Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →zsyggg/paper-deck
将论文、技术文章或知识内容制作成高真实感的 AIGC 幻灯片。先做叙事结构和逐页视觉导演，再调用生图模型生成每一页 16:9 slide image，最后合成为 PPTX/PDF。适合论文汇报、组会、公开课、技术分享、商业化研究展示；当用户提到“论文PPT”“AI生成PPT”“不像AI的PPT”“高质感幻灯片”“逐页生图PPT”时使用。
Passed 12 of 17 test cases with the skill, and 6 of 17 without it.
and 10 more in the full report
9 fixed6 passed either way5 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
My co-author wants fully editable body text over AI-generated visual backgrounds for our deck at `paper-deck/solar-cell`. When adopting this hybrid overlay approach, what record-keeping requirement must be fulfilled in `deck-brief.md`?
| Checked | Without skill | With skill |
|---|---|---|
| Record the presence of a mixed text layer in deck-brief.md. | Missed | Passed |
The instructions your model reads when the skill loads.
把论文/知识内容做成看起来真的被设计过的幻灯片。
核心路线不是用 PPT 对象硬摆版式，而是：
Paper Deck 的 V1 是 raster-first AIGC slide image 工作流。除非用户明确要求“不要生图”“用代码画图”“只要可编辑 PPT”或“使用 HTML/SVG/Canvas 生成”，否则必须调用真实的 raster image generation backend 为每一页生成图片。
严格禁止把以下产物冒充为本 skill 的“生图页”：
允许的本地处理仅限：
deck-brief.md 和交付说明中明确记录“混合文字层”，不能声称整页文字都由生图模型完成如果当前环境没有可用的 raster image generation backend，必须停止并说明缺少生图后端；不要退化成本地绘图替代方案。
适合：
不适合：
test cases passed, vs 6 / 17 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.