Crew Roster Slides

Make team introduction decks that read like a staff feature in a printed magazine: who the people are, what each of them looks after, how work moves between them, what they achieved and the habits they share, with Bodoni Moda headlines, warm paper pages, round stamps and soft-cornered portraits.

Crew Roster Slides

Bring the team, the audience, names, roles, figures to use exactly and the page count; team photographs are optional. The Skill returns one offline HTML deck that edits in the browser and exports editable PowerPoint.

How it works

  1. Brief and sequence

    Your Agent asks for the topic, the audience, what should happen after the talk, the facts and numbers to use exactly and the page count, then gives every page one layout and picks one palette.

  2. Pictures and build

    Without your team's photographs it lists the people in art.json and draws them with portrait-art.py, one seed per person so each person looks the same on every page. It writes plan.json and settings.json, then runs kit.py compose, make-deck.py and verify-deck.py to build one offline HTML file.

  3. Look and export

    It opens every page in a browser and checks wraps, overlaps and labels, tries edit, undo, save and present, then exports PowerPoint and runs verify-pptx.py against the deck.

Frequently asked questions

Is the PowerPoint really editable?

Yes. Headlines, names, roles, rows, stamps, caption slips, bars and rules are native PowerPoint objects with speaker notes; each portrait is its own picture and no slide is a full-page image. The example decks have 96 and 89 text boxes.

Where do the pictures come from?

Your team's photographs first. Otherwise the bundled portrait-art.py draws anonymous duotone studio portraits, groups, seated teams and work corners in the deck's two inks. It uses only the Python standard library and calls no model or image service. A person who appears on two pages keeps the same seed, so they are drawn as the same figure.

Which fonts does it use?

Bodoni Moda for headlines and Onest for copy, both under the SIL Open Font License. Install both on the presenting machine for matching line breaks; PowerPoint has regular and bold only, so headline weights export as bold. Chinese, Japanese and Korean use the system face with smaller display sizes.

What are the known limits?

Generated portraits are generic figures, not likenesses. Bars are drawn to the widths in the plan, not computed from the values. Geometry is fixed per layout: four roster slots, five bars and three rows, duties, stages or habits.

What was tested?

Both example decks were built from a fresh unzip of the package. Every page was inspected in Chrome and in a LibreOffice render of the exported PowerPoint, 31 browser interaction checks and 17 error-path checks passed, and python-pptx edits survived save and reopen. PowerPoint, Keynote and WPS were not opened.