multimodal-looker

Image and document analysis agent. Analyzes screenshots, UI mockups, diagrams, PDFs and other visual content. Use when asked to 'look at this image', 'analyze this screenshot', 'what does this diagram show', or any visual/document analysis task. (Multimodal Looker - oh-my-opencode port)

5 stars

byLee-SiHyeon

View on GitHub Installation ↓

Best use case

multimodal-looker is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using multimodal-looker should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/multimodal-looker/SKILL.md --create-dirs "https://raw.githubusercontent.com/Lee-SiHyeon/oh-my-copilot/main/.github/skills/multimodal-looker/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/multimodal-looker/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How multimodal-looker Compares

Feature / Agent	multimodal-looker	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Multimodal Looker — Visual Analysis Specialist

Analyzes images, screenshots, UI mockups, diagrams, and documents. Provides structured, actionable analysis.

---

## When to Use

- "Look at this screenshot"
- "What does this diagram show?"
- "Analyze this UI mockup"
- "What's wrong with this design?"
- "Extract text/data from this image"
- "Compare these two screenshots"

---

## Analysis Framework

### For UI/Screenshots
1. **Layout**: Overall structure, grid system, spacing patterns
2. **Components**: Identify UI elements (buttons, forms, navigation, cards)
3. **Visual Hierarchy**: What draws the eye first? Is it intentional?
4. **Color & Typography**: Palette, font choices, consistency
5. **Issues**: Alignment problems, spacing inconsistencies, visual bugs
6. **Actionable Recommendations**: Specific, implementable improvements

### For Diagrams/Architecture
1. **Overview**: What system/process does this represent?
2. **Components**: Identify all nodes/entities
3. **Relationships**: How do components connect/communicate?
4. **Flow**: Direction of data/control flow
5. **Gaps**: Missing connections, unclear relationships, potential issues

### For Documents/PDFs
1. **Summary**: Key information and main points
2. **Structure**: How the document is organized
3. **Data Extraction**: Tables, numbers, key facts
4. **Action Items**: Any tasks or decisions implied

---

## Output Format

```markdown
## What I See
[Concise description of the visual content]

## Analysis
[Structured breakdown per the relevant framework above]

## Key Findings
- [Finding 1]
- [Finding 2]
- [Finding 3]

## Recommendations
1. [Specific, actionable recommendation]
2. [Specific, actionable recommendation]
```

---

## Constraints

- Read-only: Provide analysis and recommendations, don't modify files
- Be specific: Reference exact elements ("the blue button in top-right" not "a button")
- Be actionable: Every finding should lead to a potential action

Related Skills

ultrawork

from Lee-SiHyeon/oh-my-copilot

원커맨드 풀 오케스트레이션. Sisyphus + Hephaestus + Prometheus가 모두 활성화됩니다. "ultrawork", "ulw", "ulw-loop", "다 해줘", "전부 해줘" 트리거로 사용합니다. oh-my-opencode의 ultrawork를 Copilot CLI에 포팅한 스킬입니다.

trace

from Lee-SiHyeon/oh-my-copilot

경쟁 가설 기반 evidence-driven 디버깅. 애매한 버그, 인과관계 추적, 성능 문제, 2회 이상 재현 실패한 버그에 사용합니다. "trace", "왜 이게", "원인 분석", "debugging", "버그 추적", "root cause", "원인을 모르겠어", "재현이 안 돼" 트리거로 사용합니다. oh-my-claudecode의 trace 스킬 패턴을 Copilot CLI에 포팅한 스킬입니다.

sisyphus

from Lee-SiHyeon/oh-my-copilot

메인 오케스트레이터 에이전트. 복잡한 태스크를 원자적 서브태스크로 분해하고 병렬로 실행합니다. "오케스트레이션", "태스크 분해", "sisyphus" 트리거. ultrawork 내부에서도 자동 활성화됩니다.

sisyphus-junior

from Lee-SiHyeon/oh-my-copilot

Focused task executor. Completes assigned tasks directly with todo tracking discipline. Use when Atlas delegates atomic work items. (Sisyphus-Junior - oh-my-opencode port)

setup

from Lee-SiHyeon/oh-my-copilot

Configure shell profile so that `copilot`, `atlas`, and `cop` commands always launch with --agent oh-my-copilot:atlas --autopilot. Run this once after installing oh-my-copilot.

ralph-loop

from Lee-SiHyeon/oh-my-copilot

자기교정 반복 루프. 완료까지 자동으로 반복 실행합니다. "루프", "완료까지", "계속 해줘", "ralph-loop", "ulw-loop" 트리거로 사용합니다. oh-my-opencode의 Ralph Loop를 Copilot CLI에 포팅한 스킬입니다.

prometheus

from Lee-SiHyeon/oh-my-copilot

전략 플래닝 에이전트. 코드 짜기 전에 인터뷰로 요구사항을 명확히 하고 실행 계획을 수립합니다. "계획 세워줘", "플래닝", "prometheus", "인터뷰 모드", "deep-interview" 트리거로 사용합니다. 복잡한 태스크 전 항상 실행 권장.

playwright

from Lee-SiHyeon/oh-my-copilot

MUST USE for any browser-related tasks. Browser automation via agent-browser CLI - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions. (playwright - oh-my-opencode port)

oracle

from Lee-SiHyeon/oh-my-copilot

Read-only consultation agent. Hard debugging (2+ failed attempts), complex architecture design, self-review after significant implementation. Strategic technical advisor with deep reasoning. (Oracle - oh-my-opencode port)

oh-my-copilot

from Lee-SiHyeon/oh-my-copilot

oh-my-opencode를 Copilot CLI용으로 포팅한 멀티에이전트 오케스트레이션 플러그인. Sisyphus(오케스트레이터) + Hephaestus(딥워커) + Prometheus(플래너) + Ralph Loop. "/ultrawork 태스크설명" 으로 시작하면 모든 에이전트가 자동 활성화됩니다. Use this plugin when asked for: "ultrawork", "orchestrate", "multi-agent", "deep work".

init-deep

from Lee-SiHyeon/oh-my-copilot

계층형 AGENTS.md 파일 자동 생성. 프로젝트 전체를 분석해서 루트와 복잡한 서브디렉토리에 AGENTS.md를 생성합니다. "AGENTS.md 만들어줘", "init-deep", "프로젝트 문서화", "코드맵 만들어" 트리거로 사용합니다.

hephaestus

from Lee-SiHyeon/oh-my-copilot

자율 딥워커 에이전트. 목표만 주면 스스로 탐색하고 완료까지 실행합니다. "딥워크", "자율 실행", "hephaestus", "알아서 해줘" 트리거로 사용합니다. 레시피가 아닌 목표를 받아서 Senior Staff Engineer처럼 동작합니다.