Baoyu article illustrator

--- name: baoyu-article-illustrator description: Analyzes article structure, identifies sections requiring visual aids, and generates illustrations using a three-dimensional approach based on Type × Style × Palette. Use when the user asks to “illustrate an article,” “add images,” “generate images for an article,” or “为文章配图.” version: 1.117.4 metadata: openclaw: homepage: https://github.com/JimLiu/baoyu-skills#baoyu-article-illustrator --- # Article Illustrator Analyze articles, identify positions for illustrations, and generate images that maintain consistency in Type × Style × Palette. ## User Input Tools When this skill prompts the user, follow this tool-selection rule (in order of priority): 1. Prefer built-in user-input tools exposed by the current agent runtime:e.g., AskUserQuestion, request_user_input, clarify, ask_user, or any equivalent. 2. Fallback: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question. 3. Batching: If the tool supports multiple questions per call, combine all applicable questions into a single call; if it only supports a single question, ask them one at a time in order of priority. AskUserQuestion-specific references below are examples:substitute the local equivalent in other runtimes. ## Image Generation Tools When this skill needs to render an image, resolve the backend in this order: 1. Current-request override : if the user specifies a specific backend in the current message, use it. 2. Saved preference : if EXTEND.md sets preferred_image_backend to a backend available right now, use it. 3. Auto-select (when the preference is “auto,” “unset,” or the pinned backend is not available): - **Codex (imagegen)** : first, check your available-skills/tool inventory. If a skill named imagegen is listed, you are running within Codex and MUST use it: invoke it via the Skill tool with skill: "imagegen", passing the contents of the saved prompt file (plus the output path and aspect ratio as specified in Codeximagegen’s own arguments). Codex imagegen is the official raster-backendd in that runtime and takes precedence over any non-native skill (e.g., baoyu-image-gen) unless the user has explicitly pinned a different preferred_image_backend. - **Codex via codex exec (codex-imagegen)** : if the current runtime exposes no native imagegen skill but the codex CLI is on PATH with an active codex login, route through baoyu-image-gen --provider codex-cli (preferred), or : if baoyu-image-gen is unavailable : invoke the bundled wrapper directly. Details, parameters, and the runtime-discovery procedure are documented in [references/ codex-imagegen.md](references/ codex-imagegen.md) : load that file only when this branch is selected. - **Cursor (GenerateImage)** : if the runtime exposes a native GenerateImage tool, you are running within Cursor, and it takes precedence over any non-native skill, just as Codex imagegen does. Two important caveats: (a) it has no aspect-ratio parameter : explicitly specify the target aspect ratio and dimensions in the prompt text passed as description; (b) it does not accept an output directory:it saves to a tool-managed location, so after generation, copy or move the file to the expected output path of the skill (e.g., outputs/.../NN-xxx.png). Reference images go in reference_image_paths. - Other runtime-native tools : if the runtime exposes a different native image tool (e.g., Hermes image_generate), use it in the same way. - Otherwise, if exactly one non-native backend is installed (e.g., baoyu-image-gen), use it. - Otherwise (multiple non-native backends with no runtime-native tool), ask the user once:as part of any other initial questions. 4. If none are available, inform the user and ask how to proceed. ⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation. Codex imagegen’s own description states that it should be used “when the output should be a bitmap asset rather threpo-native code or vector.” If you cannot resolve a raster-backends via step 3, proceed to step 4 and ask the user:do not silently output SVG, write inline <svg> markup, or produce HTML/CSS art as a substitute. Th