obsidian-connection-detector
Detect and classify relationships between vault notes. Use when a new note is created, or to scan for connections across the corpus. Triggers: "find connections", "what relates to X", or auto-called by other skills after note creation.
64
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Obsidian Connection Detector
Detects and classifies relationships between Obsidian vault notes using AI-powered analysis.
What it does
- Takes a note path (or scans recent notes)
- Extracts key claims/theses from the note
- Searches the vault for related notes (by tags, keywords, concepts)
- Classifies each relationship as: supports, contradicts, extends, or bridges
- Writes connection entries to a tracker file (
Research/connections.json) - Optionally adds a
## Connectionssection to the source note with classified links - Updates relevant topic MOCs with podcast↔library connections (adds a
### 🎙️ Related Podcast Episodessubsection)
Usage
# Detect connections for a specific note
python scripts/detect.py --note "Research/Library/01.../some-note.md"
# Detect connections for a podcast note
python scripts/detect.py --note "Podcasts/The a16z Podcast/2026-08-04 - Episode Title.md"
# Scan the 5 most recently modified notes (Library + Podcasts, balanced)
python scripts/detect.py --scan-recent 5
# Full corpus scan (expensive — calls xAI API for every candidate pair)
python scripts/detect.py --scan-all
# Backfill existing podcast connections into topic MOCs (no API calls)
python scripts/detect.py --update-mocsConfiguration
- Vault path:
C:\Users\nuno_\Documents\Obsidian Vault - xAI API key: loaded from env var
XAI_API_KEYor~/.config/last30days/.env - Model:
grok-4.5 - Output:
Research/connections.jsoninside the vault
Integration
This skill feeds data into obsidian-thesis-tracker, which clusters connections into emerging theses and can auto-generate reports.
Step N: Reflection (composable)
Invoke the skill-reflection skill with the following context:
- Calling skill:
obsidian-connection-detector - SKILL.md path:
.github/skills/obsidian-connection-detector/SKILL.md - Steps completed: list each step with pass/fail/skipped
- Friction notes: any workarounds, retries, unexpected errors, or manual interventions
The reflection skill will analyze the run and produce improvement recommendations.
- Repository
0xRabbidfly/Eric-Cartman
- Revision
dccd2a1
- Last updated
- First committed
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.