HTML Slides
A polished, animated deck planned one idea per slide, with speaker notes.
Creative · produces a Slides · built in, ready to run
What you give it
Whatever the job is about — a block of text, a URL, a name. It arrives below the instructions, fenced and labelled as data, so nothing inside it can rewrite the procedure.
Tools it uses
Restricted to these, and nothing else:
create_presentationsearch_inforead_pagegenerate_image
Fewer tools means fewer ways to do the job, which is what makes the result the same next week. If one of these needs an app you have not connected, the skill says so rather than failing quietly.
What it reads
This skill carries material of its own. None of it is loaded up front — the assistant opens a file when the job calls for it, and leaves the rest alone.
| File | What it holds |
|---|---|
references/deck-shapes.md |
Deck shapes by type |
The procedure it follows
This is the skill, in full. Add it to your own skills to change any of it.
Decide the deck type, the length (8 for a pitch, 10 to 12 for a lesson, 6 for a status update unless asked) and the one-sentence takeaway; research real figures with search_info and read_page when the deck makes claims. Write the outline one slide per idea, each title a short takeaway sentence and each summary one line with the real figure and its source; slide 1 is the takeaway, the last slide is the ask. Write speaker notes per slide in the reply. Generate an image with generate_image (16:9, no text) only for up to three slides whose visual carries the point, and put its URL in that slide's summary. Call create_presentation once with the title in the user's language, a full English prompt, slide_count, outline, deck_topic and a one-line style_request; afterwards reply with one short line and do not describe the slides.
How to run it
| Where | How |
|---|---|
| Chat | "Run my HTML Slides skill", or pick it from the + menu |
| Skills page | Find HTML Slides under Library and press Add & Use |
| Automations | Invoke it on every trigger |
| API | POST /v1/skills/{id}/run — add it to your own skills first, then take the id from GET /v1/skills |
In chat, on the Skills page and in automations you do not have to add it first — a library skill runs as it is. Adding it makes an editable copy under your own skills, which is what you need to change the wording, and what the API works against.
New to skills? Start with what a skill is.
Open App