baoyu-infographic

Name: baoyu-infographic
Author: jimliu

byjimliu· 68 skills

Installs

30k

Stars

24k

Forks

2.7k

How to install baoyu-infographic?

jimliu/baoyu-skills/baoyu-infographic

$npx -y skills add jimliu/baoyu-skills --skill baoyu-infographic

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-infographic"` 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	# Infographic Generator
2
3	Two dimensions: layout (information structure) × style (visual aesthetics). Freely combine any layout with any style.
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 labels, headings, callouts, data values, or any other text inside an already generated infographic. If text is wrong or unclear, regenerate from a corrected prompt, switch to a layout with less on-image 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 backend receives the prompt file (or its content); 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	## Reference Images
41
42	Users may supply reference images to guide style, palette, composition, or subject.
43
44	Intake: Accept via `--ref <files...>` or when the user provides file paths / pastes images in conversation.
45	- File path(s) → copy to `refs/NN-ref-{slug}.{ext}` alongside the output
46	- Pasted image with no path → ask the user for the path (per the User Input Tools rule above), or extract style traits verbally as a text fallback
47	- No reference → skip this section
48
49	Usage modes (per reference):
50
51	\| Usage \| Effect \|
52	\|-------\|--------\|
53	\| `direct` \| Pass the file to the backend as a reference image \|
54	\| `style` \| Extract style traits (line treatment, texture, mood) and append to the prompt body \|
55	\| `palette` \| Extract hex colors from the image and append to the prompt body \|
56
57	Record in `prompts/infographic.md` frontmatter when refs exist:
58
59	```yaml
60	references:
61	- ref_id: 01
62	filename: 01-ref-brand.png
63	usage: direct
64	```
65
66	At generation time:
67	- Verify each referenced file exists on disk
68	- If `usage: direct` AND the chosen backend accepts reference images (e.g., `baoyu-image-gen` via `--ref`) → pass the file via the backend's ref parameter
69	- Otherwise → embed extracted `style`/`palette` traits in the prompt text
70
71	## Confirmation Policy
72
73	Default behavior: confirm before generation.
74
75	- Treat explicit skill invocation, a file path, a matched keyword shortcut, `EXTEND.md` defaults, and the documented default combination as recommendation inputs only. None of them authorizes skipping confirmation.
76	- Do not start Step 5 or Step 6 until the user confirms the combination/aspect/language/backend choices.
77	- Skip confirmation only when the current request explicitly says to do so, for example: `--no-confirm`, "直接生成", "不用确认", "跳过确认", "按默认出图", or equivalent wording.
78	- If confirmation is skipped explicitly, state the assumed combination/aspect/language/backend in the next user-facing update before generating.
79
80	## Options
81
82	\| Option \| Values \|
83	\|--------\|--------\|
84	\| `--layout` \| 21 options (see Layout Gallery), default: bento-grid \|
85	\| `--style` \| 22 options (see Style Gallery), default: craft-handmade \|
86	\| `--aspect` \| Named: landscape (16:9), portrait (9:16), square (1:1). Custom: any W:H ratio (e.g., 3:4, 4:3, 2.35:1) \|
87	\| `--lang` \| en, zh, ja, etc. \|
88	\| `--no-confirm` \| Skip Step 4 only when the user explicitly requests direct generation without confirmation \|
89	\| `--ref <files...>` \| Reference images (file paths) for style / palette / composition / subject guidance \|
90
91	## Layout Gallery (21)
92
93	\| Layout \| Best For \|
94	\|--------\|----------\|
95	\| `linear-progression` \| Timelines, processes, tutorials \|
96	\| `binary-comparison` \| A vs B, before-after, pros-cons \|
97	\| `comparison-matrix` \| Multi-factor comparisons \|
98	\| `hierarchical-layers` \| Pyramids, priority levels \|
99	\| `tree-branching` \| Categories, taxonomies \|
100	\| `hub-spoke` \| Central concept with related items \|
101	\| `structural-breakdown` \| Exploded views, cross-sections \|
102	\| `bento-grid` \| Multiple topics, overview (default) \|
103	\| `iceberg` \| Surface vs hidden aspects \|
104	\| `bridge` \| Problem-solution \|
105	\| `funnel` \| Conversion, filtering \|
106	\| `isometric-map` \| Spatial relationships \|
107	\| `dashboard` \| Metrics, KPIs \|
108	\| `periodic-table` \| Categorized collections \|
109	\| `comic-strip` \| Narratives, sequences \|
110	\| `story-mountain` \| Plot structure, tension arcs \|
111	\| `jigsaw` \| Interconnected parts \|
112	\| `venn-diagram` \| Overlapping concepts \|
113	\| `winding-roadmap` \| Journey, milestones \|
114	\| `circular-flow` \| Cycles, recurring processes \|
115	\| `dense-modules` \| High-density modules, data-rich guides \|
116
117	Full definitions live at `references/layouts/<layout>.md`.
118
119	## Style Gallery (22)
120
121	\| Style \| Description \|
122	\|-------\|-------------\|
123	\| `craft-handmade` \| Hand-drawn, paper craft (default) \|
124	\| `claymation` \| 3D clay figures, stop-motion \|
125	\| `kawaii` \| Japanese cute, pastels \|
126	\| `storybook-watercolor` \| Soft painted, whimsical \|
127	\| `chalkboard` \| Chalk on black board \|
128	\| `cyberpunk-neon` \| Neon glow, futuristic \|
129	\| `bold-graphic` \| Comic style, halftone \|
130	\| `aged-academia` \| Vintage science, sepia \|
131	\| `corporate-memphis` \| Flat vector, vibrant \|
132	\| `technical-schematic` \| Blueprint, engineering \|
133	\| `origami` \| Folded paper, geometric \|
134	\| `pixel-art` \| Retro 8-bit \|
135	\| `ui-wireframe` \| Grayscale interface mockup \|
136	\| `subway-map` \| Transit diagram \|
137	\| `ikea-manual` \| Minimal line art \|
138	\| `knolling` \| Organized flat-lay \|
139	\| `lego-brick` \| Toy brick construction \|
140	\| `pop-laboratory` \| Blueprint grid, coordinate markers, lab precision \|
141	\| `morandi-journal` \| Hand-drawn doodle, warm Morandi tones \|
142	\| `retro-pop-grid` \| 1970s retro pop art, Swiss grid, thick outlines \|
143	\| `hand-drawn-edu` \| Macaron pastels, hand-drawn wobble, stick figures \|
144	\| `retro-popup-pop` \| Retro popup collage, vintage UI, thick outlines, flat pop colors \|
145
146	Full definitions live at `references/styles/<style>.md`.
147
148	## Recommended Combinations
149
150	\| Content Type \| Layout + Style \|
151	\|--------------\|----------------\|
152	\| Timeline/History \| `linear-progression` + `craft-handmade` \|
153	\| Step-by-step \| `linear-progression` + `ikea-manual` \|
154	\| A vs B \| `binary-comparison` + `corporate-memphis` \|
155	\| Hierarchy \| `hierarchical-layers` + `craft-handmade` \|
156	\| Overlap \| `venn-diagram` + `craft-handmade` \|
157	\| Conversion \| `funnel` + `corporate-memphis` \|
158	\| Cycles \| `circular-flow` + `craft-handmade` \|
159	\| Technical \| `structural-breakdown` + `technical-schematic` \|
160	\| Metrics \| `dashboard` + `corporate-memphis` \|
161	\| Educational \| `bento-grid` + `chalkboard` \|
162	\| Journey \| `winding-roadmap` + `storybook-watercolor` \|
163	\| Categories \| `periodic-table` + `bold-graphic` \|
164	\| Product Guide \| `dense-modules` + `morandi-journal` \|
165	\| Technical Guide \| `dense-modules` + `pop-laboratory` \|
166	\| Trendy Guide \| `dense-modules` + `retro-pop-grid` \|
167	\| Retro Pop Guide \| `dense-modules` + `retro-popup-pop` \|
168	\| Educational Diagram \| `hub-spoke` + `hand-drawn-edu` \|
169	\| Process Tutorial \| `linear-progression` + `hand-drawn-edu` \|
170
171	Default combination: `bento-grid` + `craft-handmade` (fallback recommendation only — per the [Confirmation Policy](#confirmation-policy), defaults never bypass Step 4).
172
173	## Keyword Shortcuts
174
175	When the user's input contains these keywords, use the mapped layout as the leading Step 3 recommendation and promote the listed styles to the top of the Step 3 list. Skip content-based layout inference for matched keywords. Append any `Prompt Notes` to the Step 5 prompt.
176
177	\| User Keyword \| Layout \| Recommended Styles \| Default Aspect \| Prompt Notes \|
178	\|--------------\|--------\|--------------------\|----------------\|--------------\|
179	\| 高密度信息大图 / high-density-info \| `dense-modules` \| `morandi-journal`, `pop-laboratory`, `retro-pop-grid`, `retro-popup-pop` \| portrait \| — \|
180	\| 信息图 / infographic \| `bento-grid` \| `craft-handmade` \| landscape \| Minimalist: clean canvas, ample whitespace, no complex background textures. Simple cartoon elements and icons only. \|
181
182	## Output Structure
183
184	```
185	infographic/{topic-slug}/
186	├── source-{slug}.{ext}
187	├── analysis.md
188	├── structured-content.md
189	├── prompts/infographic.md
190	└── infographic.png
191	```
192
193	Slug: 2-4 words kebab-case from topic. Conflict: append `-YYYYMMDD-HHMMSS`.
194
195	## Core Principles
196
197	- Preserve source data faithfully—no summarization or rephrasing (but strip any credentials, API keys, tokens, or secrets before including in outputs)
198	- Define learning objectives before structuring content
199	- Structure for visual communication (headlines, labels, visual elements)
200
201	## Workflow
202
203	### Step 1: Setup & Analyze
204
205	1.1 Load Preferences (EXTEND.md)
206
207	Check EXTEND.md in priority order — the first one found wins:
208
209	\| Priority \| Path \| Scope \|
210	\|----------\|------\|-------\|
211	\| 1 \| `.baoyu-skills/baoyu-infographic/EXTEND.md` \| Project \|
212	\| 2 \| `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-infographic/EXTEND.md` \| XDG \|
213	\| 3 \| `$HOME/.baoyu-skills/baoyu-infographic/EXTEND.md` \| User home \|
214
215	\| Result \| Action \|
216	\|--------\|--------\|
217	\| Found \| Read, parse, display a one-line summary \|
218	\| Not found \| Ask the user with `AskUserQuestion` (see `references/config/first-time-setup.md`) \|
219
220	EXTEND.md supports: preferred layout/style, default aspect ratio, language preference, preferred image backend, custom style definitions.
221
222	Schema: `references/config/preferences-schema.md`
223
224	1.2 Analyze Content → `analysis.md`
225
226	1. Save source content (file path or paste → `source.md`)
227	- Backup rule: If `source.md` exists, rename to `source-backup-YYYYMMDD-HHMMSS.md`
228	2. Analyze: topic, data type, complexity, tone, audience
229	3. Detect source language and user language
230	4. Extract design instructions from user input
231	5. Save analysis
232	- Backup rule: If `analysis.md` exists, rename to `analysis-backup-YYYYMMDD-HHMMSS.md`
233
234	See `references/analysis-framework.md` for detailed format.
235
236	### Step 2: Generate Structured Content → `structured-content.md`
237
238	Transform content into infographic structure:
239	1. Title and learning objectives
240	2. Sections with: key concept, content (verbatim), visual element, text labels
241	3. Data points (all statistics/quotes copied exactly)
242	4. Design instructions from user
243
244	Rules: Markdown only. No new information. Preserve data faithfully. Strip any credentials or secrets from output.
245
246	See `references/structured-content-template.md` for detailed format.
247
248	### Step 3: Recommend Combinations
249
250	3.1 Check Keyword Shortcuts first: If user input matches a keyword from the Keyword Shortcuts table, use the associated layout as the leading recommendation and prioritize associated styles as top recommendations. Skip content-based layout inference.
251
252	3.2 Otherwise, recommend 3-5 layout×style combinations based on:
253	- Data structure → matching layout
254	- Content tone → matching style
255	- Audience expectations
256	- User design instructions
257
258	### Step 4: Confirm Options
259
260	Hard gate: this step is mandatory per the [Confirmation Policy](#confirmation-policy) — Steps 5–6 cannot start until the user confirms here (or explicitly opts out with `--no-confirm` / equivalent in the current request).
261
262	Ask the user to confirm the questions below following the [User Input Tools](#user-input-tools) rule at the top of this file (batch into one call if the runtime supports multiple questions; otherwise ask one at a time in priority order).
263
264	\| Priority \| Question \| When \| Options \|
265	\|----------\|----------\|------\|---------\|
266	\| 1 \| Combination \| Always \| 3+ layout×style combos with rationale \|
267	\| 2 \| Aspect \| Always \| Named presets (landscape/portrait/square) or custom W:H ratio (e.g., 3:4, 4:3, 2.35:1) \|
268	\| 3 \| Language \| Only if source ≠ user language \| Language for text content \|
269	\| 4 \| Image Backend \| Only if step 3 of the `## Image Generation Tools` rule needs to ask (no runtime-native tool AND multiple non-native backends, OR `preferred_image_backend: ask`) \| Available backends \|
270
271	### Step 5: Generate Prompt → `prompts/infographic.md`
272
273	Backup rule: If `prompts/infographic.md` exists, rename to `prompts/infographic-backup-YYYYMMDD-HHMMSS.md`
274
275	Combine:
276	1. Layout definition from `references/layouts/<layout>.md`
277	2. Style definition from `references/styles/<style>.md`
278	3. Base template from `references/base-prompt.md`
279	4. Structured content from Step 2
280	5. All text in confirmed language
281
282	Aspect ratio resolution for `{{ASPECT_RATIO}}`:
283	- Named presets → ratio string: landscape→`16:9`, portrait→`9:16`, square→`1:1`
284	- Custom W:H ratios → use as-is (e.g., `3:4`, `4:3`, `2.35:1`)
285
286	### Step 6: Generate Image
287
288	1. Resolve the backend per the `## Image Generation Tools` rule at the top of this file.
289	2. Ensure the full final prompt is persisted at `prompts/infographic.md` (already written in Step 5) BEFORE invoking the backend — the file is the reproducibility record.
290	3. Check for existing file: Before generating, check if `infographic.png` exists
291	- If exists: Rename to `infographic-backup-YYYYMMDD-HHMMSS.png`
292	4. Call the chosen backend with the prompt file and output path.
293	- `codex-imagegen` invocation: when the rule resolves to `codex-imagegen`, see [references/codex-imagegen.md](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).
294	5. On failure, auto-retry once
295
296	Text correction policy:
297
298	- If labels, headings, callouts, data values, or any other rendered text is misspelled, garbled, hard to read, or visually weak, do not patch the bitmap with code.
299	- For text-correction regenerations, write a new prompt file and a new output path so the flawed candidate is preserved for comparison.
300	- Post-processing is limited to crop, resize, compression, or format conversion that does not alter text or the main composition.
301
302	### Step 7: Output Summary
303
304	Report: topic, layout, style, aspect, language, image backend, output path, files created.
305
306	## References
307
308	- `references/analysis-framework.md` - Analysis methodology
309	- `references/structured-content-template.md` - Content format
310	- `references/base-prompt.md` - Prompt template
311	- `references/layouts/<layout>.md` - 21 layout definitions
312	- `references/styles/<style>.md` - 21 style definitions
313
314	## Changing Preferences
315
316	EXTEND.md lives at the first matching path in Step 1.1. Three ways to change it:
317
318	- Edit directly — open EXTEND.md and change fields. Full schema: `references/config/preferences-schema.md`.
319	- Reconfigure interactively — delete EXTEND.md (or ask "reconfigure baoyu-infographic preferences" / "重新配置"). The next run re-triggers first-time setup.
320	- Common one-line edits:
321	- `preferred_image_backend: auto` — default; runtime-native tool wins, falls back to the only installed backend, asks only if multiple non-native are present.
322	- `preferred_image_backend: codex-imagegen` — pin to Codex's built-in.
323	- `preferred_image_backend: baoyu-image-gen` — pin to the baoyu-image-gen skill.
324	- `preferred_image_backend: ask` — confirm backend every run.
325	- `preferred_layout: dense-modules`, `preferred_style: morandi-journal`, `preferred_aspect: portrait`, `language: zh` — shift the Step-3 recommendations and Step-4 defaults (per [Confirmation Policy](#confirmation-policy), these never bypass Step 4).

6 picks

Type

Run `npx skills use "https://github.com/jimliu/baoyu-skills" --skill "jimliu/baoyu-skills/baoyu-infographic"` 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-infographic

How to install baoyu-infographic?

Related

baoyu-infographic

How to install baoyu-infographic?

Related