Soft Gradient Deck
Calm slides, one idea each
Builds a presentation deck with soft low-saturation gradient washes, generous whitespace, and one full-sentence headline per slide, for talks that feel calm instead of corporate.

Install it in 3 steps
No sign-up. No CLI tools. Pick your AI, copy one line, paste it over.
Prefer doing it yourself? Buy the skill ($4.99), download the ZIP from your checkout confirmation, unzip it into the directory shown above, restart your AI session — same result. Already bought it? Your AI assistant can download it for you.
What’s inside
One SKILL.md (the playbook) + one starter template. A preview:
Soft Gradient Deck
When to use
- You're giving a talk, pitch, or team update and your current deck is a wall of bullet points on white
- You need a deck that looks designed but you have no designer and no time to learn a design tool
- Your slides have to work for a friendly audience — a workshop, a community talk, a product demo — where a hard-edged corporate template feels wrong
- You're repurposing a dense document into a deck and need a structure that forces brevity
- You want one reusable template your whole team can fill in without breaking the look
Workflow
- Find the spine (input: topic + audience + time → output: 1-sentence spine + slide list)
Write one sentence the audience should remember after the talk — that's the spine. Then list the slides as a story, not a table of contents: problem → tension → idea → proof → what changes → ask. A 10-minute talk gets 8–10 slides; a 20-minute talk gets 12–15. If a slide doesn't move the spine forward, cut it now — gradients can't save a deck with no spine, and one idea per slide is the rule that makes the rest work. - Write the slides as headlines (input: spine + slide list → output: headline per slide)
Every slide gets one headline that IS the point, written as a full sentence ("Onboarding takes 2 weeks — most of it is waiting"), not a label ("Onboarding"). Supporting content is 1–3 short lines, one number, or one image — never a paragraph, never more than 6 bullets, and most slides should have zero bullets. Speaker notes hold the detail; the slide holds the idea. If you can't write the headline as a sentence, you don't yet know what the slide is saying. - Apply the gradient system (input: headlines → output: styled slides)
The look: soft, low-contrast gradients — two neighboring colors (peach→rose, sky→mint, lilac→blue) at low saturation, flowing diagonally or top-to-bottom, with large areas of near-white or near-black breathing room. Text sits on the lightest part of the wash, never across a busy color transition. One typeface, two weights (bold headlines, regular body), headline 40–54px, body 20–24px. Charts use the gradient's own palette at higher saturation so they read as part of the design, not pasted in from another deck.
Template preview
Soft Gradient Deck — Template
One spine, one headline per slide, one idea per slide. Fill the spine and headlines first; style last.
Talk: {title} · Audience: {who} · Length: {10 / 20 / 30} min · Slides: {8–10 / 12–15}
Spine (one sentence the audience should remember): {sentence}
Slide list (story order: problem → tension → idea → proof → what changes → ask)
*(Add or remove middle slides to fit the talk length — cut slides, never speed up.)*
Gradient system (one family per deck)
Color pair (neighboring, low saturation): {e.g. peach → rose} · Direction: {diagonal / top-to-bottom}


