big-pics-little-words is a short prompt-style skill for turning the current conversation into a visual explainer. The agent builds an HTML page that shows the subject with large visuals and terse, jargon-free text, written as if the viewer is new to the topic.
It leaves the design to the agent’s taste, asks for real pictures or icons only where they help, and is set to run only when you invoke it by name.
What You Get
- An HTML page that explains the current subject visually
- Large visuals with short captions that keep the key details
- Real-world pictures or icons used selectively where they clarify
- Everyday-language prose with jargon removed
Common Use Cases
- Understanding a complicated architecture the agent just described in text
- Explaining a bug or a design decision to a teammate who was not in the conversation
- Turning a long planning discussion into a page you can skim in a minute
- Giving a newcomer an orientation to a codebase or a topic
What Makes It Unique
It is deliberately minimal, with no template, house style or checklist to follow. The skill sets one preference, show more and say less, and leaves layout, imagery and visual direction to the agent. It is a sibling of the one-pager skill, which aims the same idea at sharing with teammates.
Under The Hood
The skill is a single short instruction file with no scripts, and its frontmatter keeps the model from invoking it automatically. The agent writes an HTML file to your workspace. The instructions ask for real-world pictures where they help, so the agent may fetch or reference images from the web, and you should check what ends up on the page.