baoyu-xhs-images

Name: baoyu-xhs-images
Author: jimliu

byjimliu· 68 skills

Installs

29k

Stars

24k

Forks

2.7k

How to install baoyu-xhs-images?

jimliu/baoyu-skills/baoyu-xhs-images

$npx -y skills add jimliu/baoyu-skills --skill baoyu-xhs-images

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/jimliu/baoyu-skills" --skill "jimliu/baoyu-skills/baoyu-xhs-images"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/jimliu/baoyu-skills" that are relevant to the current task. Run `npx skills add "https://github.com/jimliu/baoyu-skills"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub

SKILL.md

1	# Image Card Series Generator
2
3	Break down complex content into eye-catching image card series with multiple style options.
4
5	## User Input Tools
6
7	When this skill prompts the user, follow this tool-selection rule (priority order):
8
9	1. Prefer built-in user-input tools exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.
10	2. Fallback: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
11	3. 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.
12
13	Concrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.
14
15	## Image Generation Tools
16
17	When this skill needs to render an image, resolve the backend in this order:
18
19	1. Current-request override — if the user names a specific backend in the current message, use it.
20	2. Saved preference — if `EXTEND.md` sets `preferred_image_backend` to a backend available right now, use it.
21	3. Auto-select (when the preference is `auto`, unset, or the pinned backend isn't available):
22	- Codex (`imagegen`) — first, inspect your available-skills / tool inventory. If a skill named `imagegen` is listed, you are running inside Codex and MUST use it: invoke via the `Skill` tool with `skill: "imagegen"`, passing the saved prompt file's content (plus output path and aspect ratio per Codex `imagegen`'s own args). Codex `imagegen` is the official raster backend in that runtime and outranks any non-native skill (e.g., `baoyu-image-gen`) unless the user has explicitly pinned a different `preferred_image_backend`.
23	- Codex via `codex exec` (`codex-imagegen`) — if the current runtime exposes no native `imagegen` skill but the `codex` CLI is on `PATH` with an active `codex login`, route through `baoyu-image-gen --provider codex-cli` (preferred), or — if baoyu-image-gen is unavailable — invoke the bundled wrapper directly. Details, parameters, and the runtime-discovery procedure live in [references/codex-imagegen.md](references/codex-imagegen.md) — load that file only when this branch is selected.
24	- Cursor (`GenerateImage`) — if the runtime exposes a native `GenerateImage` tool, you are running inside Cursor and it outranks any non-native skill the same way Codex `imagegen` does. Two hard caveats: (a) it has no aspect-ratio parameter — state the target aspect ratio / dimensions explicitly in the prompt text passed as `description`; (b) it does not accept an output directory — it saves to a tool-managed location, so after generation copy/move the file to the skill's expected output path (e.g., `outputs/.../NN-xxx.png`). Reference images go in `reference_image_paths`.
25	- Other runtime-native tools — if the runtime exposes a different native image tool (e.g., Hermes `image_generate`), use it the same way.
26	- Otherwise, if exactly one non-native backend is installed (e.g., `baoyu-image-gen`), use it.
27	- Otherwise (multiple non-native backends with no runtime-native tool), ask the user once — batch with any other initial questions.
28	4. If none are available, tell the user and ask how to proceed.
29
30	⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation. Codex `imagegen`'s own description says it should be used "when the output should be a bitmap asset rather than repo-native code or vector." If you cannot resolve a raster backend via step 3, fall through to step 4 and ask the user — do not silently emit SVG, write inline `<svg>` markup, or produce HTML/CSS art as a substitute. This applies even if the article/section seems "diagram-like": the consumer skill calling this rule has already decided that a raster image is what it needs.
31
32	⛔ Never repair rendered text by painting over a generated bitmap. Do not use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other programmatic overlay to cover, rewrite, erase, stroke, or replace titles, body copy, tags, or any other text inside an already generated image card. If text is wrong or unclear, regenerate from a corrected prompt, switch to a layout with less on-card text, or ask the user which imperfect candidate to keep.
33
34	Setting `preferred_image_backend: ask` forces the step-3 prompt every run regardless of available backends. Users change the pinned backend via the `## Changing Preferences` section below.
35
36	Prompt file requirement (hard): write each image's full, final prompt to a standalone file under `prompts/` (naming: `NN-{type}-[slug].md`) BEFORE invoking any backend. The file is the reproducibility record and lets you switch backends without regenerating prompts.
37
38	Concrete tool names (`imagegen`, `GenerateImage`, `image_generate`, `baoyu-image-gen`) above are examples — substitute the local equivalents under the same rule.
39
40	## Batch Generation Policy
41
42	After every prompt file for the current generation group has been saved and verified, generate images in batches by default.
43
44	Priority order:
45
46	1. 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.
47	2. 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.
48	3. If neither native batch nor parallel tool calls are available, generate sequentially.
49
50	Rules:
51
52	- Honor the image-1 anchor chain: generate image 1 first, then batch images 2+ using image 1 as the reference.
53	- Never start a batch until every selected prompt file for that batch exists on disk.
54	- Retry failed items once without regenerating successful items.
55	- Do not use subagents merely to parallelize image rendering. Use subagents only for separate prompt iteration or creative exploration.
56
57	## Confirmation Policy
58
59	Default behavior: confirm before generation.
60
61	- Treat explicit skill invocation, a file path, matched signals/presets, and `EXTEND.md` defaults as recommendation inputs only. None of them authorizes skipping confirmation.
62	- Do not start Step 3 until the user completes Step 2.
63	- 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.
64	- If confirmation is skipped explicitly, state the assumed strategy / style / layout / palette / count / backend in the next user-facing update before generating.
65
66	## Language
67
68	Respond in the user's language across questions, progress, errors, and completion summary. Keep technical tokens (style names, file paths, code) in English.
69
70	## Options
71
72	\| Option \| Description \|
73	\|--------\|-------------\|
74	\| `--style <name>` \| Visual style (see Styles below) \|
75	\| `--layout <name>` \| Information layout (see Layouts below) \|
76	\| `--palette <name>` \| Color override: macaron / warm / neon \|
77	\| `--preset <name>` \| Style + layout + optional palette shorthand (see Presets below; per-preset prompt fragments in `references/style-presets.md`) \|
78	\| `--ref <files...>` \| Reference images applied to image 1 as the series anchor \|
79	\| `--batch-size <n>` \| Temporary generation batch size for this run. Default: `generation_batch_size` from EXTEND.md, otherwise 4. Clamp to 1-8. \|
80	\| `--yes` \| Non-interactive: skip all confirmations, use EXTEND.md or built-in defaults, auto-confirm recommended plan (Path A) \|
81
82	## Dimensions
83
84	Three independent knobs combine freely:
85
86	\| Dimension \| Controls \| Options \|
87	\|-----------\|----------\|---------\|
88	\| Style \| Visual aesthetics (lines, decorations, rendering) \| 12 styles (see Styles below) \|
89	\| Layout \| Information structure (density, arrangement) \| 8 layouts (see Layouts below) \|
90	\| Palette (optional) \| Color override, replaces the style's default colors \| macaron / warm / neon (see Palettes below) \|
91
92	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).
93
94	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).
95
96	## Styles (12)
97
98	\| Style \| Description \|
99	\|-------\|-------------\|
100	\| `cute` (Default) \| Sweet, adorable, girly aesthetic \|
101	\| `fresh` \| Clean, refreshing, natural \|
102	\| `warm` \| Cozy, friendly, approachable \|
103	\| `bold` \| High impact, attention-grabbing \|
104	\| `minimal` \| Ultra-clean, sophisticated \|
105	\| `retro` \| Vintage, nostalgic, trendy \|
106	\| `pop` \| Vibrant, energetic, eye-catching \|
107	\| `notion` \| Minimalist hand-drawn line art, intellectual \|
108	\| `chalkboard` \| Colorful chalk on black board, educational \|
109	\| `study-notes` \| Realistic handwritten photo style, blue pen + red annotations + yellow highlighter \|
110	\| `screen-print` \| Bold poster art, halftone textures, limited colors, symbolic storytelling \|
111	\| `sketch-notes` \| Hand-drawn educational infographic, macaron pastels on warm cream, wobble lines \|
112
113	Per-style specifications: `references/presets/<style>.md`.
114
115	## Layouts (8)
116
117	\| Layout \| Description \|
118	\|--------\|-------------\|
119	\| `sparse` (Default) \| 1-2 points, maximum impact \|
120	\| `balanced` \| 3-4 points, standard \|
121	\| `dense` \| 5-8 points, knowledge-card style \|
122	\| `list` \| Enumeration / ranking (4-7 items) \|
123	\| `comparison` \| Side-by-side contrast \|
124	\| `flow` \| Process / timeline (3-6 steps) \|
125	\| `mindmap` \| Center-radial (4-8 branches) \|
126	\| `quadrant` \| Four-quadrant / circular sections \|
127
128	Layout specs: `references/elements/canvas.md`.
129
130	## Palettes (optional override)
131
132	Replaces the style's colors while keeping rendering rules (line treatment, textures) intact.
133
134	\| Palette \| Background \| Zone Colors \| Accent \| Feel \|
135	\|---------\|------------\|-------------\|--------\|------\|
136	\| `macaron` \| Warm cream #F5F0E8 \| Blue #A8D8EA, Lavender #D5C6E0, Mint #B5E5CF, Peach #F8D5C4 \| Coral #E8655A \| Soft, educational \|
137	\| `warm` \| Soft peach #FFECD2 \| Orange #ED8936, Terracotta #C05621, Golden #F6AD55, Rose #D4A09A \| Sienna #A0522D \| Earth tones, cozy \|
138	\| `neon` \| Dark purple #1A1025 \| Cyan #00F5FF, Magenta #FF00FF, Green #39FF14, Pink #FF6EC7 \| Yellow #FFFF00 \| High-energy, futuristic \|
139
140	Palette specs: `references/palettes/<palette>.md`.
141
142	## Presets (style + layout shortcuts)
143
144	Quick-start combos, grouped by scenario. Use `--preset <name>` or recommend during Step 2.
145
146	Knowledge & Learning:
147
148	\| Preset \| Style \| Layout \| Best For \|
149	\|--------\|-------\|--------\|----------\|
150	\| `knowledge-card` \| notion \| dense \| 干货知识卡、概念科普 \|
151	\| `checklist` \| notion \| list \| 清单、排行榜 \|
152	\| `concept-map` \| notion \| mindmap \| 概念图、知识脉络 \|
153	\| `swot` \| notion \| quadrant \| SWOT 分析、四象限 \|
154	\| `tutorial` \| chalkboard \| flow \| 教程步骤、操作流程 \|
155	\| `classroom` \| chalkboard \| balanced \| 课堂笔记、知识讲解 \|
156	\| `study-guide` \| study-notes \| dense \| 学习笔记、考试重点 \|
157	\| `hand-drawn-edu` \| sketch-notes \| flow \| 手绘教程、流程图解 \|
158	\| `sketch-card` \| sketch-notes \| dense \| 手绘知识卡 \|
159	\| `sketch-summary` \| sketch-notes \| balanced \| 手绘总结、图文笔记 \|
160
161	Lifestyle & Sharing:
162
163	\| Preset \| Style \| Layout \| Best For \|
164	\|--------\|-------\|--------\|----------\|
165	\| `cute-share` \| cute \| balanced \| 少女风分享、日常种草 \|
166	\| `girly` \| cute \| sparse \| 甜美封面、氛围感 \|
167	\| `cozy-story` \| warm \| balanced \| 生活故事、情感分享 \|
168	\| `product-review` \| fresh \| comparison \| 产品对比、测评 \|
169	\| `nature-flow` \| fresh \| flow \| 健康流程、自然主题 \|
170
171	Impact & Opinion:
172
173	\| Preset \| Style \| Layout \| Best For \|
174	\|--------\|-------\|--------\|----------\|
175	\| `warning` \| bold \| list \| 避坑指南、重要提醒 \|
176	\| `versus` \| bold \| comparison \| 正反对比 \|
177	\| `clean-quote` \| minimal \| sparse \| 金句、极简封面 \|
178	\| `pro-summary` \| minimal \| balanced \| 专业总结、商务内容 \|
179
180	Trend & Entertainment:
181
182	\| Preset \| Style \| Layout \| Best For \|
183	\|--------\|-------\|--------\|----------\|
184	\| `retro-ranking` \| retro \| list \| 复古排行、经典盘点 \|
185	\| `throwback` \| retro \| balanced \| 怀旧分享 \|
186	\| `pop-facts` \| pop \| list \| 趣味冷知识 \|
187	\| `hype` \| pop \| sparse \| 炸裂封面、惊叹分享 \|
188
189	Poster & Editorial:
190
191	\| Preset \| Style \| Layout \| Best For \|
192	\|--------\|-------\|--------\|----------\|
193	\| `poster` \| screen-print \| sparse \| 海报风封面、影评书评 \|
194	\| `editorial` \| screen-print \| balanced \| 观点文章、文化评论 \|
195	\| `cinematic` \| screen-print \| comparison \| 电影对比、戏剧张力 \|
196
197	Full prompt-fragment definitions: `references/style-presets.md`.
198
199	## Auto-Selection
200
201	Match content signals to the best combo. First row whose keywords appear wins; fall back to `cute-share` if nothing matches.
202
203	\| Signals in source \| Style \| Layout \| Recommended preset \|
204	\|-------------------\|-------\|--------\|--------------------\|
205	\| beauty, fashion, cute, girl, pink \| `cute` \| sparse/balanced \| `cute-share`, `girly` \|
206	\| health, nature, fresh, organic \| `fresh` \| balanced/flow \| `product-review`, `nature-flow` \|
207	\| life, story, emotion, warm \| `warm` \| balanced \| `cozy-story` \|
208	\| warning, important, must, critical \| `bold` \| list/comparison \| `warning`, `versus` \|
209	\| professional, business, elegant \| `minimal` \| sparse/balanced \| `clean-quote`, `pro-summary` \|
210	\| classic, vintage, traditional \| `retro` \| balanced \| `throwback`, `retro-ranking` \|
211	\| fun, exciting, wow, amazing \| `pop` \| sparse/list \| `hype`, `pop-facts` \|
212	\| knowledge, concept, productivity, SaaS \| `notion` \| dense/list \| `knowledge-card`, `checklist` \|
213	\| education, tutorial, learning, classroom \| `chalkboard` \| balanced/dense \| `tutorial`, `classroom` \|
214	\| notes, handwritten, study guide, realistic \| `study-notes` \| dense/list/mindmap \| `study-guide` \|
215	\| movie, poster, opinion, editorial, cinematic \| `screen-print` \| sparse/comparison \| `poster`, `editorial`, `cinematic` \|
216	\| hand-drawn, infographic, workflow, 手绘，图解 \| `sketch-notes` \| flow/balanced/dense \| `hand-drawn-edu`, `sketch-card`, `sketch-summary` \|
217
218	## Style × Layout Matrix
219
220	Compatibility scores (✓✓ highly recommended, ✓ works well, ✗ avoid). Use when the user picks a non-default combo and you want to flag a poor match.
221
222	\| \| sparse \| balanced \| dense \| list \| comparison \| flow \| mindmap \| quadrant \|
223	\|--------------\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|
224	\| cute \| ✓✓ \| ✓✓ \| ✓ \| ✓✓ \| ✓ \| ✓ \| ✓ \| ✓ \|
225	\| fresh \| ✓✓ \| ✓✓ \| ✓ \| ✓ \| ✓ \| ✓✓ \| ✓ \| ✓ \|
226	\| warm \| ✓✓ \| ✓✓ \| ✓ \| ✓ \| ✓✓ \| ✓ \| ✓ \| ✓ \|
227	\| bold \| ✓✓ \| ✓ \| ✓ \| ✓✓ \| ✓✓ \| ✓ \| ✓ \| ✓✓ \|
228	\| minimal \| ✓✓ \| ✓✓ \| ✓✓ \| ✓ \| ✓ \| ✓ \| ✓ \| ✓ \|
229	\| retro \| ✓✓ \| ✓✓ \| ✓ \| ✓✓ \| ✓ \| ✓ \| ✓ \| ✓ \|
230	\| pop \| ✓✓ \| ✓✓ \| ✓ \| ✓✓ \| ✓✓ \| ✓ \| ✓ \| ✓ \|
231	\| notion \| ✓✓ \| ✓✓ \| ✓✓ \| ✓✓ \| ✓✓ \| ✓✓ \| ✓✓ \| ✓✓ \|
232	\| chalkboard \| ✓✓ \| ✓✓ \| ✓✓ \| ✓✓ \| ✓ \| ✓✓ \| ✓✓ \| ✓ \|
233	\| study-notes \| ✗ \| ✓ \| ✓✓ \| ✓✓ \| ✓ \| ✓ \| ✓✓ \| ✓ \|
234	\| screen-print \| ✓✓ \| ✓✓ \| ✗ \| ✓ \| ✓✓ \| ✓ \| ✗ \| ✓✓ \|
235	\| sketch-notes \| ✓ \| ✓✓ \| ✓✓ \| ✓✓ \| ✓ \| ✓✓ \| ✓✓ \| ✓ \|
236
237	## Outline Strategies
238
239	Three differentiated approaches — each produces a structurally different outline. The workflow recommends one; Path C generates all three and lets the user choose.
240
241	\| Strategy \| Concept \| Best for \| Structure \|
242	\|----------\|---------\|----------\|-----------\|
243	\| A — Story-Driven \| Personal experience as the thread, emotional resonance first \| Reviews, personal shares, transformation \| Hook → Problem → Discovery → Experience → Conclusion \|
244	\| B — Information-Dense \| Value-first, efficient information delivery \| Tutorials, comparisons, checklists \| Core conclusion → Info card → Pros/Cons → Recommendation \|
245	\| C — Visual-First \| Visual impact as core, minimal text \| High-aesthetic products, lifestyle, mood content \| Hero image → Detail shots → Lifestyle scene → CTA \|
246
247	## Reference Images
248
249	User-supplied refs are separate from the internal "image-1 as anchor" chain (Step 3) — they layer on top of it.
250
251	Intake: via `--ref <files...>` or paths pasted in conversation.
252	- File path → copy to `refs/NN-ref-{slug}.{ext}`
253	- Pasted with no path → ask for the path, or extract style traits as a text fallback
254
255	Usage modes (per reference):
256
257	\| Usage \| Effect \|
258	\|-------\|--------\|
259	\| `direct` \| Pass the file to the backend (typically on image 1 only, so the anchor propagates through the chain) \|
260	\| `style` \| Extract style traits and append to every card's prompt body \|
261	\| `palette` \| Extract hex colors and append to every card's prompt body \|
262
263	Record refs in each affected card's prompt frontmatter:
264
265	```yaml
266	references:
267	- ref_id: 01
268	filename: 01-ref-brand.png
269	usage: direct
270	```
271
272	At generation time: verify files exist. Image 1 with `usage: direct` + backend that accepts refs → pass via the backend's ref parameter (becomes the chain anchor). Images 2+ keep using image-1 as `--ref` per Step 3 — do NOT re-stack user refs on top (avoids conflicting signals). For `style`/`palette`, embed extracted traits in every prompt.
273
274	## File Layout
275
276	```
277	image-cards/{topic-slug}/
278	├── source-{slug}.{ext}
279	├── analysis.md
280	├── outline-strategy-{a,b,c}.md # Path C only
281	├── outline.md
282	├── prompts/NN-{type}-{slug}.md
283	├── NN-{type}-{slug}.png
284	└── refs/ # only if --ref used
285	```
286
287	Slug: 2-4 words, kebab-case. "AI 工具推荐" → `ai-tools-recommend`. On collision, append `-YYYYMMDD-HHMMSS`.
288
289	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.
290
291	## Workflow
292
293	```
294	- [ ] Step 0: Load EXTEND.md ⛔ BLOCKING (interactive only)
295	- [ ] Step 1: Analyze content → analysis.md
296	- [ ] Step 2: Smart Confirm ⚠️ REQUIRED (Path A / B / C)
297	- [ ] Step 3: Generate images
298	- [ ] Step 4: Completion report
299	```
300
301	### Step 0: Load EXTEND.md ⛔ BLOCKING
302
303	Check these paths in order; first hit wins:
304
305	\| Path \| Scope \|
306	\|------\|-------\|
307	\| `.baoyu-skills/baoyu-xhs-images/EXTEND.md` \| Project \|
308	\| `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-xhs-images/EXTEND.md` \| XDG \|
309	\| `$HOME/.baoyu-skills/baoyu-xhs-images/EXTEND.md` \| User home \|
310
311	- Found → read, parse, print a summary (style / layout / watermark / language), continue.
312	- 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.
313	- 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.
314
315	EXTEND.md keys: watermark, preferred style/layout, custom style definitions, language preference, preferred image backend, generation batch size. Schema: `references/config/preferences-schema.md`.
316
317	### Step 1: Analyze Content → `analysis.md`
318
319	1. Save the source (backup rule applies if `source.md` exists).
320	2. Run the deep analysis in `references/workflows/analysis-framework.md`: content type, hook potential, audience, engagement signals, visual opportunity map, swipe flow.
321	3. Detect source language, pick recommended image count (2-10).
322	4. Auto-recommend strategy + style + layout + palette using the Auto-Selection table above.
323	5. Write everything to `analysis.md`.
324
325	### Step 2: Smart Confirm ⚠️ REQUIRED
326
327	Hard gate: this step is mandatory per the [Confirmation Policy](#confirmation-policy) — Step 3 cannot start until the user confirms here (or explicit

6 picks

Type

Run `npx skills use "https://github.com/jimliu/baoyu-skills" --skill "jimliu/baoyu-skills/baoyu-xhs-images"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the skills in "https://github.com/jimliu/baoyu-skills" that are relevant to the current task. Run `npx skills add "https://github.com/jimliu/baoyu-skills"` and select the relevant skills, then follow their instructions.

baoyu-xhs-images

How to install baoyu-xhs-images?

Related

baoyu-xhs-images

How to install baoyu-xhs-images?

Related