cover-3d-eye-with-docs

3D Eye With Docs

Use this skill when one article needs both a cover and section-bound inline visuals in the 3D Eye family. This skill is self-contained. Do not route runtime work to cover-3d-eye, article-visual-planner, or any illustration skill.

Hard Boundaries

• Accepted article sources: pasted article text, Markdown files, or plain-text files.
• Do not claim DOCX, PDF, remote article, or web scraping support.
• The article source remains read-only.
• If no valid article content is available, ask for pasted text or a Markdown/plain-text path. Do not downgrade to cover-only behavior.
• Default output is returned in the conversation. Write a file only when the user explicitly provides an output path.
• An output path applies only to that requested path; do not overwrite or modify any other file.

Output Type

Use the explicit --out-type parameter to decide what to output.

• --out-type template: output the invocation template only.
• --out-type brief: output the article visual brief set only.
• --out-type prompt: output final image prompts for every planned asset.
• --out-type all: output the brief set first, then the prompts.
• Omitted --out-type: default to brief.

Treat 直接生成, 出图, 生成封面和配图, and 开始生图 as direct image generation only when the user explicitly asks for images.

Template Output

For template-only mode, output exactly this structure and fill every field:

使用 $cover-3d-eye-with-docs 生成一套文章封面+正文配图方案
文章来源：{article_source}
输出类型：{out_type}
封面用途：{cover_use_case}
正文配图用途：{inline_use_case}
正文配图数量：{inline_count}
语言：{language}
封面画幅比例：{cover_ratio}
正文主画幅比例：{inline_ratio}
核心钩子：{core_hook}
已有图片处理：{image_handling}
补充背景：{context}
禁用元素：{forbidden_elements}

Required Inputs

Extract or infer:

• Article source: required.
• Topic / thesis: required.
• Cover use case: X article cover, WeChat cover, blog header, tutorial cover, YouTube thumbnail, local AI poster.
• Inline use case: install guide visual, hardware map, privacy comparison, quantization explainer, workflow strip, mistake checklist, cost comparison.
• Inline count: this is a hard constraint. If 正文配图数量 is omitted, use 3. If it is explicitly supplied, accept only an integer from 1 to 5. Validate this before producing any template, brief, prompt, or image. An explicit 0, negative number, non-integer, or value above 5 must fail with a clear request to use an integer from 1 to 5; never clamp, round, expand, truncate, omit, or route to the base cover skill or cover-only behavior.
• Language: Chinese, English, or mixed Chinese-English.
• Core hook: privacy, offline, local ownership, no cloud, hardware fit, quantization, speed, cost, mistakes, workflow clarity.
• Cover ratio and inline ratio: optional; infer from use case when omitted.
• Extra context: optional.
• Forbidden elements: optional.