[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D5V90Q9VC9B3KBHKRJHDF7":3,"skill-same:01M7D5V90Q9VC9B3KBHKRJHDF7":186},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":29,"commitSha":30,"skillDirectory":5,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7D5V90Q9VC9B3KBHKRJHDF7","baoyu-xhs-images",null,"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.","tangyixiao\u002Ftangyixiao-skills","tangyixiao","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F115929632?v=4","01M7D582YK6A4M63CAK4CSY4EW","Tang Yixiao","01M7D582Z64DMRSYR872SR34SA",2,"MIT","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: baoyu-xhs-images\ndescription: Generates infographic image card series with 12 visual styles, 8 layouts,\n  and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized\n  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\",\n  \"微信贴图\", \"image cards\", \"图片卡片\", baoyu-xhs-images, or wants social media infographic\n  series.\nmetadata:\n  openclaw:\n    homepage: https:\u002F\u002Fgithub.com\u002FJimLiu\u002Fbaoyu-skills#baoyu-xhs-images\n  upstream-version: 2.0.1\n---\n\n# Image Card Series Generator\n\nBreak down complex content into eye-catching image card series with multiple style options.\n\n## User Input Tools\n\nWhen this skill prompts the user, follow this tool-selection rule (priority order):\n\n1. **Prefer built-in user-input tools** exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.\n2. **Fallback**: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number\u002Fanswer for each question.\n3. **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.\n\nConcrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.\n\n## Image Generation Tools\n\nResolve the image backend in this order:\n\n1. **User names a backend** in the current message → use it.\n2. **`preferred_image_backend`** in `EXTEND.md` names a backend available now → use it. `ask` means ask every run.\n3. **Auto-select** (preference `auto`, unset, or the pinned backend is unavailable), first match wins:\n   - **Codex `imagegen`** skill is in your available skills → you are in Codex and MUST use it: `Skill` with `skill: \"imagegen\"`, passing the prompt file's content plus output path and aspect ratio. It outranks non-native skills such as `baoyu-image-gen`.\n   - **Codex via `codex exec` (`codex-imagegen`)**: no native `imagegen`, but the `codex` CLI is on `PATH` with an active `codex login` → `baoyu-image-gen --provider codex-cli` (preferred), or the bundled wrapper if baoyu-image-gen is unavailable. Load [references\u002Fcodex-imagegen.md](references\u002Fcodex-imagegen.md) only for this branch.\n   - **Cursor `GenerateImage`** → use it (outranks non-native skills). It has no aspect-ratio parameter, so state the aspect ratio \u002F dimensions in the `description` prompt; it saves to a tool-managed location, so copy the file to the expected output path (e.g., `outputs\u002F...\u002FNN-xxx.png`). Reference images go in `reference_image_paths`.\n   - **Other runtime-native image tool** (e.g., Hermes `image_generate`) → use it the same way.\n   - Exactly one non-native backend installed (e.g., `baoyu-image-gen`) → use it.\n   - Several non-native backends → ask the user once, batched with other initial questions.\n4. **None available** → tell the user and ask how to proceed.\n\n**⛔ Raster only**: never substitute SVG, HTML\u002FCSS, canvas, or other code-based rendering for a raster image, even for diagram-like content. If no raster backend resolves, go to step 4.\n\n**⛔ No bitmap text patching**: never use ImageMagick, Pillow, Canvas, SVG, HTML\u002FCSS, 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.\n\n**Prompt file (hard)**: before invoking any backend, write each image's full, final prompt to its own file under `prompts\u002F` (`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.\n\nChange the pinned backend via `## Changing Preferences` below. Tool names above are examples; use the local equivalent in other runtimes.\n\n## Batch Generation Policy\n\nAfter every prompt file for the current generation group has been saved and verified, generate images in batches by default.\n\nPriority order:\n\n1. Use the chosen backend's native batch \u002F multi-task interface if it exists. Each task must keep its own prompt file, output path, aspect ratio, session ID, and direct reference images.\n2. If no native batch interface exists but the runtime can issue parallel tool calls, dispatch up to `generation_batch_size` images at a time. Default: `4`. An explicit user request in the current message, such as `--batch-size 4` or \"并行 4 张一起生成\", overrides EXTEND.md.\n3. If neither native batch nor parallel tool calls are available, generate sequentially.\n\nRules:\n\n- Honor the image-1 anchor chain: generate image 1 first, then batch images 2+ using image 1 as the reference.\n- Never start a batch until every selected prompt file for that batch exists on disk.\n- Retry failed items once without regenerating successful items.\n- Do not use subagents merely to parallelize image rendering. Use subagents only for separate prompt iteration or creative exploration.\n\n## Confirmation Policy\n\nDefault behavior: **confirm before generation**.\n\n- Treat explicit skill invocation, a file path, matched signals\u002Fpresets, and `EXTEND.md` defaults as **recommendation inputs only**. None of them authorizes skipping confirmation.\n- Do **not** start Step 3 until the user completes Step 2.\n- 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.\n- If confirmation is skipped explicitly, state the assumed strategy \u002F style \u002F layout \u002F palette \u002F count \u002F backend in the next user-facing update before generating.\n\n## Language\n\nRespond in the user's language across questions, progress, errors, and completion summary. Keep technical tokens (style names, file paths, code) in English.\n\n## Options\n\n| Option | Description |\n|--------|-------------|\n| `--style \u003Cname>` | Visual style (see Styles below) |\n| `--layout \u003Cname>` | Information layout (see Layouts below) |\n| `--palette \u003Cname>` | Color override: macaron \u002F warm \u002F neon |\n| `--preset \u003Cname>` | Style + layout + optional palette shorthand (see `references\u002Fstyle-presets.md`) |\n| `--ref \u003Cfiles...>` | Reference images applied to image 1 as the series anchor |\n| `--batch-size \u003Cn>` | Temporary generation batch size for this run. Default: `generation_batch_size` from EXTEND.md, otherwise 4. Clamp to 1-8. |\n| `--yes` | Non-interactive: skip all confirmations, use EXTEND.md or built-in defaults, auto-confirm recommended plan (Path A) |\n\n## Dimensions\n\nThree independent knobs combine freely:\n\n| Dimension | Controls | Options |\n|-----------|----------|---------|\n| **Style** | Visual aesthetics (lines, decorations, rendering) | 12 styles (see Styles below) |\n| **Layout** | Information structure (density, arrangement) | 8 layouts (see Layouts below) |\n| **Palette** (optional) | Color override, replaces the style's default colors | macaron \u002F warm \u002F neon (see Palettes below) |\n\nExample: `--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).\n\n**Palette behavior**: no `--palette` → style's built-in colors; `--palette \u003Cname>` → overrides colors only, rendering rules unchanged. Some styles declare a `default_palette` (e.g., sketch-notes defaults to macaron).\n\n## Styles (12)\n\n| Style | Description |\n|-------|-------------|\n| `cute` (Default) | Sweet, adorable, girly aesthetic |\n| `fresh` | Clean, refreshing, natural |\n| `warm` | Cozy, friendly, approachable |\n| `bold` | High impact, attention-grabbing |\n| `minimal` | Ultra-clean, sophisticated |\n| `retro` | Vintage, nostalgic, trendy |\n| `pop` | Vibrant, energetic, eye-catching |\n| `notion` | Minimalist hand-drawn line art, intellectual |\n| `chalkboard` | Colorful chalk on black board, educational |\n| `study-notes` | Realistic handwritten photo style, blue pen + red annotations + yellow highlighter |\n| `screen-print` | Bold poster art, halftone textures, limited colors, symbolic storytelling |\n| `sketch-notes` | Hand-drawn educational infographic, macaron pastels on warm cream, wobble lines |\n\nPer-style specifications: `references\u002Fpresets\u002F\u003Cstyle>.md`.\n\n## Layouts (8)\n\n| Layout | Description |\n|--------|-------------|\n| `sparse` (Default) | 1-2 points, maximum impact |\n| `balanced` | 3-4 points, standard |\n| `dense` | 5-8 points, knowledge-card style |\n| `list` | Enumeration \u002F ranking (4-7 items) |\n| `comparison` | Side-by-side contrast |\n| `flow` | Process \u002F timeline (3-6 steps) |\n| `mindmap` | Center-radial (4-8 branches) |\n| `quadrant` | Four-quadrant \u002F circular sections |\n\nLayout specs: `references\u002Felements\u002Fcanvas.md`.\n\n## Palettes (optional override)\n\nReplaces the style's colors while keeping rendering rules (line treatment, textures) intact.\n\n| Palette | Background | Zone Colors | Accent | Feel |\n|---------|------------|-------------|--------|------|\n| `macaron` | Warm cream #F5F0E8 | Blue #A8D8EA, Lavender #D5C6E0, Mint #B5E5CF, Peach #F8D5C4 | Coral #E8655A | Soft, educational |\n| `warm` | Soft peach #FFECD2 | Orange #ED8936, Terracotta #C05621, Golden #F6AD55, Rose #D4A09A | Sienna #A0522D | Earth tones, cozy |\n| `neon` | Dark purple #1A1025 | Cyan #00F5FF, Magenta #FF00FF, Green #39FF14, Pink #FF6EC7 | Yellow #FFFF00 | High-energy, futuristic |\n\nPalette specs: `references\u002Fpalettes\u002F\u003Cpalette>.md`.\n\n## Presets (style + layout shortcuts)\n\n26 presets grouped by scenario (knowledge, lifestyle, impact, trend, poster). Read `references\u002Fstyle-presets.md` when the user passes `--preset` or when recommending a preset in Step 2.\n\n## Auto-Selection\n\nMatch content signals to the best combo. First row whose keywords appear wins; fall back to `cute-share` if nothing matches.\n\n| Signals in source | Style | Layout | Recommended preset |\n|-------------------|-------|--------|--------------------|\n| beauty, fashion, cute, girl, pink | `cute` | sparse\u002Fbalanced | `cute-share`, `girly` |\n| health, nature, fresh, organic | `fresh` | balanced\u002Fflow | `product-review`, `nature-flow` |\n| life, story, emotion, warm | `warm` | balanced | `cozy-story` |\n| warning, important, must, critical | `bold` | list\u002Fcomparison | `warning`, `versus` |\n| professional, business, elegant | `minimal` | sparse\u002Fbalanced | `clean-quote`, `pro-summary` |\n| classic, vintage, traditional | `retro` | balanced | `throwback`, `retro-ranking` |\n| fun, exciting, wow, amazing | `pop` | sparse\u002Flist | `hype`, `pop-facts` |\n| knowledge, concept, productivity, SaaS | `notion` | dense\u002Flist | `knowledge-card`, `checklist` |\n| education, tutorial, learning, classroom | `chalkboard` | balanced\u002Fdense | `tutorial`, `classroom` |\n| notes, handwritten, study guide, realistic | `study-notes` | dense\u002Flist\u002Fmindmap | `study-guide` |\n| movie, poster, opinion, editorial, cinematic | `screen-print` | sparse\u002Fcomparison | `poster`, `editorial`, `cinematic` |\n| hand-drawn, infographic, workflow, 手绘，图解 | `sketch-notes` | flow\u002Fbalanced\u002Fdense | `hand-drawn-edu`, `sketch-card`, `sketch-summary` |\n\n## Style × Layout Matrix\n\nWhen the user picks a non-default style + layout combo, check `references\u002Fstyle-layout-matrix.md` and flag poor matches (✗).\n\n## Outline Strategies\n\nThree differentiated approaches — each produces a structurally different outline. The workflow recommends one; Path C generates all three and lets the user choose.\n\n| Strategy | Concept | Best for | Structure |\n|----------|---------|----------|-----------|\n| **A — Story-Driven** | Personal experience as the thread, emotional resonance first | Reviews, personal shares, transformation | Hook → Problem → Discovery → Experience → Conclusion |\n| **B — Information-Dense** | Value-first, efficient information delivery | Tutorials, comparisons, checklists | Core conclusion → Info card → Pros\u002FCons → Recommendation |\n| **C — Visual-First** | Visual impact as core, minimal text | High-aesthetic products, lifestyle, mood content | Hero image → Detail shots → Lifestyle scene → CTA |\n\n## Reference Images\n\nOnly when the user supplies refs (`--ref \u003Cfiles...>` or pasted paths): read `references\u002Freference-images.md` for intake, usage modes (`direct` \u002F `style` \u002F `palette`), prompt frontmatter, and how refs combine with the image-1 anchor chain.\n\n## File Layout\n\n```\nimage-cards\u002F{topic-slug}\u002F\n├── source-{slug}.{ext}\n├── analysis.md\n├── outline-strategy-{a,b,c}.md    # Path C only\n├── outline.md\n├── prompts\u002FNN-{type}-{slug}.md\n├── NN-{type}-{slug}.png\n└── refs\u002F                          # only if --ref used\n```\n\n**Slug**: 2-4 words, kebab-case. \"AI 工具推荐\" → `ai-tools-recommend`. On collision, append `-YYYYMMDD-HHMMSS`.\n\n**Backup rule** (applies throughout): before overwriting any file — source, outline, prompt, image — rename the existing one to `\u003Cname>-backup-YYYYMMDD-HHMMSS.\u003Cext>`. This protects user edits.\n\n## Workflow\n\n```\n- [ ] Step 0: Load EXTEND.md ⛔ BLOCKING (interactive only)\n- [ ] Step 1: Analyze content → analysis.md\n- [ ] Step 2: Smart Confirm ⚠️ REQUIRED (Path A \u002F B \u002F C)\n- [ ] Step 3: Generate images\n- [ ] Step 4: Completion report\n```\n\n### Step 0: Load EXTEND.md ⛔ BLOCKING\n\nCheck these paths in order; first hit wins:\n\n| Path | Scope |\n|------|-------|\n| `.baoyu-skills\u002Fbaoyu-xhs-images\u002FEXTEND.md` | Project |\n| `${XDG_CONFIG_HOME:-$HOME\u002F.config}\u002Fbaoyu-skills\u002Fbaoyu-xhs-images\u002FEXTEND.md` | XDG |\n| `$HOME\u002F.baoyu-skills\u002Fbaoyu-xhs-images\u002FEXTEND.md` | User home |\n\n- **Found** → read, parse, print a summary (style \u002F layout \u002F watermark \u002F language), continue.\n- **Not found + interactive** → run first-time setup (see `references\u002Fconfig\u002Ffirst-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.\n- **Not found + `--yes`** → skip setup, use built-in defaults (no watermark, style\u002Flayout auto-selected, language from content). Do not prompt, do not create EXTEND.md.\n\n**EXTEND.md keys**: watermark, preferred style\u002Flayout, custom style definitions, language preference, preferred image backend, generation batch size. Schema: `references\u002Fconfig\u002Fpreferences-schema.md`.\n\n### Step 1: Analyze Content → `analysis.md`\n\n1. Save the source (backup rule applies if `source.md` exists).\n2. Run the deep analysis in `references\u002Fworkflows\u002Fanalysis-framework.md`: content type, hook potential, audience, engagement signals, visual opportunity map, swipe flow.\n3. Detect source language, pick recommended image count (2-10).\n4. Auto-recommend strategy + style + layout + palette using the **Auto-Selection** table above.\n5. Write everything to `analysis.md`.\n\n### Step 2: Smart Confirm ⚠️ REQUIRED\n\n**Hard gate**: this step is mandatory per the [Confirmation Policy](#confirmation-policy) — Step 3 cannot start until the user confirms here (or explicitly opts out with `--yes` \u002F equivalent wording in the current request).\n\nGoal: 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.\n\n**Display summary** before asking:\n\n```\n📋 内容分析\n  主题：[topic] | 类型：[content_type]\n  要点：[key points]\n  受众：[audience]\n\n🎨 推荐方案（自动匹配）\n  策略：[A\u002FB\u002FC] [name]（[reason]）\n  风格：[style] · 布局：[layout] · 配色：[palette or 默认] · 预设：[preset]\n  图片：[N]张（封面+[N-2]内容+结尾）\n  元素：[background] \u002F [decorations] \u002F [emphasis]\n```\n\nThen ask one question — three paths. Verbatim option copy: `references\u002Fconfirmation.md`.\n\n**Path A — Quick confirm** (trust auto-recommendation): generate a single outline using the recommended strategy + style → save to `outline.md` → Step 3.\n\n**Path B — Customize**: ask five questions (strategy\u002Fstyle, 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\u002Fconfirmation.md`.\n\n**Path C — Detailed mode**: two sub-confirmations.\n\n- *Step 2a — Content understanding*: ask selling points (multi-select), audience, style preference (authentic \u002F professional \u002F aesthetic \u002F auto), optional context. Update `analysis.md`.\n- *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 — include `style_reason` in the frontmatter. Page-count heuristic: A ~4-6, B ~3-5, C ~3-4. Template: `references\u002Fworkflows\u002Foutline-template.md`; frontmatter example in `references\u002Fconfirmation.md`.\n- *Step 2c — Selection*: ask three questions (outline A\u002FB\u002FC\u002FCombined, style, visual elements). Save selected\u002Fmerged outline to `outline.md` → Step 3.\n\n### Step 3: Generate Images\n\nWith confirmed outline + style + layout + palette:\n\n**Visual consistency — image-1 anchor chain**: character \u002F mascot \u002F 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.\n\nGeneration flow:\n\n1. Write the full prompt for every image to `prompts\u002FNN-{type}-{slug}.md` in the user's preferred language (backup rule applies), then verify all selected prompt files exist.\n2. Generate **image 1** first without `--ref`; backup rule applies to the PNG file. This establishes the anchor.\n3. Build a task list for **images 2+** using image 1 as `--ref \u003Cpath-to-image-01.png>`.\n4. Dispatch images 2+ in batches per the `## Batch Generation Policy`: backend native batch first, runtime parallel tool calls second, sequential only as fallback.\n5. Report progress after each completed image. On failure, retry only the failed item once from the same saved prompt file.\n\n**Watermark** (if enabled in EXTEND.md): append to the generation prompt:\n\n```\nInclude a subtle watermark \"[content]\" positioned at [position].\nThe watermark should be legible but not distracting.\n```\n\nSee `references\u002Fconfig\u002Fwatermark-guide.md`.\n\n**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.\n\n**`codex-imagegen` invocation**: when the rule resolves to `codex-imagegen`, see [references\u002Fcodex-imagegen.md](references\u002Fcodex-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).\n\n**Session ID** (if the backend supports `--sessionId`): use `cards-{topic-slug}-{timestamp}` for every image; combined with the ref chain this gives maximum consistency.\n\n### Step 4: Completion Report\n\n```\nImage Card Series Complete!\n\nTopic: [topic]\nMode: [Quick \u002F Custom \u002F Detailed]\nStrategy: [A\u002FB\u002FC\u002FCombined]\nStyle: [name]\nPalette: [name or \"default\"]\nLayout: [name or \"varies\"]\nLocation: [directory]\nImages: N total\n\n✓ analysis.md\n✓ outline.md\n✓ outline-strategy-a\u002Fb\u002Fc.md (detailed mode only)\n\n- 01-cover-[slug].png ✓ Cover (sparse)\n- 02-content-[slug].png ✓ Content (balanced)\n- ...\n- NN-ending-[slug].png ✓ Ending (sparse)\n```\n\n## Content Breakdown Principles\n\n| Position | Purpose | Typical layout |\n|----------|---------|----------------|\n| Cover (image 1) | Hook + visual impact | `sparse` |\n| Content (middle) | Core value per image | `balanced` \u002F `dense` \u002F `list` \u002F `comparison` \u002F `flow` |\n| Ending (last) | CTA \u002F summary | `sparse` or `balanced` |\n\nFor the style × layout compatibility matrix, see `references\u002Fstyle-layout-matrix.md`.\n\n## Image Modification\n\nWhen the user asks to edit, add, delete, or fix text on a card after generation, read `references\u002Fimage-modification.md` first. Always update the prompt file before regenerating, and never patch bitmap text with code.\n\n## References\n\n| File | Content |\n|------|---------|\n| `references\u002Fconfirmation.md` | Verbatim AskUserQuestion copy for every confirmation path |\n| `references\u002Fstyle-presets.md` | Full preset shortcut definitions, presets grouped by scenario |\n| `references\u002Fstyle-layout-matrix.md` | Style × layout compatibility scores |\n| `references\u002Freference-images.md` | User-supplied reference image intake and usage |\n| `references\u002Fimage-modification.md` | Edit \u002F add \u002F delete cards, text correction policy |\n| `references\u002Fpresets\u002F\u003Cstyle>.md` | Per-style element definitions |\n| `references\u002Fpalettes\u002F\u003Cname>.md` | Per-palette color definitions |\n| `references\u002Felements\u002Fcanvas.md` | Aspect ratios, safe zones, grid layouts |\n| `references\u002Felements\u002Fimage-effects.md` | Cutout, stroke, filters |\n| `references\u002Felements\u002Ftypography.md` | Decorated text, tags, text direction |\n| `references\u002Felements\u002Fdecorations.md` | Emphasis marks, backgrounds, doodles, frames |\n| `references\u002Fworkflows\u002Fanalysis-framework.md` | Content analysis framework |\n| `references\u002Fworkflows\u002Foutline-template.md` | Outline template with layout guide |\n| `references\u002Fworkflows\u002Fprompt-assembly.md` | Prompt assembly guide |\n| `references\u002Fconfig\u002Fpreferences-schema.md` | EXTEND.md schema |\n| `references\u002Fconfig\u002Ffirst-time-setup.md` | First-time setup flow |\n| `references\u002Fconfig\u002Fwatermark-guide.md` | Watermark configuration |\n\n## Notes\n\n- Auto-retry once on generation failure before reporting an error.\n- For sensitive public figures, use stylized cartoon alternatives.\n- Smart Confirm (Step 2) is required; Detailed mode adds a second confirmation (2a + 2c).\n\n## Changing Preferences\n\nEXTEND.md lives at the first matching path listed in Step 0. Three ways to change it:\n\n- **Edit directly** — open EXTEND.md and change fields. Full schema: `references\u002Fconfig\u002Fpreferences-schema.md`.\n- **Reconfigure interactively** — delete EXTEND.md (or ask \"reconfigure baoyu-xhs-images preferences\" \u002F \"重新配置\"). The next run re-triggers first-time setup.\n- **Common one-line edits**:\n  - `preferred_image_backend: auto` — default; runtime-native tool wins, falls back to the only installed backend, asks only if multiple non-native are present.\n  - `preferred_image_backend: codex-imagegen` — pin to Codex's built-in.\n  - `preferred_image_backend: baoyu-image-gen` — pin to the baoyu-image-gen skill.\n  - `preferred_image_backend: ask` — confirm backend every run.\n  - `generation_batch_size: 4` — default number of images to render concurrently when the backend\u002Fruntime supports batch or parallel generation.\n  - `preferred_style: notion`, `preferred_layout: dense`, `preferred_palette: macaron`, `language: zh`.\n  - `watermark.enabled: true` + `watermark.content: \"@handle\"` — add a watermark.\n","# Image Card Series Generator\n\nBreak down complex content into eye-catching image card series with multiple style options.\n\n## User Input Tools\n\nWhen this skill prompts the user, follow this tool-selection rule (priority order):\n\n1. **Prefer built-in user-input tools** exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.\n2. **Fallback**: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number\u002Fanswer for each question.\n3. **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.\n\nConcrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.\n\n## Image Generation Tools\n\nResolve the image backend in this order:\n\n1. **User names a backend** in the current message → use it.\n2. **`preferred_image_backend`** in `EXTEND.md` names a backend available now → use it. `ask` means ask every run.\n3. **Auto-select** (preference `auto`, unset, or the pinned backend is unavailable), first match wins:\n   - **Codex `imagegen`** skill is in your available skills → you are in Codex and MUST use it: `Skill` with `skill: \"imagegen\"`, passing the prompt file's content plus output path and aspect ratio. It outranks non-native skills such as `baoyu-image-gen`.\n   - **Codex via `codex exec` (`codex-imagegen`)**: no native `imagegen`, but the `codex` CLI is on `PATH` with an active `codex login` → `baoyu-image-gen --provider codex-cli` (preferred), or the bundled wrapper if baoyu-image-gen is unavailable. Load [references\u002Fcodex-imagegen.md](references\u002Fcodex-imagegen.md) only for this branch.\n   - **Cursor `GenerateImage`** → use it (outranks non-native skills). It has no aspect-ratio parameter, so state the aspect ratio \u002F dimensions in the `description` prompt; it saves to a tool-managed location, so copy the file to the expected output path (e.g., `outputs\u002F...\u002FNN-xxx.png`). Reference images go in `reference_image_paths`.\n   - **Other runtime-native image tool** (e.g., Hermes `image_generate`) → use it the same way.\n   - Exactly one non-native backend installed (e.g., `baoyu-image-gen`) → use it.\n   - Several non-native backends → ask the user once, batched with other initial questions.\n4. **None available** → tell the user and ask how to proceed.\n\n**⛔ Raster only**: never substitute SVG, HTML\u002FCSS, canvas, or other code-based rendering for a raster image, even for diagram-like content. If no raster backend resolves, go to step 4.\n\n**⛔ No bitmap text patching**: never use ImageMagick, Pillow, Canvas, SVG, HTML\u002FCSS, 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.\n\n**Prompt file (hard)**: before invoking any backend, write each image's full, final prompt to its own file under `prompts\u002F` (`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.\n\nChange the pinned backend via `## Changing Preferences` below. Tool names above are examples; use the local equivalent in other runtimes.\n\n## Batch Generation Policy\n\nAfter every prompt file for the current generation group has been saved and verified, generate images in batches by default.\n\nPriority order:\n\n1. Use the chosen backend's native batch \u002F multi-task interface if it exists. Each task must keep its own prompt file, output path, aspect ratio, session ID, and direct reference images.\n2. If no native batch interface exists but the runtime can issue parallel tool calls, dispatch up to `generation_batch_size` images at a time. Default: `4`. An explicit user request in the current message, such as `--batch-size 4` or \"并行 4 张一起生成\", overrides EXTEND.md.\n3. If neither native batch nor parallel tool calls are available, generate sequentially.\n\nRules:\n\n- Honor the image-1 anchor chain: generate image 1 first, then batch images 2+ using image 1 as the reference.\n- Never start a batch until every selected prompt file for that batch exists on disk.\n- Retry failed items once without regenerating successful items.\n- Do not use subagents merely to parallelize image rendering. Use subagents only for separate prompt iteration or creative exploration.\n\n## Confirmation Policy\n\nDefault behavior: **confirm before generation**.\n\n- Treat explicit skill invocation, a file path, matched signals\u002Fpresets, and `EXTEND.md` defaults as **recommendation inputs only**. None of them authorizes skipping confirmation.\n- Do **not** start Step 3 until the user completes Step 2.\n- 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.\n- If confirmation is skipped explicitly, state the assumed strategy \u002F style \u002F layout \u002F palette \u002F count \u002F backend in the next user-facing update before generating.\n\n## Language\n\nRespond in the user's language across questions, progress, errors, and completion summary. Keep technical tokens (style names, file paths, code) in English.\n\n## Options\n\n| Option | Description |\n|--------|-------------|\n| `--style \u003Cname>` | Visual style (see Styles below) |\n| `--layout \u003Cname>` | Information layout (see Layouts below) |\n| `--palette \u003Cname>` | Color override: macaron \u002F warm \u002F neon |\n| `--preset \u003Cname>` | Style + layout + optional palette shorthand (see `references\u002Fstyle-presets.md`) |\n| `--ref \u003Cfiles...>` | Reference images applied to image 1 as the series anchor |\n| `--batch-size \u003Cn>` | Temporary generation batch size for this run. Default: `generation_batch_size` from EXTEND.md, otherwise 4. Clamp to 1-8. |\n| `--yes` | Non-interactive: skip all confirmations, use EXTEND.md or built-in defaults, auto-confirm recommended plan (Path A) |\n\n## Dimensions\n\nThree independent knobs combine freely:\n\n| Dimension | Controls | Options |\n|-----------|----------|---------|\n| **Style** | Visual aesthetics (lines, decorations, rendering) | 12 styles (see Styles below) |\n| **Layout** | Information structure (density, arrangement) | 8 layouts (see Layouts below) |\n| **Palette** (optional) | Color override, replaces the style's default colors | macaron \u002F warm \u002F neon (see Palettes below) |\n\nExample: `--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).\n\n**Palette behavior**: no `--palette` → style's built-in colors; `--palette \u003Cname>` → overrides colors only, rendering rules unchanged. Some styles declare a `default_palette` (e.g., sketch-notes defaults to macaron).\n\n## Styles (12)\n\n| Style | Description |\n|-------|-------------|\n| `cute` (Default) | Sweet, adorable, girly aesthetic |\n| `fresh` | Clean, refreshing, natural |\n| `warm` | Cozy, friendly, approachable |\n| `bold` | High impact, attention-grabbing |\n| `minimal` | Ultra-clean, sophisticated |\n| `retro` | Vintage, nostalgic, trendy |\n| `pop` | Vibrant, energetic, eye-catching |\n| `notion` | Minimalist hand-drawn line art, intellectual |\n| `chalkboard` | Colorful chalk on black board, educational |\n| `study-notes` | Realistic handwritten photo style, blue pen + red annotations + yellow highlighter |\n| `screen-print` | Bold poster art, halftone textures, limited colors, symbolic storytelling |\n| `sketch-notes` | Hand-drawn educational infographic, macaron pastels on warm cream, wobble lines |\n\nPer-style specifications: `references\u002Fpresets\u002F\u003Cstyle>.md`.\n\n## Layouts (8)\n\n| Layout | Description |\n|--------|-------------|\n| `sparse` (Default) | 1-2 points, maximum impact |\n| `balanced` | 3-4 points, standard |\n| `dense` | 5-8 points, knowledge-card style |\n| `list` | Enumeration \u002F ranking (4-7 items) |\n| `comparison` | Side-by-side contrast |\n| `flow` | Process \u002F timeline (3-6 steps) |\n| `mindmap` | Center-radial (4-8 branches) |\n| `quadrant` | Four-quadrant \u002F circular sections |\n\nLayout specs: `references\u002Felements\u002Fcanvas.md`.\n\n## Palettes (optional override)\n\nReplaces the style's colors while keeping rendering rules (line treatment, textures) intact.\n\n| Palette | Background | Zone Colors | Accent | Feel |\n|---------|------------|-------------|--------|------|\n| `macaron` | Warm cream #F5F0E8 | Blue #A8D8EA, Lavender #D5C6E0, Mint #B5E5CF, Peach #F8D5C4 | Coral #E8655A | Soft, educational |\n| `warm` | Soft peach #FFECD2 | Orange #ED8936, Terracotta #C05621, Golden #F6AD55, Rose #D4A09A | Sienna #A0522D | Earth tones, cozy |\n| `neon` | Dark purple #1A1025 | Cyan #00F5FF, Magenta #FF00FF, Green #39FF14, Pink #FF6EC7 | Yellow #FFFF00 | High-energy, futuristic |\n\nPalette specs: `references\u002Fpalettes\u002F\u003Cpalette>.md`.\n\n## Presets (style + layout shortcuts)\n\n26 presets grouped by scenario (knowledge, lifestyle, impact, trend, poster). Read `references\u002Fstyle-presets.md` when the user passes `--preset` or when recommending a preset in Step 2.\n\n## Auto-Selection\n\nMatch content signals to the best combo. First row whose keywords appear wins; fall back to `cute-share` if nothing matches.\n\n| Signals in source | Style | Layout | Recommended preset |\n|-------------------|-------|--------|--------------------|\n| beauty, fashion, cute, girl, pink | `cute` | sparse\u002Fbalanced | `cute-share`, `girly` |\n| health, nature, fresh, organic | `fresh` | balanced\u002Fflow | `product-review`, `nature-flow` |\n| life, story, emotion, warm | `warm` | balanced | `cozy-story` |\n| warning, important, must, critical | `bold` | list\u002Fcomparison | `warning`, `versus` |\n| professional, business, elegant | `minimal` | sparse\u002Fbalanced | `clean-quote`, `pro-summary` |\n| classic, vintage, traditional | `retro` | balanced | `throwback`, `retro-ranking` |\n| fun, exciting, wow, amazing | `pop` | sparse\u002Flist | `hype`, `pop-facts` |\n| knowledge, concept, productivity, SaaS | `notion` | dense\u002Flist | `knowledge-card`, `checklist` |\n| education, tutorial, learning, classroom | `chalkboard` | balanced\u002Fdense | `tutorial`, `classroom` |\n| notes, handwritten, study guide, realistic | `study-notes` | dense\u002Flist\u002Fmindmap | `study-guide` |\n| movie, poster, opinion, editorial, cinematic | `screen-print` | sparse\u002Fcomparison | `poster`, `editorial`, `cinematic` |\n| hand-drawn, infographic, workflow, 手绘，图解 | `sketch-notes` | flow\u002Fbalanced\u002Fdense | `hand-drawn-edu`, `sketch-card`, `sketch-summary` |\n\n## Style × Layout Matrix\n\nWhen the user picks a non-default style + layout combo, check `references\u002Fstyle-layout-matrix.md` and flag poor matches (✗).\n\n## Outline Strategies\n\nThree differentiated approaches — each produces a structurally different outline. The workflow recommends one; Path C generates all three and lets the user choose.\n\n| Strategy | Concept | Best for | Structure |\n|----------|---------|----------|-----------|\n| **A — Story-Driven** | Personal experience as the thread, emotional resonance first | Reviews, personal shares, transformation | Hook → Problem → Discovery → Experience → Conclusion |\n| **B — Information-Dense** | Value-first, efficient information delivery | Tutorials, comparisons, checklists | Core conclusion → Info card → Pros\u002FCons → Recommendation |\n| **C — Visual-First** | Visual impact as core, minimal text | High-aesthetic products, lifestyle, mood content | Hero image → Detail shots → Lifestyle scene → CTA |\n\n## Reference Images\n\nOnly when the user supplies refs (`--ref \u003Cfiles...>` or pasted paths): read `references\u002Freference-images.md` for intake, usage modes (`direct` \u002F `style` \u002F `palette`), prompt frontmatter, and how refs combine with the image-1 anchor chain.\n\n## File Layout\n\n```\nimage-cards\u002F{topic-slug}\u002F\n├── source-{slug}.{ext}\n├── analysis.md\n├── outline-strategy-{a,b,c}.md    # Path C only\n├── outline.md\n├── prompts\u002FNN-{type}-{slug}.md\n├── NN-{type}-{slug}.png\n└── refs\u002F                          # only if --ref used\n```\n\n**Slug**: 2-4 words, kebab-case. \"AI 工具推荐\" → `ai-tools-recommend`. On collision, append `-YYYYMMDD-HHMMSS`.\n\n**Backup rule** (applies throughout): before overwriting any file — source, outline, prompt, image — rename the existing one to `\u003Cname>-backup-YYYYMMDD-HHMMSS.\u003Cext>`. This protects user edits.\n\n## Workflow\n\n```\n- [ ] Step 0: Load EXTEND.md ⛔ BLOCKING (interactive only)\n- [ ] Step 1: Analyze content → analysis.md\n- [ ] Step 2: Smart Confirm ⚠️ REQUIRED (Path A \u002F B \u002F C)\n- [ ] Step 3: Generate images\n- [ ] Step 4: Completion report\n```\n\n### Step 0: Load EXTEND.md ⛔ BLOCKING\n\nCheck these paths in order; first hit wins:\n\n| Path | Scope |\n|------|-------|\n| `.baoyu-skills\u002Fbaoyu-xhs-images\u002FEXTEND.md` | Project |\n| `${XDG_CONFIG_HOME:-$HOME\u002F.config}\u002Fbaoyu-skills\u002Fbaoyu-xhs-images\u002FEXTEND.md` | XDG |\n| `$HOME\u002F.baoyu-skills\u002Fbaoyu-xhs-images\u002FEXTEND.md` | User home |\n\n- **Found** → read, parse, print a summary (style \u002F layout \u002F watermark \u002F language), continue.\n- **Not found + interactive** → run first-time setup (see `references\u002Fconfig\u002Ffirst-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.\n- **Not found + `--yes`** → skip setup, use built-in defaults (no watermark, style\u002Flayout auto-selected, language from content). Do not prompt, do not create EXTEND.md.\n\n**EXTEND.md keys**: watermark, preferred style\u002Flayout, custom style definitions, language preference, preferred image backend, generation batch size. Schema: `references\u002Fconfig\u002Fpreferences-schema.md`.\n\n### Step 1: Analyze Content → `analysis.md`\n\n1. Save the source (backup rule applies if `source.md` exists).\n2. Run the deep analysis in `references\u002Fworkflows\u002Fanalysis-framework.md`: content type, hook potential, audience, engagement signals, visual opportunity map, swipe flow.\n3. Detect source language, pick recommended image count (2-10).\n4. Auto-recommend strategy + style + layout + palette using the **Auto-Selection** table above.\n5. Write everything to `analysis.md`.\n\n### Step 2: Smart Confirm ⚠️ REQUIRED\n\n**Hard gate**: this step is mandatory per the [Confirmation Policy](#confirmation-policy) — Step 3 cannot start until the user confirms here (or explicitly opts out with `--yes` \u002F equivalent wording in the current request).\n\nGoal: 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.\n\n**Display summary** before asking:\n\n```\n📋 内容分析\n  主题：[topic] | 类型：[content_type]\n  要点：[key points]\n  受众：[audience]\n\n🎨 推荐方案（自动匹配）\n  策略：[A\u002FB\u002FC] [name]（[reason]）\n  风格：[style] · 布局：[layout] · 配色：[palette or 默认] · 预设：[preset]\n  图片：[N]张（封面+[N-2]内容+结尾）\n  元素：[background] \u002F [decorations] \u002F [emphasis]\n```\n\nThen ask one question — three paths. Verbatim option copy: `references\u002Fconfirmation.md`.\n\n**Path A — Quick confirm** (trust auto-recommendation): generate a single outline using the recommended strategy + style → save to `outline.md` → Step 3.\n\n**Path B — Customize**: ask five questions (strategy\u002Fstyle, 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\u002Fconfirmation.md`.\n\n**Path C — Detailed mode**: two sub-confirmations.\n\n- *Step 2a — Content understanding*: ask selling points (multi-select), audience, style preference (authentic \u002F professional \u002F aesthetic \u002F auto), optional context. Update `analysis.md`.\n- *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 — include `style_reason` in the frontmatter. Page-count heuristic: A ~4-6, B ~3-5, C ~3-4. Template: `references\u002Fworkflows\u002Foutline-template.md`; frontmatter example in `references\u002Fconfirmation.md`.\n- *Step 2c — Selection*: ask three questions (outline A\u002FB\u002FC\u002FCombined, style, visual elements). Save selected\u002Fmerged outline to `outline.md` → Step 3.\n\n### Step 3: Generate Images\n\nWith confirmed outline + style + layout + palette:\n\n**Visual consistency — image-1 anchor chain**: character \u002F mascot \u002F 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.\n\nGeneration flow:\n\n1. Write the full prompt for every image to `prompts\u002FNN-{type}-{slug}.md` in the user's preferred language (backup rule applies), then verify all selected prompt files exist.\n2. Generate **image 1** first without `--ref`; backup rule applies to the PNG file. This establishes the anchor.\n3. Build a task list for **images 2+** using image 1 as `--ref \u003Cpath-to-image-01.png>`.\n4. Dispatch images 2+ in batches per the `## Batch Generation Policy`: backend native batch first, runtime parallel tool calls second, sequential only as fallback.\n5. Report progress after each completed image. On failure, retry only the failed item once from the same saved prompt file.\n\n**Watermark** (if enabled in EXTEND.md): append to the generation prompt:\n\n```\nInclude a subtle watermark \"[content]\" positioned at [position].\nThe watermark should be legible but not distracting.\n```\n\nSee `references\u002Fconfig\u002Fwatermark-guide.md`.\n\n**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.\n\n**`codex-imagegen` invocation**: when the rule resolves to `codex-imagegen`, see [references\u002Fcodex-imagegen.md](references\u002Fcodex-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).\n\n**Session ID** (if the backend supports `--sessionId`): use `cards-{topic-slug}-{timestamp}` for every image; combined with the ref chain this gives maximum consistency.\n\n### Step 4: Completion Report\n\n```\nImage Card Series Complete!\n\nTopic: [topic]\nMode: [Quick \u002F Custom \u002F Detailed]\nStrategy: [A\u002FB\u002FC\u002FCombined]\nStyle: [name]\nPalette: [name or \"default\"]\nLayout: [name or \"varies\"]\nLocation: [directory]\nImages: N total\n\n✓ analysis.md\n✓ outline.md\n✓ outline-strategy-a\u002Fb\u002Fc.md (detailed mode only)\n\n- 01-cover-[slug].png ✓ Cover (sparse)\n- 02-content-[slug].png ✓ Content (balanced)\n- ...\n- NN-ending-[slug].png ✓ Ending (sparse)\n```\n\n## Content Breakdown Principles\n\n| Position | Purpose | Typical layout |\n|----------|---------|----------------|\n| Cover (image 1) | Hook + visual impact | `sparse` |\n| Content (middle) | Core value per image | `balanced` \u002F `dense` \u002F `list` \u002F `comparison` \u002F `flow` |\n| Ending (last) | CTA \u002F summary | `sparse` or `balanced` |\n\nFor the style × layout compatibility matrix, see `references\u002Fstyle-layout-matrix.md`.\n\n## Image Modification\n\nWhen the user asks to edit, add, delete, or fix text on a card after generation, read `references\u002Fimage-modification.md` first. Always update the prompt file before regenerating, and never patch bitmap text with code.\n\n## References\n\n| File | Content |\n|------|---------|\n| `references\u002Fconfirmation.md` | Verbatim AskUserQuestion copy for every confirmation path |\n| `references\u002Fstyle-presets.md` | Full preset shortcut definitions, presets grouped by scenario |\n| `references\u002Fstyle-layout-matrix.md` | Style × layout compatibility scores |\n| `references\u002Freference-images.md` | User-supplied reference image intake and usage |\n| `references\u002Fimage-modification.md` | Edit \u002F add \u002F delete cards, text correction policy |\n| `references\u002Fpresets\u002F\u003Cstyle>.md` | Per-style element definitions |\n| `references\u002Fpalettes\u002F\u003Cname>.md` | Per-palette color definitions |\n| `references\u002Felements\u002Fcanvas.md` | Aspect ratios, safe zones, grid layouts |\n| `references\u002Felements\u002Fimage-effects.md` | Cutout, stroke, filters |\n| `references\u002Felements\u002Ftypography.md` | Decorated text, tags, text direction |\n| `references\u002Felements\u002Fdecorations.md` | Emphasis marks, backgrounds, doodles, frames |\n| `references\u002Fworkflows\u002Fanalysis-framework.md` | Content analysis framework |\n| `references\u002Fworkflows\u002Foutline-template.md` | Outline template with layout guide |\n| `references\u002Fworkflows\u002Fprompt-assembly.md` | Prompt assembly guide |\n| `references\u002Fconfig\u002Fpreferences-schema.md` | EXTEND.md schema |\n| `references\u002Fconfig\u002Ffirst-time-setup.md` | First-time setup flow |\n| `references\u002Fconfig\u002Fwatermark-guide.md` | Watermark configuration |\n\n## Notes\n\n- Auto-retry once on generation failure before reporting an error.\n- For sensitive public figures, use stylized cartoon alternatives.\n- Smart Confirm (Step 2) is required; Detailed mode adds a second confirmation (2a + 2c).\n\n## Changing Preferences\n\nEXTEND.md lives at the first matching path listed in Step 0. Three ways to change it:\n\n- **Edit directly** — open EXTEND.md and change fields. Full schema: `references\u002Fconfig\u002Fpreferences-schema.md`.\n- **Reconfigure interactively** — delete EXTEND.md (or ask \"reconfigure baoyu-xhs-images preferences\" \u002F \"重新配置\"). The next run re-triggers first-time setup.\n- **Common one-line edits**:\n  - `preferred_image_backend: auto` — default; runtime-native tool wins, falls back to the only installed backend, asks only if multiple non-native are present.\n  - `preferred_image_backend: codex-imagegen` — pin to Codex's built-in.\n  - `preferred_image_backend: baoyu-image-gen` — pin to the baoyu-image-gen skill.\n  - `preferred_image_backend: ask` — confirm backend every run.\n  - `generation_batch_size: 4` — default number of images to render concurrently when the backend\u002Fruntime supports batch or parallel generation.\n  - `preferred_style: notion`, `preferred_layout: dense`, `preferred_palette: macaron`, `language: zh`.\n  - `watermark.enabled: true` + `watermark.content: \"@handle\"` — add a watermark.\n",{"name":5,"metadata":25,"description":7},{"openclaw":26,"upstream-version":28},{"homepage":27},"https:\u002F\u002Fgithub.com\u002FJimLiu\u002Fbaoyu-skills#baoyu-xhs-images","2.0.1","main","2a870f189175a48c39f5f7e26a6d93b0be9cd13b",0,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills","https:\u002F\u002Ftangyixiao.github.io\u002Ftangyixiao-skills\u002F","https:\u002F\u002Fgithub.com\u002Ftangyixiao","http:\u002F\u002Fwww.sxyz.net\u002F","I am Tang Yixiao, a student in Shaoxing No.1 High School. I am eager to learn on GitHub and contribute my part to this community.","2026-11-11 15:45:59",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add tangyixiao\u002Ftangyixiao-skills --skill baoyu-xhs-images",{"tool":44,"command":45},"bunx","bunx skills add tangyixiao\u002Ftangyixiao-skills --skill baoyu-xhs-images",{"tool":47,"command":48},"pnpm","pnpm dlx skills add tangyixiao\u002Ftangyixiao-skills --skill baoyu-xhs-images","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002FSKILL.md",true,[52,58,62,66,70,74,78,82,86,90,94,98,102,106,110,114,118,122,126,130,134,138,142,146,150,154,158,162,166,170,174,178,182],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"INSTALL-SOURCE.json","REFERENCE","参考文档",543,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002FINSTALL-SOURCE.json",{"path":59,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":16},"LICENSE","许可证",1064,{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fcodex-imagegen.md",3717,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fcodex-imagegen.md",{"path":67,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fconfig\u002Ffirst-time-setup.md",3456,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fconfig\u002Ffirst-time-setup.md",{"path":71,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fconfig\u002Fpreferences-schema.md",4017,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fconfig\u002Fpreferences-schema.md",{"path":75,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fconfig\u002Fwatermark-guide.md",1977,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fconfig\u002Fwatermark-guide.md",{"path":79,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fconfirmation.md",3929,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fconfirmation.md",{"path":83,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Felements\u002Fcanvas.md",3727,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Felements\u002Fcanvas.md",{"path":87,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Felements\u002Fdecorations.md",5049,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Felements\u002Fdecorations.md",{"path":91,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Felements\u002Fimage-effects.md",2990,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Felements\u002Fimage-effects.md",{"path":95,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Felements\u002Ftypography.md",3258,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Felements\u002Ftypography.md",{"path":99,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fimage-modification.md",888,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fimage-modification.md",{"path":103,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fpalettes\u002Fmacaron.md",1437,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpalettes\u002Fmacaron.md",{"path":107,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fpalettes\u002Fneon.md",1271,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpalettes\u002Fneon.md",{"path":111,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Fpalettes\u002Fwarm.md",1225,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpalettes\u002Fwarm.md",{"path":115,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fpresets\u002Fbold.md",1577,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fbold.md",{"path":119,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Fpresets\u002Fchalkboard.md",2324,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fchalkboard.md",{"path":123,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Fpresets\u002Fcute.md",1565,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fcute.md",{"path":127,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":128,"sourceHtmlUrl":129},"references\u002Fpresets\u002Ffresh.md",1496,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Ffresh.md",{"path":131,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":132,"sourceHtmlUrl":133},"references\u002Fpresets\u002Fminimal.md",1418,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fminimal.md",{"path":135,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":136,"sourceHtmlUrl":137},"references\u002Fpresets\u002Fnotion.md",1591,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fnotion.md",{"path":139,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":140,"sourceHtmlUrl":141},"references\u002Fpresets\u002Fpop.md",1528,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fpop.md",{"path":143,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":144,"sourceHtmlUrl":145},"references\u002Fpresets\u002Fretro.md",1483,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fretro.md",{"path":147,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":148,"sourceHtmlUrl":149},"references\u002Fpresets\u002Fscreen-print.md",2680,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fscreen-print.md",{"path":151,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":152,"sourceHtmlUrl":153},"references\u002Fpresets\u002Fsketch-notes.md",3216,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fsketch-notes.md",{"path":155,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":156,"sourceHtmlUrl":157},"references\u002Fpresets\u002Fstudy-notes.md",2977,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fstudy-notes.md",{"path":159,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":160,"sourceHtmlUrl":161},"references\u002Fpresets\u002Fwarm.md",1476,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fpresets\u002Fwarm.md",{"path":163,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":164,"sourceHtmlUrl":165},"references\u002Freference-images.md",1176,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Freference-images.md",{"path":167,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":168,"sourceHtmlUrl":169},"references\u002Fstyle-layout-matrix.md",1315,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fstyle-layout-matrix.md",{"path":171,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":172,"sourceHtmlUrl":173},"references\u002Fstyle-presets.md",4185,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fstyle-presets.md",{"path":175,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":176,"sourceHtmlUrl":177},"references\u002Fworkflows\u002Fanalysis-framework.md",7235,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fworkflows\u002Fanalysis-framework.md",{"path":179,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":180,"sourceHtmlUrl":181},"references\u002Fworkflows\u002Foutline-template.md",6101,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fworkflows\u002Foutline-template.md",{"path":183,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":184,"sourceHtmlUrl":185},"references\u002Fworkflows\u002Fprompt-assembly.md",10328,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbaoyu-xhs-images\u002Freferences\u002Fworkflows\u002Fprompt-assembly.md",[187,196,204,212,220,228],{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":191,"licenseFileUrl":192,"sourceHtmlUrl":193,"categories":194,"keywords":195,"publishedAt":20},"01M7D8JK8FYBFNNAJXWD89CFH7","xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FSKILL.md",[],[],{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":200,"sourceHtmlUrl":201,"categories":202,"keywords":203,"publishedAt":20},"01M7D8JG8ERGGQQAMX0DWCG9GR","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FSKILL.md",[],[],{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":208,"sourceHtmlUrl":209,"categories":210,"keywords":211,"publishedAt":20},"01M7D8JE672GW3EHSE8EF185M4","writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FSKILL.md",[],[],{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":216,"sourceHtmlUrl":217,"categories":218,"keywords":219,"publishedAt":20},"01M7D8JBK572YDFMND8Q6CEYJW","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":221,"name":222,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":224,"sourceHtmlUrl":225,"categories":226,"keywords":227,"publishedAt":20},"01M7D8J5QPWEXX61EGBKYH73R8","writing-clearly-and-concisely","Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FSKILL.md",[],[],{"skillNo":229,"name":230,"nameZh":6,"description":231,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":232,"sourceHtmlUrl":233,"categories":234,"keywords":235,"publishedAt":20},"01M7D8J36YWC8WZS5DK5AH03CD","writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FSKILL.md",[],[]]