.claude/skills/broken-links/SKILL.md
--- context: fork --- # /broken-links Scan the vault for broken [[wiki-links]] and suggest fixes using parallel Sonnet sub-agents. ## Usage ``` /broken-links /broken-links --auto-fix # Interactive fixes with suggestions ``` ## Instructions This skill uses **3 parallel Sonnet sub-agents** to scan different vault areas concurrently for maximum performance. ### Phase 1: Launch Parallel Link Scanners Create **3 Task agents** running in parallel with `model: "sonnet"`: **Agent 1: Root Dir
npx skillsauth add DavidROliverBA/ArchitectKB .claude/skills/broken-linksInstall 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.
Scan the vault for broken [[wiki-links]] and suggest fixes using parallel Sonnet sub-agents.
/broken-links
/broken-links --auto-fix # Interactive fixes with suggestions
This skill uses 3 parallel Sonnet sub-agents to scan different vault areas concurrently for maximum performance.
Create 3 Task agents running in parallel with model: "sonnet":
Agent 1: Root Directory Scanner (Sonnet)
Task: Scan root directory for broken wiki-links
- Use Glob to find all *.md files in root (exclude +Daily, +Meetings, +Templates)
- For each file, use Read tool to get content
- Extract all [[wiki-links]] using regex: \[\[([^\]|]+)(\|[^\]]+)?\]\]
- Also check frontmatter fields for wiki-links
- Build list of all referenced note names
- Compare against existing files using Glob
- Return: List of broken links with source files
Format:
{
"source": "filename.md",
"brokenLinks": ["Missing Note 1", "Missing Note 2"],
"line": "content snippet with [[broken link]]"
}
Agent 2: Meetings Directory Scanner (Sonnet)
Task: Scan +Meetings/ directory for broken wiki-links
- Use Glob to find all *.md files in +Meetings/
- For each file, extract [[wiki-links]] from content and frontmatter
- Check attendees, project links, and inline person references
- Identify missing Person, Project, and Organisation notes
- Return: List of broken links in meeting notes
Agent 3: Daily Notes Scanner (Sonnet)
Task: Scan +Daily/ directory for broken wiki-links
- Use Glob to find all *.md files in +Daily/
- Extract [[wiki-links]] from daily notes
- Check task references, project links, person mentions
- Identify temporal references that may be broken
- Return: List of broken links in daily notes
After all 3 agents complete:
Merge Results
Categorize by Severity
Fuzzy Match Suggestions
# Broken Wiki-Links Report
Generated: {{DATE}}
Total Broken Links: {{count}}
## Critical ({{critical_count}})
### [[Missing Note Name]] (referenced {{count}} times)
**Referenced in:**
- [[Source Note 1]] (line 42): "Context snippet with [[Missing Note Name]]"
- [[Source Note 2]] (line 15): "Another context [[Missing Note Name]]"
**Suggestions:**
- Did you mean [[Similar Note]]? (85% match)
- Did you mean [[Another Match]]? (72% match)
**Actions:**
- [ ] Create the note [[Missing Note Name]]
- [ ] Replace with [[Similar Note]] in all references
- [ ] Remove the broken links
---
## Warnings ({{warning_count}})
{{same format}}
## Info ({{info_count}})
{{same format}}
## Summary
| Severity | Count | % of Total |
|----------|-------|------------|
| Critical | {{n}} | {{%}} |
| Warning | {{n}} | {{%}} |
| Info | {{n}} | {{%}} |
## Next Steps
1. **Create Missing Critical Notes**: {{list top 5}}
2. **Fix Case Mismatches**: {{list}}
3. **Review and Clean Up Info-level**: {{list}}
If --auto-fix flag is provided:
Case Mismatch Fixes (automatic)
Fuzzy Match Replacements (prompt user)
Bulk Deletions (prompt user)
Vault Cleanup:
Link Hygiene:
Refactoring Support:
Quality Assurance:
[[Note Name]] and [[Note Name|Display Text]] formats[[Note#Heading]] → checks Note existstools
--- 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