prompt-xray
Analyzes prompts to uncover the secrets behind design layouts, color palettes, and visuals.
Install
mkdir -p .claude/skills/prompt-xray && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3160" && unzip -o skill.zip -d .claude/skills/prompt-xray && rm skill.zipInstalls to .claude/skills/prompt-xray
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
提示词X光透视 - 从优秀提示词中逆向提取"如何做X"的知识，让黑盒变透明Key capabilities
- →Extract color theory knowledge from prompts
- →Analyze layout generation logic
- →Deconstruct complex design prompts
- →Synthesize design knowledge from multiple agents
How it works
The system utilizes a multi-agent architecture where specialized agents like the color analyzer and layout architect dissect prompt components to reverse-engineer design knowledge.
Inputs & outputs
When to use prompt-xray
- →Extracting color theory from a prompt
- →Analyzing how a layout was generated
- →Deconstructing complex design prompts
About this skill
Prompt Xray - 提示词X光透视系统
状态: 🚧 开发中 版本: 1.0 灵感: BerryXia Multi-Agent Architecture
快速开始
# 从项目根目录运行
python -m claude.skills.prompt_xray.xray_controller
目录结构
prompt-xray/
├── skill.md # Skill说明文档
├── xray_controller.py # 主控制器
├── agents/ # 8个分析Agent
│ ├── color_analyzer.py
│ ├── layout_architect.py
│ └── ...
└── utils/ # 工具函数
已实现功能
- COLOR_ANALYZER - 配色知识提取
- LAYOUT_ARCHITECT - 布局知识提取
- SYMBOL_EXTRACTOR - 符号添加方法
- TYPOGRAPHY_ANALYST - 排版知识
- MATERIAL_ENGINEER - 材质知识
- LIGHT_PHYSICIST - 光影知识
- KNOWLEDGE_SYNTHESIZER - 知识聚合
When not to use it
- →Analyzing typography
- →Extracting material properties
- →Processing light and shadow physics
Prerequisites
Limitations
- →Symbol extraction is not yet implemented
- →Typography analysis is currently unavailable
- →Material and light physics analysis are not functional
How it compares
Unlike manual prompt analysis, this system automates the decomposition of prompts into structured design logic using specific domain-focused agents.
Compared to similar skills
prompt-xray side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| prompt-xray (this skill) | 1 | 7mo | Review | Intermediate |
| pdf-processing | 37 | 9mo | Review | Intermediate |
| whisper | 11 | 7mo | Review | Beginner |
| office-docs | 1 | 6mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by huangserva
View all by huangserva →You might also like
pdf-processing
Ming-Kai-LC
Comprehensive PDF processing techniques for handling large files that exceed Claude Code's reading limits, including chunking strategies, text/table extraction, and OCR for scanned documents. Use when working with PDFs larger than 10-15MB or more than 30-50 pages.
whisper
davila7
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
office-docs
Xxiii8322766509
Extract text and tables from .docx and .xlsx using local scripts (no external deps).
pdf-processor
lofcz
Extracts text and tables from PDF files, fills forms, and merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
calc
Anhvu1107
ALWAYS use this when the request matches Calc: Spreadsheet creation, format conversion (ODS/XLSX/CSV), formulas, data automation with LibreOffice Calc.
training-check
GRIND-Lab-Core
Monitors running spatial experiments. Checks output files, log files, and process status. Categorizes results as OK, STALLED, FAILED, or COMPLETE. Fires alerts by appending to output/PROJ_NOTES.md. Run every 15 minutes during Stage 3 of research-pipeline.