-doc
Stars
275
Forks
24
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 AkoliteZA on GitHub. Read the source before you install it.

Installation

Install the Idea To Design Doc 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/AkoliteZA/hermes-agent-idea-workflow/tree/main/idea-to-design-doc
  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/AkoliteZA/hermes-agent-idea-workflow.git /tmp/hermes-agent-idea-workflow
mkdir -p .claude/skills
cp -r /tmp/hermes-agent-idea-workflow/idea-to-design-doc .claude/skills/idea-to-design-doc
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Idea To Design Doc 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 Idea To Design Doc 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 Idea To Design Doc 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.

Idea to Design Doc Workflow

Use this skill when the user says things like:

  • "I have an idea for an app"
  • "Help me flesh out this product"
  • "Turn this thought into a design doc"
  • "Make me a list of ideas and link each one to a note"

Goal

Convert a rough idea into a structured design document with:

  1. A master ideas index
  2. One markdown note per idea
  3. A guided interview that stops when the user says stop, that's enough, or done
  4. The product idea, philosophy, intended experience, and practical technical shape needed to understand the app

This workflow starts with product thinking and only moves into technical aspects after the concept/philosophy is clear. The design doc should capture what the user wants and enough technical direction to support a later build plan.

Important constraints

  • Do not push into backend, frameworks, database design, or code architecture too early.
  • First capture product intent, behavior, audience, layout, features, UX, and philosophy.
  • Then, when drafting the design doc, include the relevant technical aspects: platform assumptions, major system components, data needs, integrations, constraints, and likely architecture questions.
  • For Full mode or build-bound ideas, recommend sensible technical defaults first, then let the user accept or change them. Cover database/storage, hosting/deployment, backend/runtime, frontend/UI, auth, platform targets, and other technical pieces only after the product direction is clear.
  • Ask one question at a time when possible.
  • If the user gives a short answer, follow up with a narrower question.
  • If the user says to stop, immediately draft the note from what you have.

Default storage layout

Save files locally first, rather than directly into the Obsidian vault.

Recommended local folder structure:

  • ./ideas/Ideas Index.md
  • ./ideas/<idea-title>.md

If the user later wants Obsidian export, treat that as a separate export step.

Lite vs Full mode

Use Lite mode for quick idea capture: ask only enough to produce a useful note. Use Full mode when the user wants a durable design doc or eventual implementation handoff.

The user can force the next stage with the exact phrase GREENLIGHT NEXT STAGE. If they use it, stop questioning, draft with current information, and record gaps under Open questions.

Interview flow

Ask questions in this order, adapting to the user's answers. For stronger prompts, use idea-superpowers-suite/references/interview-question-bank.md:

  1. Working title
    • "What should we call this idea for now?"
  2. Problem / purpose
    • "What problem does it solve, or what is it for?"
  3. Audience
    • "Who is it for?"
  4. Core behavior
    • "What should it do when someone uses it?"
  5. Primary user flow
    • "What is the main thing a user should be able to do from start to finish?"
  6. Key features
    • "What are the must-have features?"
  7. Layout / organization
    • "How should the main parts be arranged or grouped?"
  8. Data location / hosting preference
    • "Should the data stay local, be self-hosted, go to Cloudflare/AWS/another cloud, or is that undecided?"
  9. Platform targets
    • "Should this be web-only, or should it also have a Windows app, Mac app, cross-platform desktop app, mobile app, or responsive mobile web?"
  10. Recommended technical defaults
  • "Based on this idea, I recommend these technical defaults: . Do you want to accept them or change any part?"
  1. Preferences / feel
  • "Should it feel simple, playful, serious, fast, calm, etc.?"
  1. Non-goals
  • "What should this not do?"
  1. Success criteria
    • "How will you know this idea is good enough to move forward?"

Interview style

Use prompts like:

  • "Tell me more about that part."
  • "What would happen next?"
  • "Can you give an example?"
  • "Is that a must-have or a nice-to-have?"
  • "Do you want it to be simple or more feature-rich?"

If the user is unsure, offer lightweight options instead of open-ended pressure:

  • "Do you want this to be more like a list app, an overview page, or a single-focus tool?"
  • "Should users see everything at once, or step through it one section at a time?"

Stop condition

If the user says any of the following, stop interviewing and draft immediately:

  • stop
  • that's enough
  • enough for now
  • done
  • draft it
  • write it up
  • GREENLIGHT NEXT STAGE

Output format

When drafting, produce a markdown note with this structure:

markdown
# <Idea Title>

## One-line summary

## Problem / purpose

## Product philosophy

## Target user

## Core concept

## Desired behavior

## Key features

## Layout / information architecture

## UX / product notes

## Technical shape

## Data / integrations / platform needs

## Hosting / data location

## Platform targets

## Recommended technical defaults

## Non-goals

## Open questions

## Next steps

Master index format

Maintain Ideas Index.md as a simple bullet list of idea notes:

markdown
# Ideas Index

- [[Idea Title]] — short one-line summary
- [[Another Idea]] — short one-line summary

If the index file exists, append the new idea in alphabetical or newest-first order, but stay consistent.

Suggested response behavior

During the interview:

  • Be conversational and concise.
  • Ask a question, then wait for the user's answer.
  • Keep the scope on product/design thinking.

When the user stops:

  • Summarize the idea clearly.
  • Capture uncertainties under Open questions.
  • Save the note locally.
  • Add/update the local index.
  • Give the user the local note path.

Quality bar

A good result should make it easy to revisit the idea later and immediately understand:

  • what it is
  • who it is for
  • how it should behave
  • what matters most
  • what is intentionally out of scope

Frequently asked questions

What does the Idea To Design Doc AI skill do?

Use when turning a rough idea into a focused product/design Markdown doc through guided questions, without moving into implementation too early.

Why use Idea To Design Doc on TypingMind?

Because you install it once and use it with any model. Idea To Design Doc 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 Idea To Design Doc in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AkoliteZA/hermes-agent-idea-workflow/tree/main/idea-to-design-doc. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Idea To Design Doc?

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 Idea To Design Doc?

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

Is the Idea To Design Doc AI skill free?

Yes. It is published on GitHub by AkoliteZA 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 👇