/youtube-thumbnail-generate

name: youtube-thumbnail-generate
description: >
  Generate on-brand YouTube thumbnails for Ben van Sprundel using Higgsfield in
  one shot. Use when the user says create a thumbnail, make a YT thumbnail,
  thumbnail for video, generate ben thumbnail, variation of last thumbnail, or
  shares a video concept and asks for a thumbnail. Auto-infers mode from the
  inputs (variation, new-with-ben, ben-plus-other, no-face), defaults to 3
  variants, and asks at most one question. Uses reference images as the identity
  anchor (a current photo of Ben from refs/, plus optional past thumbnails or
  style anchors). No Soul training is required. Reads the locked style spec at
  Context/youtube-thumbnail-style.md if present. Real logos are never rendered.
  The thumbnail fills its frame edge-to-edge; the user composites the actual
  logo on top in post.

YouTube Thumbnail Generate

One-shot thumbnail generation. Takes a concept (plus optional reference image and count), infers everything else, ships 3 variants and a manifest.

Inputs

Two things, ideally both in the user's first message:

1. **Concept** — what the thumbnail should show. A sentence or phrase. ("Claude Code Skills, why it changes everything for solo founders") 2. **Reference image(s)** (optional but recommended, may be multiple) — a past thumbnail, a photo of Ben, a second subject, a style anchor, a real logo PNG, or any combination. Determines the mode AND ALL of them must be passed into the generation. Never silently drop a user-supplied reference; if they gave you one, it has to end up in `medias[]`. If they gave you a LIST, read EVERY image in the list, then pass every relevant one to `medias[]` (don't pre-select just one). Also: every reference image MUST be visually read (via the `Read` tool on the file path) before the prompt is built, so the prompt captures each reference's actual style, texture, palette, composition, and recurring motifs rather than relying only on the style spec defaults.

**If the user mentions a reference image but does not provide a path or attachment, ASK for the path BEFORE doing anything else.** Examples that require asking: "use my previous thumbnail as a ref" (which file?), "include the Anthropic logo" (where is the PNG?), "match this style" (which image?). Ask in one short line: *"Got it — what's the file path for the reference image?"* Do not guess, do not proceed, do not generate without seeing the path.

Optional third: **variant count**. Defaults to 3. Max 4.

If the concept is missing or genuinely unclear, ask ONE combined question:

> "What should the thumbnail show, and how many variations do you want? (default 3)"

Do not split into multiple questions. Do not ask about mode, model, or palette; all of that is inferred or read from the style spec.

Identity Anchor (no Soul required)

Every `new-with-ben` thumbnail uses a reference photo of Ben as the identity anchor, passed as `medias[0]`. The photo lives at `Projects/youtube/thumbnails/refs/ben_reference_{YYYY-QQ}.jpg`.

If the user did NOT attach a photo of Ben and there is no `ben_reference_*.jpg` in `refs/`, ask once for a photo. Without it, `new-with-ben` cannot produce a faithful Ben rendering.

If multiple `ben_reference_*.jpg` files exist, pick the most recent (highest `YYYY-QQ` suffix). Note which one was used in the manifest.

Mode Auto-Inference

| User attached | Concept hints | Mode | Model | Reference flow | |---|---|---|---|---| | 16:9 image that looks like a past thumbnail | "vary this", "tweak this", "redo with X" | `variation` | `nano_banana_2` | past thumbnail as `medias[0]` | | A portrait of Ben | Ben centered in the concept | `new-with-ben` | `nano_banana_2` | user-supplied photo as `medias[0]` | | Two images (Ben + something) | "Ben plus X" | `ben-plus-other` | `nano_banana_2` (multi-ref) | Ben as `medias[0]`, second subject as `medias[1]` | | No image | Object or abstract concept, no Ben | `no-face` | `nano_banana_2` (or `gpt_image_2` if concept centers on rendered text) | optional style anchor as `medias[0]` | | No image | Concept mentions Ben | `new-with-ben` | `nano_banana_2` | most recent `ben_reference_*.jpg` from `refs/` as `medias[0]`. If none, ask. |

`nano_banana_2` is the default model for every mode. Switch to `gpt_image_2` only when text rendering is the hero element of a no-face thumbnail.

Style Spec Handling (silent)

Read `Context/youtube-thumbnail-style.md` if it exists. Pull:

• Palette, framing library, expression library, lighting, prohibited list, anchor refs

If the spec is missing or has `[FILL]` blocks: don't refuse. Fall back to the locked Ben AI thumbnail visual language (see `references/visual-language.md` for the full catalog). Built-in defaults:

• **Palette**: deep charcoal `#1F1F1F` background with subtle dot-grid texture, signature coral `#E97B5D` accent on folders / app icons / asterisk marks, white `#FFFFFF` for primary text and hand-drawn arrows, near-black `#0A0A0A` for text on light backgrounds
• **Layout**: Ben on the right third, text and supporting visuals on the left third, one hand-drawn white curved arrow from text toward the visual
• **Framing**: chest-up, Ben on right third
• **Expression**: slight smile (default), focused neutral for analytical topics
• **Wardrobe**: plain black t-shirt or hoodie
• **Lighting**: soft front-left key, gentle rim from behind, no hard shadows
• **Banned colors**: navy blue, royal blue, sky blue, pure red, magenta, purple (except Obsidian purple for Obsidian topics), green, neon variants
• **Prohibited**: real logos rendered by the model, empty rectangles or reserved gaps in the composition, centered composition when Ben is in frame, multiple arrows, cartoon/illustrated rendering of Ben, em dashes
• **Logos**: never reserved as a gap in the render. The thumbnail fills edge-to-edge. Logos are composited on top in Figma or Canva on the winner.

Surface a one-line note at the end (not before generation): "Style spec missing or inc