Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tsingyuai/xhs-render-cards
把已批准的小红书草稿、单一分析参考和真实产品素材变成可审查卡片：先完成 DAI 与 image plan，再按确定性、完整效果或可分离图层模式制作，机械验证 PNG 与清单并运行合规检查。精确文字和真实 UI 不交给模型猜测；AI 生图需要单独配置和授权。
Passed 17 of 21 test cases with the skill, and 5 of 21 without it.
and 11 more in the full report
13 fixed6 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
After inspecting card readability, privacy, and evidence accuracy, what filename should store the visual review summary report?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies visual-review.md as the report output file. | Missed | Passed |
The instructions your model reads when the skill loads.
Read visual-production-contract.md, rendering.md, and visual-review-rubric.md. Keep DAI and compliance rules from deai.md and quality-gates.md.
Require before rendering:
visual-reference-selection.json when external visual research is used;memory/xhs-replicate/ run;The selected public reference is analysis-only. Learn hierarchy, proof-zone proportion, density, and reading rhythm; never copy its wording, logo, proprietary UI, exact composition, distinctive decoration, or full sequence. Rejected candidates contribute no visual rules.
Run DAI on title, caption, card copy, CTA, and tags. Every Product claim needs a current evidence source. Delete unsupported claims instead of weakening them with defensive filler.
Write image-plan.md using image-plan.md. Lock every visible string before rendering. Do not add cards merely to match the reference.
Use screenshot-assets for real Product UI, website, code, or data. Keep the original screenshot as evidence. Do not ask an image model to recreate Product UI, logos, citations, statistics, or source text and present it as real.
deterministic: HTML/CSS, Canvas, SVG, or Pillow owns layout and exact text. Preferred for Chinese copy, dense diagrams, real screenshots, and repeatable series.separable-layer: the image model creates only a background, texture, or illustration without text/UI; deterministic rendering places approved copy and Product evidence.complete-effect: the image model proposes a whole visual direction. Generated text, UI, logos, evidence, and sensitive claims must be replaced or the candidate rejected.Image generation is optional and separately authorized. If neither OPENAI_API_KEY nor GEMINI_API_KEY is configured, show the user the exact steps in CONFIGURATION.md and offer deterministic rendering or a no-image handoff. Never silently retry or request a key in conversation.
Before expanding a large pack, render:
test cases passed, vs 5 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.