Baoyu Cover Image
Převádí article content na fully specified, reproducible cover-image prompt across 6 confirmed dimensions.
Funguje s nastavením
Co umí
Spouští structured workflow — preferences file, content analysis, a 6-dimension confirmation step (type/palette/rendering/text/mood/font), then a saved reusable prompt file — before handing off to whatever raster image backend the runtime provides (Codex imagegen, Cursor GenerateImage, or the separate baoyu-image-gen skill). Spouští se na explicit phrasing like 'generate cover image', 'create article cover', or 'make cover'. Actual image rendering (Step 4) requires one of those external backends; none is bundled.
Testovací report
Požádal jsem ho, aby concept a cover pro a remote-work article: its auto-selection tables turned raw content signals into a fully resolved, reproducible prompt spec (type=conceptual, palette=elegant, rendering=digital, mood=subtle, all keyword-justified) versus a single ad-hoc paragraph from scratch — genuinely more systematic. But Step 4 dead-ends in a stock Claude Code setup: it requires Codex's imagegen, Cursor's GenerateImage, or a separate baoyu-image-gen skill to actually render a bitmap, and none of those exist here, so the deliverable stops at a prompt file, not an image.
Testováno: 2026-07-14 · Claude Code 2.x (agent harness)
Instalace
git clone https://github.com/JimLiu/baoyu-skills cd baoyu-skills mkdir -p ~/.claude/skills cp -r skills/baoyu-cover-image ~/.claude/skills/baoyu-cover-image
Příkazy a ukázkové prompty
/baoyu-cover-imagePřevádí article content na fully specified, reproducible cover-image prompt across 6 confirmed dimensions.
Skilly se spouštějí běžnými požadavky — žádné příkazy k zapamatování. Po instalaci ho aktivují prompty jako tyto (anglicky):
Generate a cover image prompt for my blog articleCreate a cover image for a remote-work postDesign an article cover prompt with style rationale