psycho-baller/obsidian-search
skills/obsidian-search/SKILL.md
Find and retrieve notes from Rami's Obsidian vault by topic or theme using semantic search against Smart Connections embeddings. Use when asked to find notes about a specific subject, retrieve relevant vault content, or surface what Rami has written about a topic.
testing
Updated May 21, 2026
$ install --global
skillsauthnpx skillsauth add psycho-baller/skills obsidian-searchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 21, 2026, 5:38 AM57.3s2 files scanned
SKILL.md
- name:
- obsidian-search
- version:
- 1.0.0
- description:
- Find and retrieve notes from Rami's Obsidian vault by topic or theme using semantic search against Smart Connections embeddings. Use when asked to find notes about a specific subject, retrieve relevant vault content, or surface what Rami has written about a topic.
Obsidian Vault Search
You help Rami find relevant notes in his Obsidian vault using semantic search. This is NOT the same as letterly-automation (which imports notes) — this skill is purely for finding existing notes by topic.
Vault location
/Users/rami/Library/Mobile Documents/iCloud~md~obsidian/Documents/Obsidian
Also accessible via symlink at: /Users/rami/Documents/life-os/Obsidian
Use the symlink path when working inside the life-os repo.
Smart Connections embeddings
The vault uses the Smart Connections Obsidian plugin. Embeddings live in:
<vault>/.smart-env/multi/
Each .ajson file corresponds to one note. The filename is the note path with /, , and . replaced by _, then .ajson appended.
Example: My Notes/Foo bar.md → My_Notes_Foo_bar_md.ajson
The shared utility for reading these is at:
/Users/rami/Documents/life-os/ai-agents-config/skills/utils/smart_connections.py
Key functions:
get_vault_root()— finds the vault by looking for.smart-env/load_note_embeddings()— loads all note-level vectorsload_block_embeddings()— loads all heading-level vectors
Search approach
Option A — Semantic search via Smart Connections (preferred when embeddings are available)
Run a semantic search using the existing utility:
cd /Users/rami/Documents/life-os
.venv/bin/python ai-agents-config/skills/obsidian-similar-notes/scripts/find_similar.py \
--query "TOPIC HERE" \
--mode note \
--threshold 0.4 \
--top 10
If the venv isn't set up, fall back to Option B.
Option B — Keyword search with grep (fallback)
grep -r -l --include="*.md" -i "KEYWORD" "/Users/rami/Library/Mobile Documents/iCloud~md~obsidian/Documents/Obsidian" 2>/dev/null | head -20
Then read the top matches.
Option C — Direct folder browsing
If the user specifies a folder (e.g., "check my Essays folder"), use Glob to list files in that subtree, then read the most relevant ones.
After finding matches
- List the matching notes with their path and a 1-sentence summary of what each is about.
- Ask the user which ones they want to read in full, or read the top 3 automatically if they asked you to "fetch" or "retrieve" them.
- If the user wants to build on the content (write an article, brainstorm, etc.), read the full note text and present it clearly before proceeding.
Key vault structure (for context)
unprocessed/— inbox, newly imported notes not yet organizedMy Outputs/Transcriptions/— processed voice memos and video transcriptsMy Outputs/My Essays/— published or draft essaysMy Resources/— Maps of Content (MOCs) only, no raw notesHidden/— personal/private notes (gitignored, may have access)
Notes on the embeddings model
Model: TaylorAI/bge-micro-v2 (384-dim vectors)
Similarity threshold for "related": 0.45 (use 0.4 for broader search)
Block-level search uses heading chains: path#H1#H2
Related Skills
psycho-baller/task-framing
tools
VerifiedTrustedCommunity
Pre-task clarity ritual for Rami. Surfaces real intention, maps work to his pillars, and produces a Session Brief. Use when Rami is about to start a task or plan a work session.
SKILL.mdUpdated May 21, 2026
psycho-baller/update-patterns
testing
VerifiedTrustedCommunity
Update living Obsidian pattern files from metadata-enriched transcriptions. Use when asked to populate or update pattern files for communication flaws, beliefs, fears, principles, or people/projects mentioned.
SKILL.mdUpdated May 2, 2026
psycho-baller/generate-principles
testing
VerifiedTrustedCommunity
Generate evidence-backed personal principles from markdown notes, reflections, and transcripts. Use when extracting life principles, decision rules, or lessons from journal entries and reflections.
SKILL.mdUpdated May 2, 2026
psycho-baller/generate-metadata
testing
VerifiedTrustedCommunity
Generate and validate frontmatter metadata for markdown transcriptions and voice notes. Use when processing raw transcriptions, enriching Letterly notes, or preparing notes before moving them to final outputs.
SKILL.mdUpdated May 2, 2026