baoyu-xhs-images
Skill27k starsChanged 7 months agoMITView on GitHub
Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized for social media engagement. Use when user mentions "小红书图片", "小红书种草", "小绿书", "微信图文", "微信贴图", "image cards", "图片卡片", baoyu-xhs-images, or wants social media infographic series.
15 other projects use a version of this, 6 of them edited; 6 of 6 edited versions we compared changed its rules; 1 new project in the last 4 weeks, against 0 the 4 before.
How people change it
6 of 6 edited versions changed its rules, and some changes recur.
Of the 6 edited versions we compared: 6 made changes of their own.
Rules people drop
- Codex via
codex exec(codex-imagegen): no nativeimagegen, but thecodexCLI is onPATHwith an activecodex login→baoyu-image-gen --provider codex-cli(preferred), or the bundled wrapper if baoyu-image-gen is unavailable. …dropped by 6 of 6 - ⛔ Raster only: never substitute SVG, HTML/CSS, canvas, or other code-based rendering for a raster image, even for diagram-like content. If no raster backend resolves, go to step 4.dropped by 6 of 6
- When the user picks a non-default style + layout combo, check
references/style-layout-matrix.mdand flag poor matches (✗).dropped by 6 of 6 - Only when the user supplies refs (
--ref <files...>or pasted paths): readreferences/reference-images.mdfor intake, usage modes (direct/style/palette), prompt frontmatter, and how refs combine with the image-1 anchor chain.dropped by 6 of 6 - When the user asks to edit, add, delete, or fix text on a card after generation, read
references/image-modification.mdfirst. Always update the prompt file before regenerating, and never patch bitmap text with code.dropped by 6 of 6 - When this skill prompts the user, follow this tool-selection rule (priority order):dropped by 2 of 6
- 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.dropped by 2 of 6
- Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.dropped by 2 of 6
Rules people add
- A rule we can't quote: its licence doesn't allow itadded by 4 of 6
- A rule we can't quote: its licence doesn't allow itadded by 4 of 6
- A rule we can't quote: its licence doesn't allow itadded by 4 of 6
- If
Projects/xhs-posts/{topic-slug}/already exists:added by 2 of 6 - CRITICAL: If EXTEND.md not found, MUST complete first-time setup before ANY other questions or steps. Do NOT proceed to content analysis, do NOT ask about style, do NOT ask about layout — ONLY complete the preferences setup first.added by 2 of 6
- Check EXTEND.md existence (priority order):added by 2 of 6
- Language: Use user's input language or saved language preference.added by 2 of 6
- Use AskUserQuestion with ALL questions in ONE call. See
.agents/skills/baoyu-xhs-images/references/config/first-time-setup.mdfor question details.added by 2 of 6
We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.
Adopted by
Surging: 1 new project took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- AgnesAI-Labs/agnet-skills-cnedited, first seen Nov 1, 2026
- full-aigc-plugins/image-factory-pluginedited, first seen Oct 20, 2026
- xfstudio/skillstheir own version, first seen Oct 13, 2026
- eugeneli326/claude-skillsedited, first seen Oct 13, 2026
- zephyrwang6/myskilltheir own version, first seen Oct 8, 2026
- alexkamen123/carmen-quantedited, first seen Sep 3, 2026
Who's talking about JimLiu/baoyu-skills
- 宝玉的技术分享“Agent Skills 设计哲学和实战进化”YouTube · Mar 23, 2026 · 2k views
- Yangjin | AI, Life & Business“我让 Codex 找 GitHub Skill,为什么一个都没直接装?”YouTube · Jul 19, 2026 · 1.4k views
- GitHub Trending Digest“baoyu-skills - GitHub Trending Today”YouTube · Apr 11, 2026 · 236 views
- Find Interesting AI“OPC时代—程序员的营销基础、工具选择、学习建议”YouTube · Jul 5, 2026 · 150 views
- AI워크랩“ChatGPT 보고서 꾸미기 스킬 5개 설치해 써 봤다 — Word 서식 · 테마 10종 · PPT 10장 | GitHub 인기 스킬”YouTube · Oct 21, 2026 · 114 views
The biggest 5 of 66 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 66
Talked about on GitHub, YouTube, Bluesky and the web (66 times).
On GitHub · 50
- Nov 15, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 15, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 14, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 14, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 13, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
45 more on GitHub
- Nov 13, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 12, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 12, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 11, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 11, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 10, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 10, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 9, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 9, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 8, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 8, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 7, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 7, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 6, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 6, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 5, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 5, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 4, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 4, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 3, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 3, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 2, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 2, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Nov 1, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Nov 1, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Oct 31, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Oct 31, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Oct 30, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Oct 30, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Oct 29, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Oct 29, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Oct 28, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Oct 28, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Oct 27, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Oct 27, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Oct 26, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Oct 26, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Oct 25, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Oct 25, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Oct 24, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Oct 24, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Oct 23, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Oct 23, 2026candidate: baoyu-post-to-wechat — BigPengSays/awesome-creator-skills0 reactions
- Oct 22, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
- Oct 21, 2026candidate: baoyu-wechat-summary — BigPengSays/awesome-creator-skills0 reactions
On YouTube · 12
- Mar 23, 2026Agent Skills 设计哲学和实战进化 — 宝玉的技术分享2k views · 5 comments
- Jul 19, 2026我让 Codex 找 GitHub Skill,为什么一个都没直接装? — Yangjin | AI, Life & Business1.4k views
- Apr 11, 2026baoyu-skills - GitHub Trending Today — GitHub Trending Digest236 views
- Jul 5, 2026OPC时代—程序员的营销基础、工具选择、学习建议 — Find Interesting AI150 views · 2 comments
- Oct 21, 2026ChatGPT 보고서 꾸미기 스킬 5개 설치해 써 봤다 — Word 서식 · 테마 10종 · PPT 10장 | GitHub 인기 스킬 — AI워크랩114 views
7 more on YouTube
- May 19, 2026Skills profissionais para Claude Code, Codex, Gemini e Cursor #AI #Shorts — RepoShots105 views · 1 comment
- Mar 11, 2026baoyu-skills hit 9.4K GitHub stars #BaoyuSkills #AgentSkills #ClaudeSkills #CodexSkills #Shorts — Pulse100 views · 1 comment
- May 19, 2026ClaudeCode 实战应用-打通公众号从配图、排版到推送到草稿箱,一气呵成,不再被编辑器束缚 — NicknickAI59 views
- Oct 28, 2026baoyu-skills: This AI agent can create new skills while it works — HubMesh40 views
- Oct 26, 20263 skills de Claude que convierten tu texto en cómics e infografías 🎨 — BarbuPrime IA | Claude Code Vs Codex14 views · 1 comment
- Oct 24, 2026一张产品图,做出两版醒目封面 — 慢半拍的安迪鲁14 views
- Oct 24, 2026用Codex把一页说明变成六步上手图|相机入门 #Shorts — 慢半拍的安迪鲁14 views
On Bluesky · 3
- Aug 11, 2026📦 JimLiu / baoyu-skills ⭐ 24,846 (+50) 🗒 TypeScript — @github-trending-js.bsky.social1 likes and repost
- Apr 11, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 JimLiu / baoyu-skills ⭐ 14,102 (+111) 🗒 TypeScript — @github-trending-js.bsky.social1 likes and repost
- Feb 20, 2026https://github.com/JimLiu/baoyu-skills — @tom-doerr.bsky.social1 likes and repost
On the web · 1
- Nov 2, 2026baoyu-infographic Skill: Turn Text into Infographics | PlugWiki — plugwiki.com
Used with
Projects with it also use deepl, imagemagick-conversion and 8 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
zephyrwang6Skilldeepl
Übersetzt Texte, Dokumente und XLIFF-Dateien via DeepL API. Verwende für Übersetzungen mit /deepl translate, /deepl file oder /deepl xliff.
Also in 4 projects that use this
zephyrwang6Skillimagemagick-conversion
Convert and manipulate images with ImageMagick. Covers format conversion, resizing, batch processing, quality adjustment, and image transformations. Use when user mentions image conversion, resizing images, ImageMagick, magick command, batch image processing, or thumbnail generation.
Also in 4 projects that use this
- +8 more from zephyrwang6
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 6
- open-fox/agents★ 5563% same
- alexkamen123/carmen-quant★ 463% same
- tentacle-pro/skills★ 412% same
- AgnesAI-Labs/agnet-skills-cn★ 160% same
- eugeneli326/claude-skills★ 014% same
- full-aigc-plugins/image-factory-plugin★ 063% same
Wrote their own version · 9
- zephyrwang6/myskill★ 339same name
- XY121718/baoyu-skills★ 103same name
- xuanxuan1983/baoyu-xuanyi-skills★ 45same name
- ideacco/baoyu-skills-openclaw★ 14same name
- SpaceZephyr/allSkills★ 14same name
- xfstudio/skills★ 9same name
- cocyuhao/my-ai-skills-library★ 1same name
- zhangdszq/vk-skills★ 1same name
- zinan92/skills-repo★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- release-skillsSkill
- baoyu-article-illustratorSkill
- baoyu-comicSkill
- baoyu-compress-imageSkill
- baoyu-cover-imageSkill
- baoyu-danger-gemini-webSkill
- baoyu-danger-x-to-markdownSkill
- baoyu-diagramSkill
- baoyu-electron-extractSkill
- baoyu-format-markdownSkill
- baoyu-image-genSkill
- baoyu-infographicSkill
- baoyu-markdown-to-htmlSkill
- baoyu-post-to-wechatSkill
- baoyu-post-to-weiboSkill
- baoyu-post-to-xSkill
- baoyu-slide-deckSkill
- baoyu-translateSkill
- baoyu-url-to-markdownSkill
- baoyu-wechat-summarySkill
- baoyu-youtube-transcriptSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
25 rules. 0 are common, 14 are distinctive, and 11 are very specific to this project.
0
Common
Most of the 15 edited versions we read keep these.
14
Distinctive
This author's own choices. Worth a look.
11
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
When this skill prompts the user, follow this tool-selection rule (priority order):
- Distinctive: line 19
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 …
- Distinctive: line 20
Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call.
- Very specific: line 32
Codex via
codex exec(codex-imagegen): no native imagegen, but the codex CLI is on PATH with an active codex login → baoyu-image-gen … - Distinctive: line 39
⛔ Raster only: never substitute SVG, HTML/CSS, canvas, or other code-based rendering for a raster image, even for diagram-like content.
- Very specific: line 43
Prompt file (hard): before invoking any backend, write each image's full, final prompt to its own file under prompts/ (NN-{type}-[slug].md) …
- Distinctive: line 49
After every prompt file for the current generation group has been saved and verified, generate images in batches by default.
- Distinctive: line 53
Use the chosen backend's native batch / multi-task interface if it exists.
- Very specific: line 54
If no native batch interface exists but the runtime can issue parallel tool calls, dispatch up to generation_batch_size images at a time.
- Distinctive: line 55
If neither native batch nor parallel tool calls are available, generate sequentially.
- Distinctive: line 60
Never start a batch until every selected prompt file for that batch exists on disk.
- Distinctive: line 62
Do not use subagents merely to parallelize image rendering.
- Distinctive: line 66
Default behavior: confirm before generation.
- Very specific: line 68
Treat explicit skill invocation, a file path, matched signals/presets, and EXTEND.md defaults as recommendation inputs only.
- Distinctive: line 69
Do not start Step 3 until the user completes Step 2.
- Distinctive: line 71
If confirmation is skipped explicitly, state the assumed strategy / style / layout / palette / count / backend in the next user-facing …
- Very specific: line 174
When the user picks a non-default style + layout combo, check references/style-layout-matrix.md and flag poor matches (✗).
- Very specific: line 188
Only when the user supplies refs (--ref <files...> or pasted paths): read references/reference-images.md for intake, usage modes (direct / …
- Distinctive: line 219
Check these paths in order.
- Very specific: line 236
Run the deep analysis in references/workflows/analysis-framework.md: content type, hook potential, audience, engagement signals, visual …
- Very specific: line 239
Write everything to analysis.md.
- Distinctive: line 247
Display summary: before asking:
- Very specific: line 266
Path B — Customize: ask five questions (strategy/style, layout, palette, count, optional notes) with the recommendation pre-filled — blanks …
- Very specific: line 282
Write the full prompt for every image to prompts/NN-{type}-{slug}.md in the user's preferred language (backup rule applies), then verify …
- Very specific: line 339
When the user asks to edit, add, delete, or fix text on a card after generation, read references/image-modification.md first.
“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Image Card Series Generator
Break down complex content into eye-catching image card series with multiple style options.
User Input Tools
When this skill prompts the user, follow this tool-selection rule (priority order):
- Prefer built-in user-input tools exposed by the current agent runtime — e.g.,
AskUserQuestion,request_user_input,clarify,ask_user, or any equivalent. - 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.
- Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.
Concrete AskUserQuestion references below are examples — substitute the local equivalent in other runtimes.
Image Generation Tools
Resolve the image backend in this order:
- User names a backend in the current message → use it.
preferred_image_backendinEXTEND.mdnames a backend available now → use it.askmeans ask every run.- Auto-select (preference
auto, unset, or the pinned backend is unavailable), first match wins:- Codex
imagegenskill is in your available skills → you are in Codex and MUST use it:Skillwithskill: "imagegen", passing the prompt file's content plus output path and aspect ratio. It outranks non-native skills such asbaoyu-image-gen. - Codex via
codex exec(codex-imagegen): no nativeimagegen, but thecodexCLI is onPATHwith an activecodex login→baoyu-image-gen --provider codex-cli(preferred), or the bundled wrapper if baoyu-image-gen is unavailable. Load references/codex-imagegen.md only for this branch. - Cursor
GenerateImage→ use it (outranks non-native skills). It has no aspect-ratio parameter, so state the aspect ratio / dimensions in thedescriptionprompt; it saves to a tool-managed location, so copy the file to the expected output path (e.g.,outputs/.../NN-xxx.png). Reference images go inreference_image_paths. - Other runtime-native image tool (e.g., Hermes
image_generate) → use it the same way. - Exactly one non-native backend installed (e.g.,
baoyu-image-gen) → use it. - Several non-native backends → ask the user once, batched with other initial questions.
- Codex
- None available → tell the user and ask how to proceed.
⛔ Raster only: never substitute SVG, HTML/CSS, canvas, or other code-based rendering for a raster image, even for diagram-like content. If no raster backend resolves, go to step 4.
⛔ No bitmap text patching: never use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other overlay to cover, rewrite, erase, stroke, or replace titles, body copy, tags, or any other text inside an already generated image card. Regenerate from a corrected prompt, switch to a layout with less on-card text, or ask the user which imperfect candidate to keep.
Prompt file (hard): before invoking any backend, write each image's full, final prompt to its own file under prompts/ (NN-{type}-[slug].md) and pass that file (or its content) to the backend. It is the reproducibility record and lets you switch backends without rewriting prompts.
Change the pinned backend via ## Changing Preferences below. Tool names above are examples; use the local equivalent in other runtimes.
Batch Generation Policy
After every prompt file for the current generation group has been saved and verified, generate images in batches by default.
Priority order:
- Use the chosen backend's native batch / multi-task interface if it exists. Each task must keep its own prompt file, output path, aspect ratio, session ID, and direct reference images.
- If no native batch interface exists but the runtime can issue parallel tool calls, dispatch up to
generation_batch_sizeimages at a time. Default:4. An explicit user request in the current message, such as--batch-size 4or "并行 4 张一起生成", overrides EXTEND.md. - If neither native batch nor parallel tool calls are available, generate sequentially.
Rules:
- Honor the image-1 anchor chain: generate image 1 first, then batch images 2+ using image 1 as the reference.
- Never start a batch until every selected prompt file for that batch exists on disk.
- Retry failed items once without regenerating successful items.
- Do not use subagents merely to parallelize image rendering. Use subagents only for separate prompt iteration or creative exploration.
Confirmation Policy
Default behavior: confirm before generation.
- Treat explicit skill invocation, a file path, matched signals/presets, and
EXTEND.mddefaults as recommendation inputs only. None of them authorizes skipping confirmation. - Do not start Step 3 until the user completes Step 2.
- Skip confirmation only when the current request explicitly says to do so, for example:
--yes, "直接生成", "不用确认", "跳过确认", "按默认出图", or equivalent wording. - If confirmation is skipped explicitly, state the assumed strategy / style / layout / palette / count / backend in the next user-facing update before generating.
Language
Respond in the user's language across questions, progress, errors, and completion summary. Keep technical tokens (style names, file paths, code) in English.
Options
| Option | Description |
--style <name> | Visual style (see Styles below) |
--layout <name> | Information layout (see Layouts below) |
--palette <name> | Color override: macaron / warm / neon |
--preset <name> | Style + layout + optional palette shorthand (see references/style-presets.md) |
--ref <files...> | Reference images applied to image 1 as the series anchor |
--batch-size <n> | Temporary generation batch size for this run. Default: generation_batch_size from EXTEND.md, otherwise 4. Clamp to 1-8. |
--yes | Non-interactive: skip all confirmations, use EXTEND.md or built-in defaults, auto-confirm recommended plan (Path A) |
Dimensions
Three independent knobs combine freely:
| Dimension | Controls | Options |
| Style | Visual aesthetics (lines, decorations, rendering) | 12 styles (see Styles below) |
| Layout | Information structure (density, arrangement) | 8 layouts (see Layouts below) |
| Palette (optional) | Color override, replaces the style's default colors | macaron / warm / neon (see Palettes below) |
Example: --style notion --layout dense makes an intellectual knowledge card; add --palette macaron to soften the colors without changing notion's rendering rules. A --preset is a shorthand for style + layout (+ optional palette).
Palette behavior: no --palette → style's built-in colors; --palette <name> → overrides colors only, rendering rules unchanged. Some styles declare a default_palette (e.g., sketch-notes defaults to macaron).
Styles (12)
| Style | Description |
cute (Default) | Sweet, adorable, girly aesthetic |
fresh | Clean, refreshing, natural |
warm | Cozy, friendly, approachable |
bold | High impact, attention-grabbing |
minimal | Ultra-clean, sophisticated |
retro | Vintage, nostalgic, trendy |
pop | Vibrant, energetic, eye-catching |
notion | Minimalist hand-drawn line art, intellectual |
chalkboard | Colorful chalk on black board, educational |
study-notes | Realistic handwritten photo style, blue pen + red annotations + yellow highlighter |
screen-print | Bold poster art, halftone textures, limited colors, symbolic storytelling |
sketch-notes | Hand-drawn educational infographic, macaron pastels on warm cream, wobble lines |
Per-style specifications: references/presets/<style>.md.
Layouts (8)
| Layout | Description |
sparse (Default) | 1-2 points, maximum impact |
balanced | 3-4 points, standard |
dense | 5-8 points, knowledge-card style |
list | Enumeration / ranking (4-7 items) |
comparison | Side-by-side contrast |
flow | Process / timeline (3-6 steps) |
mindmap | Center-radial (4-8 branches) |
quadrant | Four-quadrant / circular sections |
Layout specs: references/elements/canvas.md.
Palettes (optional override)
Replaces the style's colors while keeping rendering rules (line treatment, textures) intact.
| Palette | Background | Zone Colors | Accent | Feel |
macaron | Warm cream #F5F0E8 | Blue #A8D8EA, Lavender #D5C6E0, Mint #B5E5CF, Peach #F8D5C4 | Coral #E8655A | Soft, educational |
warm | Soft peach #FFECD2 | Orange #ED8936, Terracotta #C05621, Golden #F6AD55, Rose #D4A09A | Sienna #A0522D | Earth tones, cozy |
neon | Dark purple #1A1025 | Cyan #00F5FF, Magenta #FF00FF, Green #39FF14, Pink #FF6EC7 | Yellow #FFFF00 | High-energy, futuristic |
Palette specs: references/palettes/<palette>.md.
Presets (style + layout shortcuts)
26 presets grouped by scenario (knowledge, lifestyle, impact, trend, poster). Read references/style-presets.md when the user passes --preset or when recommending a preset in Step 2.
Auto-Selection
Match content signals to the best combo. First row whose keywords appear wins; fall back to cute-share if nothing matches.
| Signals in source | Style | Layout | Recommended preset |
| beauty, fashion, cute, girl, pink | cute | sparse/balanced | cute-share, girly |
| health, nature, fresh, organic | fresh | balanced/flow | product-review, nature-flow |
| life, story, emotion, warm | warm | balanced | cozy-story |
| warning, important, must, critical | bold | list/comparison | warning, versus |
| professional, business, elegant | minimal | sparse/balanced | clean-quote, pro-summary |
| classic, vintage, traditional | retro | balanced | throwback, retro-ranking |
| fun, exciting, wow, amazing | pop | sparse/list | hype, pop-facts |
| knowledge, concept, productivity, SaaS | notion | dense/list | knowledge-card, checklist |
| education, tutorial, learning, classroom | chalkboard | balanced/dense | tutorial, classroom |
| notes, handwritten, study guide, realistic | study-notes | dense/list/mindmap | study-guide |
| movie, poster, opinion, editorial, cinematic | screen-print | sparse/comparison | poster, editorial, cinematic |
| hand-drawn, infographic, workflow, 手绘,图解 | sketch-notes | flow/balanced/dense | hand-drawn-edu, sketch-card, sketch-summary |
Style × Layout Matrix
When the user picks a non-default style + layout combo, check references/style-layout-matrix.md and flag poor matches (✗).
Outline Strategies
Three differentiated approaches — each produces a structurally different outline. The workflow recommends one; Path C generates all three and lets the user choose.
| Strategy | Concept | Best for | Structure |
| A — Story-Driven | Personal experience as the thread, emotional resonance first | Reviews, personal shares, transformation | Hook → Problem → Discovery → Experience → Conclusion |
| B — Information-Dense | Value-first, efficient information delivery | Tutorials, comparisons, checklists | Core conclusion → Info card → Pros/Cons → Recommendation |
| C — Visual-First | Visual impact as core, minimal text | High-aesthetic products, lifestyle, mood content | Hero image → Detail shots → Lifestyle scene → CTA |
Reference Images
Only when the user supplies refs (--ref <files...> or pasted paths): read references/reference-images.md for intake, usage modes (direct / style / palette), prompt frontmatter, and how refs combine with the image-1 anchor chain.
File Layout
image-cards/{topic-slug}/
├── source-{slug}.{ext}
├── analysis.md
├── outline-strategy-{a,b,c}.md # Path C only
├── outline.md
├── prompts/NN-{type}-{slug}.md
├── NN-{type}-{slug}.png
└── refs/ # only if --ref usedSlug: 2-4 words, kebab-case. "AI 工具推荐" → ai-tools-recommend. On collision, append -YYYYMMDD-HHMMSS.
Backup rule (applies throughout): before overwriting any file — source, outline, prompt, image — rename the existing one to <name>-backup-YYYYMMDD-HHMMSS.<ext>. This protects user edits.
Workflow
- [ ] Step 0: Load EXTEND.md ⛔ BLOCKING (interactive only)
- [ ] Step 1: Analyze content → analysis.md
- [ ] Step 2: Smart Confirm ⚠️ REQUIRED (Path A / B / C)
- [ ] Step 3: Generate images
- [ ] Step 4: Completion reportStep 0: Load EXTEND.md ⛔ BLOCKING
Check these paths in order; first hit wins:
| Path | Scope |
.baoyu-skills/baoyu-xhs-images/EXTEND.md | Project |
${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-xhs-images/EXTEND.md | XDG |
$HOME/.baoyu-skills/baoyu-xhs-images/EXTEND.md | User home |
- Found → read, parse, print a summary (style / layout / watermark / language), continue.
- Not found + interactive → run first-time setup (see
references/config/first-time-setup.md) and save before anything else. Do NOT analyze content or ask style questions until preferences exist — this keeps first-run behavior predictable. - Not found +
--yes→ skip setup, use built-in defaults (no watermark, style/layout auto-selected, language from content). Do not prompt, do not create EXTEND.md.
EXTEND.md keys: watermark, preferred style/layout, custom style definitions, language preference, preferred image backend, generation batch size. Schema: references/config/preferences-schema.md.
Step 1: Analyze Content → analysis.md
- Save the source (backup rule applies if
source.mdexists). - Run the deep analysis in
references/workflows/analysis-framework.md: content type, hook potential, audience, engagement signals, visual opportunity map, swipe flow. - Detect source language, pick recommended image count (2-10).
- Auto-recommend strategy + style + layout + palette using the Auto-Selection table above.
- Write everything to
analysis.md.
Step 2: Smart Confirm ⚠️ REQUIRED
Hard gate: this step is mandatory per the Confirmation Policy — Step 3 cannot start until the user confirms here (or explicitly opts out with --yes / equivalent wording in the current request).
Goal: present the auto-recommended plan and let the user confirm or adjust. Skip this step entirely under --yes — proceed with Path A using the analysis and any CLI overrides.
Display summary before asking:
📋 内容分析
主题:[topic] | 类型:[content_type]
要点:[key points]
受众:[audience]
🎨 推荐方案(自动匹配)
策略:[A/B/C] [name]([reason])
风格:[style] · 布局:[layout] · 配色:[palette or 默认] · 预设:[preset]
图片:[N]张(封面+[N-2]内容+结尾)
元素:[background] / [decorations] / [emphasis]Then ask one question — three paths. Verbatim option copy: references/confirmation.md.
Path A — Quick confirm (trust auto-recommendation): generate a single outline using the recommended strategy + style → save to outline.md → Step 3.
Path B — Customize: ask five questions (strategy/style, layout, palette, count, optional notes) with the recommendation pre-filled — blanks keep the recommendation. Generate one outline with the user's choices → outline.md → Step 3. See references/confirmation.md.
Path C — Detailed mode: two sub-confirmations.
- Step 2a — Content understanding: ask selling points (multi-select), audience, style preference (authentic / professional / aesthetic / auto), optional context. Update
analysis.md. - Step 2b — Three outline variants: generate
outline-strategy-a.md,outline-strategy-b.md,outline-strategy-c.md. Each MUST have a different structure AND a different recommended style — includestyle_reasonin the frontmatter. Page-count heuristic: A ~4-6, B ~3-5, C ~3-4. Template:references/workflows/outline-template.md; frontmatter example inreferences/confirmation.md. - Step 2c — Selection: ask three questions (outline A/B/C/Combined, style, visual elements). Save selected/merged outline to
outline.md→ Step 3.
Step 3: Generate Images
With confirmed outline + style + layout + palette:
Visual consistency — image-1 anchor chain: character / mascot / color rendering drifts between calls unless you anchor them. Generate image 1 (cover) first WITHOUT --ref, then pass image 1 as --ref to every subsequent image. This is the single most important consistency trick for this skill — don't skip it even if the backend also supports a session ID.
Generation flow:
- Write the full prompt for every image to
prompts/NN-{type}-{slug}.mdin the user's preferred language (backup rule applies), then verify all selected prompt files exist. - Generate image 1 first without
--ref; backup rule applies to the PNG file. This establishes the anchor. - Build a task list for images 2+ using image 1 as
--ref <path-to-image-01.png>. - Dispatch images 2+ in batches per the
## Batch Generation Policy: backend native batch first, runtime parallel tool calls second, sequential only as fallback. - Report progress after each completed image. On failure, retry only the failed item once from the same saved prompt file.
Watermark (if enabled in EXTEND.md): append to the generation prompt:
Include a subtle watermark "[content]" positioned at [position].
The watermark should be legible but not distracting.See references/config/watermark-guide.md.
Backend selection: per the Image Generation Tools rule at the top — use whatever is available, ask once if multiple, before any generation. Under --yes, use the EXTEND.md preference and fall back to the first available backend. Prompt files MUST exist before invoking any backend.
codex-imagegen invocation: when the rule resolves to codex-imagegen, see references/codex-imagegen.md for the invocation contract (preferred baoyu-image-gen --provider codex-cli path, runtime wrapper discovery, parameter notes, stdout schema, batch semantics — n=1 per call so card batches must dispatch one wrapper call per card; the wrapper does NOT accept --sessionId, so chain consistency must come from --ref per Step 3 above).
Session ID (if the backend supports --sessionId): use cards-{topic-slug}-{timestamp} for every image; combined with the ref chain this gives maximum consistency.
Step 4: Completion Report
Image Card Series Complete!
Topic: [topic]
Mode: [Quick / Custom / Detailed]
Strategy: [A/B/C/Combined]
Style: [name]
Palette: [name or "default"]
Layout: [name or "varies"]
Location: [directory]
Images: N total
✓ analysis.md
✓ outline.md
✓ outline-strategy-a/b/c.md (detailed mode only)
- 01-cover-[slug].png ✓ Cover (sparse)
- 02-content-[slug].png ✓ Content (balanced)
- ...
- NN-ending-[slug].png ✓ Ending (sparse)Content Breakdown Principles
| Position | Purpose | Typical layout |
| Cover (image 1) | Hook + visual impact | sparse |
| Content (middle) | Core value per image | balanced / dense / list / comparison / flow |
| Ending (last) | CTA / summary | sparse or balanced |
For the style × layout compatibility matrix, see references/style-layout-matrix.md.
Image Modification
When the user asks to edit, add, delete, or fix text on a card after generation, read references/image-modification.md first. Always update the prompt file before regenerating, and never patch bitmap text with code.
References
| File | Content |
references/confirmation.md | Verbatim AskUserQuestion copy for every confirmation path |
references/style-presets.md | Full preset shortcut definitions, presets grouped by scenario |
references/style-layout-matrix.md | Style × layout compatibility scores |
references/reference-images.md | User-supplied reference image intake and usage |
references/image-modification.md | Edit / add / delete cards, text correction policy |
references/presets/<style>.md | Per-style element definitions |
references/palettes/<name>.md | Per-palette color definitions |
references/elements/canvas.md | Aspect ratios, safe zones, grid layouts |
references/elements/image-effects.md | Cutout, stroke, filters |
references/elements/typography.md | Decorated text, tags, text direction |
references/elements/decorations.md | Emphasis marks, backgrounds, doodles, frames |
references/workflows/analysis-framework.md | Content analysis framework |
references/workflows/outline-template.md | Outline template with layout guide |
references/workflows/prompt-assembly.md | Prompt assembly guide |
references/config/preferences-schema.md | EXTEND.md schema |
references/config/first-time-setup.md | First-time setup flow |
references/config/watermark-guide.md | Watermark configuration |
Notes
- Auto-retry once on generation failure before reporting an error.
- For sensitive public figures, use stylized cartoon alternatives.
- Smart Confirm (Step 2) is required; Detailed mode adds a second confirmation (2a + 2c).
Changing Preferences
EXTEND.md lives at the first matching path listed in Step 0. Three ways to change it:
- Edit directly — open EXTEND.md and change fields. Full schema:
references/config/preferences-schema.md. - Reconfigure interactively — delete EXTEND.md (or ask "reconfigure baoyu-xhs-images preferences" / "重新配置"). The next run re-triggers first-time setup.
- Common one-line edits:
preferred_image_backend: auto— default; runtime-native tool wins, falls back to the only installed backend, asks only if multiple non-native are present.preferred_image_backend: codex-imagegen— pin to Codex's built-in.preferred_image_backend: baoyu-image-gen— pin to the baoyu-image-gen skill.preferred_image_backend: ask— confirm backend every run.generation_batch_size: 4— default number of images to render concurrently when the backend/runtime supports batch or parallel generation.preferred_style: notion,preferred_layout: dense,preferred_palette: macaron,language: zh.watermark.enabled: true+watermark.content: "@handle"— add a watermark.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

