Create logo

Create

Organization
imgly
create

Use when the user asks to create / generate / make a NEW design from a prompt — a deck or slides, poster, flyer, social post, business card, a video (animated post, reel, clip with music or voiceover), or a custom-size canvas. Runs the guided intake: derive every brief parameter the prompt already answers (class, format, audience, vibe, brand, content), ask ONLY the missing questions — one round, chip-style options, "Decide automatically" defaults — then echo the design brief and hand off to the handbook Loop. A brief given to the /codesign prompt lands here as the stated input.

Overview

Publisherimgly
Repositorycodesign
Skill namecreate
Stars
43
Forks
1
Bundled files
2
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.

  • 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 imgly on GitHub. Read the source before you install it.

Installation

Install the Create 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/imgly/codesign/tree/main/plugins/codesign/skills/create
  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/imgly/codesign.git /tmp/codesign
mkdir -p .claude/skills
cp -r /tmp/codesign/plugins/codesign/skills/create .claude/skills/create
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create 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 Create 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 Create 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.

create — derive-then-ask intake for a new design

Turn "make me a deck / poster / post" into a structured design brief before any edit runs. The one rule:

Derive every parameter you can from the prompt. Ask only the questions the prompt left unanswered. If nothing is missing, don't ask anything — build.

That rule is not local to this skill: it is the shared intake contract in ../handbook/intake.md, which brand, resize and localize follow with their own parameter tables. This skill is its worked example — the five steps below are that contract plus the class system it needs. Read the contract for the parts this skill doesn't restate: the never-invent rule, data-driven chips, and why a handoff from another skill counts as input already given.

This skill owns the intake only. Zero design rules live here — the brief hands off to the handbook Loop (which owns how to build) and the judge gate (which owns done).

Bundled files: classes.md — the full per-class parameter tables and derivation notes. Read it once you know (or must ask) the class. choice-copy.md — the grammar every question and chip must follow; read it before wording any question of your own.

The intake protocol

Five steps, in order:

  1. Classify. Map the request to a design class: deck, poster, flyer, social-post, business-card, video, or custom (explicit dimensions). If the class is ambiguous, it becomes the first — often only — question. A request for motion, a reel, an mp4, music or a voiceover is video. A launch or promo video for a product or project goes to the launch-video skill instead, which runs its own intake.

  2. Derive. Fill the class's parameter table (see classes.md) from everything already available: the prompt, earlier conversation, attached files/images, a provided brand kit. A parameter counts as answered if it is stated explicitly ("10-minute investor pitch") or safely inferable ("for our Series A roadshow" → audience: investors). Track each value's source: stated, inferred, or default. A brief passed to the /codesign prompt counts as stated.

  3. Ask — once. Collect the still-unanswered parameters the class marks ask and put them to the user in a single round, phrased as the class's canned questions with their chip options. Ask through your own environment's question UI whenever it has one — a structured question tool, an elicitation API, any form-style UI: options become chips, "Other" stays free. Only when your environment offers nothing at all, fall back to one compact markdown form listing only the missing questions. The threshold for asking at all is countable, not a judgement call: two or more of the five design-defining parameters (topic, audience, visual direction, brand, format) neither stated nor inferable → you ask. And visual direction and brand are never silently defaulted on a first build — see ../handbook/intake.md. Never ask a second round: if an answer is still vague, take the default and say so in the brief. Every question offers "Decide automatically" — only required parameters (usually just the topic/content) have no default. Word every question and chip by choice-copy.md: system-POV headers, verb-led titles, no pronouns in titles, and each value list internally parallel.

  4. Brief. Echo the assembled brief in 3–6 lines — class, format, audience, vibe, brand, content plan, content language — tagging inferred and defaulted values ("audience: investors, inferred") so a wrong derivation is correctable at a glance. Write the brief in the user's language (handbook §1), and when the design's content language was defaulted from the conversation rather than stated, say so on its line: it is the one derivation the user cannot see coming. Don't block on confirmation: state the brief and proceed, unless the user asked to see options first (or picked "Explore a few options" for the vibe — see below).

  5. Hand off. Enter the handbook Loop: build the scene from scratch in your first edit (await engine.design.create({ type: 'scene', children: [page] })), with format/page setup from the class's derivation notes. Consult brand if a brand kit is in play; finish through the judge gate and the save (export({ format: 'imgly' })) as always — an unsaved design is one the user never receives.

Exemplar: the deck intake

The canonical question set — offer these chips verbatim when asking:

  1. What's the deck about? — free text: topic, purpose, key points or content already in hand. Required — the only question with no default.

  2. Who's the audience? — Executives / leadership · Team / internal · Customers / prospects · Investors · Broad / public · Other. Default: inferred from topic, else broad/public.

  3. How long is the talk? — ~5 min · ~10 min · ~20 min · ~30+ min · Decide automatically · Other. Derives slide count ≈ 1.5 × minutes, clamped to 5–30. Default: ~10 min.

  4. What visual vibe would you like? — Clean & minimal · Bold & editorial · Corporate / professional · Warm & friendly · Explore a few options · Decide automatically · Other. Default: decide from topic + audience. Explore a few options → build 2–3 style frames of the title slide first, preview them, let the user pick, then continue the deck in the chosen direction.

    This question is asked, not defaulted, on any first build where the direction is not implied by the request, a supplied brand kit, a reference image or a prior design. It is the parameter the user sees first and the one a skipped intake invents most often.

    Explore a few options is every class's remedy, not just deck's — whenever direction is the only thing left open and the user takes Decide automatically, prefer building 2–3 style frames of the first page, previewing them, and asking which. Showing options costs one round of real work and answers the question far better than adjectives do; it is explicitly not the forbidden "second round".

  5. Any color or brand preferences? — free text: brand colors, hex codes, neutral / monochrome, or an attached brand kit. Blank → designer's choice. A brand kit routes through the brand skill.

  6. Do you have the content? — Provide the content · Provide rough notes · Draft from the topic · Other. Default: draft from the topic.

The other classes follow the same pattern with their own parameters and formats — all specced in classes.md.

Worked examples

  • "Series A pitch deck for our robotics startup, 10 minutes, use our brand kit (attached), content in the attached notes." → class, topic, audience, length, brand, and content are all stated or inferable → zero questions. Echo the brief, build.
  • "Make me a deck about Q3 results." → topic stated; ask audience + length + vibe in one round; brand and content take defaults, stated in the brief.
  • "A poster." → nothing but the class is known → ask the poster question set in one round (topic required; venue, vibe, brand, imagery with defaults).

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 Create AI skill do?

Use when the user asks to create / generate / make a NEW design from a prompt — a deck or slides, poster, flyer, social post, business card, a video (animated post, reel, clip with music or voiceover), or a custom-size canvas. Runs the guided intake: derive every brief parameter the prompt already answers (class, format, audience, vibe, brand, content), ask ONLY the missing questions — one round, chip-style options, "Decide automatically" defaults — then echo the design brief and hand off to the handbook Loop. A brief given to the /codesign prompt lands here as the stated input.

Why use Create on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/imgly/codesign/tree/main/plugins/codesign/skills/create. 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 Create?

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 Create?

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

Is the Create AI skill free?

Yes. It is published on GitHub by imgly 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 👇