Cosa contiene

Un file SKILL.md (la guida operativa) + un modello di partenza. Un'anteprima:

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

1. 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.
2. 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.
3. 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.
4. Give each slide one visual job (input: styled slides → output: finished slide set)
   Alternate slide types so the eye never gets bored: full-gradient title, white slide with one big number, gradient band with a single image, two-panel comparison, quote slide, closing ask. One image per visual slide, full-bleed or large — cropped tight, no clip-art, no watermarked stock. Every slide gets the same footer (talk title + page number) and the same margins; consistency is what makes a simple system look professional. Aim for at least 40% empty space on every slide — whitespace is part of the design, not wasted room.
5. Rehearse and trim (input: finished slide set → output: talk-ready deck)
   Read the headlines in order, out loud, with no notes: they should tell the whole story in 30 seconds. Time the talk — if you're over, cut slides, never speed up. Check the deck on the actual projector or screen if you can: soft gradients shift on dim displays, so verify text contrast on the real output. Export as PDF as a backup (fonts embedded), and keep the editable source so the next talk is a refill, not a rebuild.

Anteprima del modello

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}

Il pacchetto della skill (SKILL.md + modello) è scritto in inglese.

Acquista il pacchetto completo della skill — $4.99 Pro — tutte le 511 skill