visual-architect

Name: visual-architect
Author: proyecto26

13installs2forks

How to install visual-architect?

proyecto26/sherlock-ai-plugin/visual-architect

$npx -y skills add proyecto26/sherlock-ai-plugin --skill visual-architect

Installs into the current project.

Summary

Transform research papers into professional visual schemas. Analyzes paper logic, selects optimal layout patterns, and generates detailed prompts for AI image generation.

Files · 1

View on GitHub

SKILL.md

1	# Paper Visualizer Skill
2
3	Top-tier Scientific Visual Architect. Transforms text into geometric, structural visual instructions.
4
5	## 1. What This Skill Does
6	Takes research paper content (Methodology/Abstract) and produces a Structured Visual Schema—a high-precision prompt optimized for DALL-E 3, Midjourney v6, or Stable Diffusion.
7
8	## 2. Execution Logic (The Brain)
9
10	### Phase 1: Layout Pattern Recognition
11	You must analyze the text and enforce one of these strictly:
12	1. Linear Pipeline: Left→Right flow (Data Processing, Encoding-Decoding).
13	2. Cyclic/Iterative: Center loop (Optimization, RL, Feedback Loops).
14	3. Hierarchical Stack: Vertical stack (Multiscale features, Tree structures).
15	4. Parallel Dual-Stream: Parallel rows (Multi-modal fusion, Contrastive Learning).
16	5. Central Hub: Core connecting peripherals (Agent-Environment).
17	6. Matrix Grid: Comparison studies or ablation components.
18
19	### Phase 2: Schema Generation Rules
20	- Dynamic Zoning: Define 2-5 physical zones based on layout.
21	- Internal Visualization: Use concrete objects (Icons, Grids, Stacks), NOT abstract concepts.
22	- Explicit Connections: Describe physics of flow (e.g., "Curved arrow looping back").
23
24	## 3. Output Format (The Golden Schema)
25
26	You MUST respond strictly using this Markdown template. Use the examples in brackets `[...]` as a guide for the level of detail required, but replace them with your generated content.
27
28	```markdown
29	---BEGIN PROMPT---
30
31	[Style & Meta-Instructions]
32	High-fidelity scientific schematic, technical vector illustration, clean white background, distinct boundaries, academic textbook style. High resolution 4k, strictly 2D flat design with subtle isometric elements.
33
34	[TEXT RENDERING RULES]
35	* Typography: Use bold, sans-serif font (e.g., Helvetica/Roboto style) for maximum legibility.
36	* Hierarchy: Prioritize correct spelling for MAIN HEADERS (Zone Titles). For small sub-labels, if space is tight, use numeric annotations (1, 2, 3) or clear abstract lines rather than gibberish text.
37	* Contrast: Text must be dark grey/black on light backgrounds. Avoid overlapping text on complex textures.
38
39	[LAYOUT CONFIGURATION]
40	* Selected Layout: [e.g., Cyclic Iterative Process with 3 Nodes]
41	* Composition Logic: [e.g., A central triangular feedback loop surrounded by input/output panels]
42	* Color Palette: [e.g., Professional Pastel (Azure Blue, Slate Grey, Coral Orange, Mint Green)]
43
44	[ZONE 1: LOCATION - LABEL]
45	* Container: [Shape description, e.g., Top-Left Rectangular Panel]
46	* Visual Structure: [Concrete objects, e.g., A stack of 3 layered documents with binary code patterns]
47	* Key Text Labels: "[Text 1]"
48
49	[ZONE 2: LOCATION - LABEL]
50	* Container: [Shape description, e.g., Central Circular Engine]
51	* Visual Structure: [Concrete objects, e.g., A clockwise loop connecting 3 internal modules: A (Gear), B (Graph), C (Filter)]
52	* Key Text Labels: "[Text 2]", "[Text 3]"
53
54	[ZONE 3: LOCATION - LABEL]
55	... (Add Zone 4 or 5 if necessary based on the selected layout)
56
57	[CONNECTIONS]
58	1. [Connection description, e.g., A curved dotted arrow looping from Zone 2 back to Zone 1 labeled "Feedback"]
59	2. [Connection description, e.g., A wide flow arrow branching from Zone 2 to Zone 3]
60
61	---END PROMPT---
62
63	```
64
65	## 4. Usage Guide for User
66
67	Input: Upload your paper PDF and say:
68	> "Generate a visual schema for this paper's methodology section"
69
70	Pro Tips for Best Results:
71	* Text Correction: AI image generators often misspell complex scientific terms. Use the generated image as a base layer, then overlay correct text in PowerPoint/Canva/Illustrator.
72	* Simplification: If the diagram is too cluttered, tell the skill: "Simplify Zone 2 to show only high-level blocks."
73
74	Advanced Constraints:
75
76	* Add `--svg` to request a Mermaid/SVG code block representation (Experimental).
77	* Add `--style "poster"` for simplified, bold layouts.
78
79	## 5. Technical Limitations
80
81	* SVG output is an approximation; prioritize the Text Schema for Image Generation models.
82	* Best results come from inputting specific "Methodology" sections rather than full PDFs.

People who liked this also viewed

6 picks

Type

web-design-guidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".SkillsJul 2026483k29k
lark-slides飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 SkillsJul 2026332k16k
design-taste-frontendTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop SkillsJul 2026280k66k
ui-ux-pro-maxUI/UX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presSkillsJul 2026280k109k
caveman-helpQuick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".SkillsJul 2026249k92k
codebase-designShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-nSkillsJul 2026225k182k

visual-architect

13installs2forks

View on GitHub

How to install visual-architect?

proyecto26/sherlock-ai-plugin/visual-architect

$npx -y skills add proyecto26/sherlock-ai-plugin --skill visual-architect

Installs into the current project.

Summary

Transform research papers into professional visual schemas. Analyzes paper logic, selects optimal layout patterns, and generates detailed prompts for AI image generation.

Files · 1

View on GitHub

SKILL.md

1	# Paper Visualizer Skill
2
3	Top-tier Scientific Visual Architect. Transforms text into geometric, structural visual instructions.
4
5	## 1. What This Skill Does
6	Takes research paper content (Methodology/Abstract) and produces a Structured Visual Schema—a high-precision prompt optimized for DALL-E 3, Midjourney v6, or Stable Diffusion.
7
8	## 2. Execution Logic (The Brain)
9
10	### Phase 1: Layout Pattern Recognition
11	You must analyze the text and enforce one of these strictly:
12	1. Linear Pipeline: Left→Right flow (Data Processing, Encoding-Decoding).
13	2. Cyclic/Iterative: Center loop (Optimization, RL, Feedback Loops).
14	3. Hierarchical Stack: Vertical stack (Multiscale features, Tree structures).
15	4. Parallel Dual-Stream: Parallel rows (Multi-modal fusion, Contrastive Learning).
16	5. Central Hub: Core connecting peripherals (Agent-Environment).
17	6. Matrix Grid: Comparison studies or ablation components.
18
19	### Phase 2: Schema Generation Rules
20	- Dynamic Zoning: Define 2-5 physical zones based on layout.
21	- Internal Visualization: Use concrete objects (Icons, Grids, Stacks), NOT abstract concepts.
22	- Explicit Connections: Describe physics of flow (e.g., "Curved arrow looping back").
23
24	## 3. Output Format (The Golden Schema)
25
26	You MUST respond strictly using this Markdown template. Use the examples in brackets `[...]` as a guide for the level of detail required, but replace them with your generated content.
27
28	```markdown
29	---BEGIN PROMPT---
30
31	[Style & Meta-Instructions]
32	High-fidelity scientific schematic, technical vector illustration, clean white background, distinct boundaries, academic textbook style. High resolution 4k, strictly 2D flat design with subtle isometric elements.
33
34	[TEXT RENDERING RULES]
35	* Typography: Use bold, sans-serif font (e.g., Helvetica/Roboto style) for maximum legibility.
36	* Hierarchy: Prioritize correct spelling for MAIN HEADERS (Zone Titles). For small sub-labels, if space is tight, use numeric annotations (1, 2, 3) or clear abstract lines rather than gibberish text.
37	* Contrast: Text must be dark grey/black on light backgrounds. Avoid overlapping text on complex textures.
38
39	[LAYOUT CONFIGURATION]
40	* Selected Layout: [e.g., Cyclic Iterative Process with 3 Nodes]
41	* Composition Logic: [e.g., A central triangular feedback loop surrounded by input/output panels]
42	* Color Palette: [e.g., Professional Pastel (Azure Blue, Slate Grey, Coral Orange, Mint Green)]
43
44	[ZONE 1: LOCATION - LABEL]
45	* Container: [Shape description, e.g., Top-Left Rectangular Panel]
46	* Visual Structure: [Concrete objects, e.g., A stack of 3 layered documents with binary code patterns]
47	* Key Text Labels: "[Text 1]"
48
49	[ZONE 2: LOCATION - LABEL]
50	* Container: [Shape description, e.g., Central Circular Engine]
51	* Visual Structure: [Concrete objects, e.g., A clockwise loop connecting 3 internal modules: A (Gear), B (Graph), C (Filter)]
52	* Key Text Labels: "[Text 2]", "[Text 3]"
53
54	[ZONE 3: LOCATION - LABEL]
55	... (Add Zone 4 or 5 if necessary based on the selected layout)
56
57	[CONNECTIONS]
58	1. [Connection description, e.g., A curved dotted arrow looping from Zone 2 back to Zone 1 labeled "Feedback"]
59	2. [Connection description, e.g., A wide flow arrow branching from Zone 2 to Zone 3]
60
61	---END PROMPT---
62
63	```
64
65	## 4. Usage Guide for User
66
67	Input: Upload your paper PDF and say:
68	> "Generate a visual schema for this paper's methodology section"
69
70	Pro Tips for Best Results:
71	* Text Correction: AI image generators often misspell complex scientific terms. Use the generated image as a base layer, then overlay correct text in PowerPoint/Canva/Illustrator.
72	* Simplification: If the diagram is too cluttered, tell the skill: "Simplify Zone 2 to show only high-level blocks."
73
74	Advanced Constraints:
75
76	* Add `--svg` to request a Mermaid/SVG code block representation (Experimental).
77	* Add `--style "poster"` for simplified, bold layouts.
78
79	## 5. Technical Limitations
80
81	* SVG output is an approximation; prioritize the Text Schema for Image Generation models.
82	* Best results come from inputting specific "Methodology" sections rather than full PDFs.

People who liked this also viewed

6 picks

Type