.claude/skills/screenshot-analyze/SKILL.md
--- context: fork --- # /screenshot-analyze Perform comprehensive analysis of screenshots using Sonnet sub-agents for detailed visual inspection. ## Usage ``` /screenshot-analyze <image-path> /screenshot-analyze +Attachments/error-screenshot.png /screenshot-analyze +Attachments/ui-mockup.png --context "login flow" ``` ## Instructions This skill uses **Sonnet model sub-agents** for thorough image analysis with vision capabilities. ### Phase 1: Image Loading 1. Verify the image exists at t
npx skillsauth add DavidROliverBA/ArchitectKB .claude/skills/screenshot-analyzeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Perform comprehensive analysis of screenshots using Sonnet sub-agents for detailed visual inspection.
/screenshot-analyze <image-path>
/screenshot-analyze +Attachments/error-screenshot.png
/screenshot-analyze +Attachments/ui-mockup.png --context "login flow"
This skill uses Sonnet model sub-agents for thorough image analysis with vision capabilities.
Launch these sub-agents using model: "sonnet":
Agent 1: Content Extraction (Sonnet)
Task: Extract all visible content from the image
- Read the image file using the Read tool
- Extract all visible text (OCR)
- Identify UI elements, buttons, labels
- Note any error messages or notifications
- Capture data values, IDs, or codes visible
Return: Complete text extraction with location context
Agent 2: Visual Structure Analysis (Sonnet)
Task: Analyse the visual structure and layout
- Read the image file
- Identify the type of content (UI, diagram, document, error, etc.)
- Map the visual hierarchy and layout
- Note colour schemes, branding elements
- Identify interactive elements
- Assess visual quality and clarity
Return: Structural analysis with element inventory
Agent 3: Context & Purpose Analysis (Sonnet)
Task: Understand the purpose and context
- Read the image file
- Determine what application/system is shown
- Identify the workflow or process stage
- Note any problems or issues visible
- Assess what action might be needed
- Connect to known YourOrg systems if recognisable
Return: Contextual interpretation with system identification
# Screenshot Analysis
**Image**: {{filename}}
**Analysed**: {{DATE}}
**Type**: {{UI/Error/Diagram/Document/Other}}
## Summary
{{2-3 sentence overview of what the image shows}}
## Extracted Content
### Text Found
{{all readable text, organised by location}}
### UI Elements
| Element | Type | Label/Text | State |
|---------|------|------------|-------|
{{element inventory}}
### Data Values
{{any IDs, codes, numbers, or data visible}}
## Visual Analysis
### Layout Structure
{{description of visual hierarchy}}
### Application/System
- **Identified as**: {{system name if known}}
- **Screen/Page**: {{specific view or page}}
- **Context**: {{workflow stage}}
## Observations
### Key Findings
{{important observations}}
### Issues Detected
{{any errors, warnings, or problems visible}}
### Recommendations
{{suggested actions based on analysis}}
## Related Notes
{{suggest links to related vault notes if system is recognised}}
tools
--- context: fork --- # /youtube Save a YouTube video as both a Weblink (quick reference) and a detailed Page (full analysis). ## Usage ``` /youtube <url> /youtube <url> <optional title override> ``` ## Examples ``` /youtube https://www.youtube.com/watch?v=0TpON5T-Sw4 /youtube https://youtu.be/abc123 AWS re:Invent Keynote ``` ## Prerequisites This skill uses the MCP Docker YouTube tools: - `mcp__MCP_DOCKER__get_video_info` - Video metadata - `mcp__MCP_DOCKER__get_transcript` - Full trans
data-ai
Create and manage git worktrees for parallel agent sessions
testing
--- context: fork --- # /wipe Generate a context handoff summary, clear the session, and resume in a fresh conversation. Detects environment and provides automated (tmux) or manual workflow. ## Usage ``` /wipe /wipe quick # Minimal handoff, just essentials /wipe detailed # Comprehensive handoff with full context ``` ## Instructions When the user invokes `/wipe`: ### Phase 1: Detect Environment First, check the terminal environment: ```bash echo "Environment Detection:"
data-ai
--- context: fork --- # /weekly-summary Generate comprehensive weekly summary from daily notes, meetings, tasks, and project updates using parallel sub-agents. ## Usage ``` /weekly-summary /weekly-summary --last-week /weekly-summary --from 2026-01-01 --to 2026-01-07 /weekly-summary --output page # Create Page note instead of just outputting ``` ## Instructions This skill uses **5 parallel sub-agents** to gather data concurrently from different vault areas, then synthesizes a comprehensi