TypingMindTypingMindThe best frontend for AI
Make Static Ads Find References logo

Make Static Ads Find References

OrganizationPopular
gooseworks-ai
make-static-ads-find-references

Step of make-static-ads: picks a template for every ad in its chosen style, after its visual idea and style are set, from the brand's own ads, the GooseWorks library or category leaders, and records what the chosen creativity level keeps from it. Run make-static-ads instead; not for direct use.

Overview

Publishergooseworks-ai
Repositorygoose-skills
Skill namemake-static-ads-find-references
Stars
1.3K
Forks
219
Bundled files
1
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • 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 gooseworks-ai on GitHub. Read the source before you install it.

Installation

Install the Make Static Ads Find References 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/gooseworks-ai/goose-skills/tree/main/skills/marketing/make-static-ads-find-references
  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/gooseworks-ai/goose-skills.git /tmp/goose-skills
mkdir -p .claude/skills
cp -r /tmp/goose-skills/skills/marketing/make-static-ads-find-references .claude/skills/make-static-ads-find-references
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Make Static Ads Find References 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 Make Static Ads Find References 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 Make Static Ads Find References 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.

find-references

Reads: each board row's angle, message, visual idea and style; the chosen level (../make-static-ads/references/levels.md); profile.md. Writes: the Template column of board.md and a short template list under the board (source, its template id from ads_template_read when it has one (library or the brand's own imported ad), page link, the image's public https URL (a brand's own ad from a page or file goes through gooseworks:media_upload first), whether its image goes to the model at this level, and what it keeps).

Every ad has a template. Without one the image model falls back on its own default layout, and every brand's ads end up looking the same. A template is a finished ad with a layout: text slots, blocks, a background treatment. A plain product photo or lifestyle shot is not a template; it is a style reference at most.

1. Where to look (free first), in this order

  1. The brand's own ads (its past and running statics, from profile.md). They already look like the brand (whether their image may go to the image model: ../make-static-ads/references/levels.md).
  2. The GooseWorks template library: gooseworks:ads_template_read mode: "static_library" with a query for the layout or device the visual idea needs. Open each candidate's detail and look at the image. Name a library source as such, never as a verified running ad.
  3. Category leaders and inventive brands from other categories in the Meta Ad Library, in the host browser (routes in ../make-static-ads/references/brand-profile.md §1): the first 20 or so statics of 2–3 advertisers.

Each set uses at least one template from outside the GooseWorks library (the brand's own ads, a leader, or another category's inventive brand). If none of those can be opened, say which you tried on the board.

Look at every candidate's image before choosing. Reject fixtures, placeholder brands, illegible layouts and templates whose text slots can't carry this ad's message.

2. Choose the template after the idea

Pick a template in the row's chosen style whose layout fits the visual idea: one big object needs a hero layout, a comparison a split, a list a stacked layout. Spread the set across different templates and advertisers; two ads on one template must differ in message and visual idea.

3. Record what this level keeps (levels.md)

What each level keeps, and whether the image goes to the model: the table in levels.md.

Describe what you actually see in the template: block positions and rough sizes, background, product position and scale, each text slot's position, length and weight. Don't credit it with things you're adding.

4. Rights

This section is the one home of template rights. What may go into image_urls (at close and balanced, levels.md): the brand's own ads and GooseWorks library templates (made for remixing). Ads of other brands found in an ad library never go in, at any level. From any template keep none of another brand's product, words, logo, people or signature look. A direct competitor's template gives layout only. If a buyer could mistake ours for theirs (cover both logos and look side by side), change the picture and the words. Borrow devices, craft and abstract layout only; a celebrity or expert in a template is a slot for the brand's own endorser with permission, never a generated lookalike.

5. Showing them

Keep three looked-at candidates per ad: the chosen one and two alternates in other styles (../make-static-ads/references/levels.md, Style), so the marketer can switch the look. The marketer must see all three as images before paying, even after "your choice": on a shell host make one sheet per ad with ../make-static-ads/scripts/template_sheet.py (chosen first, each captioned with its letter, source and style) and show it to the marketer, not only to yourself: if the host has a send-file tool, send it (Claude Code desktop: SendUserFile, display: "render"); in a terminal, open it and give its full path; in an app that shows images, attach it. Viewing it with your own image reader does not count. With no shell, show the three images the same way, or their links when the host can't show images. The board says so (../make-static-ads/references/handoff-format.md §2).

Done: every ad has a chosen template and two looked-at alternates in other styles, each with its source and what the level keeps; at least one template comes from outside the library, or the board says what was tried.

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 Make Static Ads Find References AI skill do?

Step of make-static-ads: picks a template for every ad in its chosen style, after its visual idea and style are set, from the brand's own ads, the GooseWorks library or category leaders, and records what the chosen creativity level keeps from it. Run make-static-ads instead; not for direct use.

Why use Make Static Ads Find References on TypingMind?

Because you install it once and use it with any model. Make Static Ads Find References 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 Make Static Ads Find References in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gooseworks-ai/goose-skills/tree/main/skills/marketing/make-static-ads-find-references. 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 Make Static Ads Find References?

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 Make Static Ads Find References?

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

Is the Make Static Ads Find References AI skill free?

Yes. It is published on GitHub by gooseworks-ai 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.

Related AI Skills

View all
anthropics logo

Brand Guidelines

anthropics
OrganizationPopular

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual…

21.8K
184K
Instructions
View
openclaw logo

Solid

openclaw
OrganizationPopular

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

82.4K
391.7K
9 files
View
openclaw logo

Canvas

openclaw
OrganizationPopular

Present hosted widget documents on a connected macOS panel and control panel visibility or navigation.

82.2K
391K
Instructions
View
openclaw logo

Diagram Maker

openclaw
OrganizationPopular

Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.

82.2K
391K
2 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇