.claude/skills/attachment-audit/SKILL.md
--- context: fork --- # /attachment-audit Audit all images and attachments in the vault using Sonnet sub-agents for comprehensive visual analysis. ## Usage ``` /attachment-audit /attachment-audit --type images /attachment-audit --unused /attachment-audit --folder +Attachments/2025 ``` ## Instructions This skill uses **Sonnet model sub-agents** for thorough analysis of vault attachments. ### Phase 1: Inventory 1. Scan `+Attachments/` folder for all files 2. Categorise by type (images, PDF
npx skillsauth add DavidROliverBA/ArchitectKB .claude/skills/attachment-auditInstall 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.
Audit all images and attachments in the vault using Sonnet sub-agents for comprehensive visual analysis.
/attachment-audit
/attachment-audit --type images
/attachment-audit --unused
/attachment-audit --folder +Attachments/2025
This skill uses Sonnet model sub-agents for thorough analysis of vault attachments.
+Attachments/ folder for all filesLaunch these sub-agents using model: "sonnet":
Agent 1: File Inventory (Sonnet)
Task: Build complete attachment inventory
- List all files in +Attachments/ recursively
- Categorise by file type
- Get file sizes and modification dates
- Identify naming patterns
- Note any duplicates or similar names
Return: Complete file inventory with metadata
Agent 2: Usage Analysis (Sonnet)
Task: Analyse attachment usage across vault
- Search all markdown files for attachment references
- Map each attachment to notes that reference it
- Identify orphan attachments (not referenced anywhere)
- Find broken references (links to non-existent files)
- Note most frequently used attachments
Return: Usage map with orphan and broken link lists
Agent 3: Image Content Analysis (Sonnet)
Task: Analyse image contents for documentation
- For each image, read and analyse visually
- Categorise: screenshot, diagram, photo, document, other
- Identify what each image depicts
- Extract any visible text
- Note which images might need better filenames
- Identify potentially sensitive content
Return: Image content summary for each file
Agent 4: Organisation Recommendations (Sonnet)
Task: Recommend organisation improvements
- Assess current folder structure
- Identify files that should be renamed
- Suggest categorisation (by project, date, type)
- Find large files that could be compressed
- Recommend archival candidates
- Suggest metadata or tagging approach
Return: Organisation recommendations
# Attachment Audit Report
**Audit Date**: {{DATE}}
**Total Attachments**: {{count}}
**Total Size**: {{size}}
## Summary
{{Overview of attachment health and key findings}}
## Inventory
### By Type
| Type | Count | Size | % of Total |
|------|-------|------|------------|
| Images (PNG/JPG) | {{count}} | {{size}} | {{%}} |
| PDFs | {{count}} | {{size}} | {{%}} |
| Documents | {{count}} | {{size}} | {{%}} |
| Other | {{count}} | {{size}} | {{%}} |
### By Category (Content)
| Category | Count | Examples |
|----------|-------|----------|
| Screenshots | {{count}} | {{examples}} |
| Architecture Diagrams | {{count}} | {{examples}} |
| Process Flows | {{count}} | {{examples}} |
| Meeting Photos | {{count}} | {{examples}} |
| Documents/Scans | {{count}} | {{examples}} |
| Other | {{count}} | {{examples}} |
## Usage Analysis
### Well-Referenced (3+ links)
{{list of frequently used attachments}}
### Single Reference
{{attachments only used once}}
### Orphan Attachments (No References)
| File | Type | Size | Recommendation |
|------|------|------|----------------|
{{orphan files with suggested actions}}
### Broken References
| Note | Broken Link | Suggestion |
|------|-------------|------------|
{{notes with broken attachment links}}
## Content Summary
### Screenshots
{{summary of screenshot contents}}
### Diagrams
{{summary of diagram contents}}
### Documents
{{summary of document contents}}
## Issues Found
### Naming Issues
{{files with unclear or inconsistent names}}
### Large Files
{{files over 1MB that could be optimised}}
### Potential Duplicates
{{files that appear to be duplicates}}
### Sensitive Content
{{files that may contain sensitive information}}
## Recommendations
### Immediate Actions
1. {{high priority recommendation}}
2. {{high priority recommendation}}
### Rename Suggestions
| Current Name | Suggested Name | Reason |
|--------------|----------------|--------|
{{rename recommendations}}
### Archive Candidates
{{old or unused files that could be archived}}
### Folder Structure
{{suggested folder organisation}}
## Quick Fixes
To remove orphan attachments:
```bash
{{commands to clean up orphans}}
To fix broken links: {{suggested edits}}
### Modes
**--type images**: Only analyse image files
**--unused**: Focus on orphan/unused attachments
**--folder <path>**: Limit to specific subfolder
### Notes
- Full audit can take several minutes for large vaults
- Image analysis provides content descriptions for better organisation
- Useful for vault maintenance and cleanup
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