From obsidian-memory
Use this skill for efficient Obsidian vault navigation and search. Covers which MCP tools to use, search strategies, batch operations, and how to leverage frontmatter summaries for quick triage.
How this skill is triggered — by the user, by Claude, or both
Slash command
/obsidian-memory:search-navigationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Efficient strategies for finding and accessing information in the Obsidian vault.
Efficient strategies for finding and accessing information in the Obsidian vault.
| Need | Tool | Why |
|---|---|---|
| Read one file | read_note | Direct access |
| Read multiple files | read_multiple_notes | Batch (max 10) |
| Check file exists/metadata | get_notes_info | No content load |
| Get just frontmatter | get_frontmatter | See summary without content |
| Search by content | search_notes with searchContent: true | Full-text search |
| Search by metadata | search_notes with searchFrontmatter: true | Find by type/status/tags |
| Browse structure | list_directory | See folder contents |
| Find all tags | manage_tags with operation: list | See note's tags |
| Vault overview | get_vault_stats | Size, recent files |
get_frontmatter - Fast Metadata CheckUse when: You need to understand what a file is about without reading content
Returns: Just the YAML frontmatter (type, status, summary, tags)
Perfect for: Triaging multiple files quickly
get_notes_info - Batch MetadataUse when: Checking multiple files at once (up to array of paths)
Returns: Path, size, modified date, hasFrontmatter flag
Perfect for: Quick scan of a folder's contents
search_notes - Find ContentParameters:
- query: Search text
- searchContent: true (default) - search in note body
- searchFrontmatter: true - search in YAML frontmatter
- limit: Max results (default 5, max 20)
- caseSensitive: false (default)
Use searchFrontmatter for:
- Finding notes by type: "type: decision"
- Finding by status: "status: active"
- Finding by summary keywords
read_multiple_notes - Batch ReadParameters:
- paths: Array of note paths (max 10)
- includeContent: true (default)
- includeFrontmatter: true (default)
Use when: You know which files you need and want to read them efficiently
When looking for notes on a topic:
Search frontmatter for summary keywords
search_notes(query: "authentication", searchFrontmatter: true, searchContent: false)
Get info on promising results
get_notes_info(paths: [results])
Read only the relevant ones
read_note(path: "the-one-I-need.md")
When you know the category:
List directory to see options
list_directory(path: "knowledge-base/aws-services")
Get frontmatter for files of interest
get_frontmatter(path: "knowledge-base/aws-services/lambda-patterns.md")
Read if summary matches need
When looking for cross-cutting concerns:
Search frontmatter for tag
search_notes(query: "#blocker", searchFrontmatter: true)
Or search content for inline tags
search_notes(query: "#decision", searchContent: true)
When looking for recent work:
Get vault stats with recent files
get_vault_stats(recentCount: 10)
Read recent files that look relevant
Before starting work on a client/project:
1. list_directory("engagements/active/[client]")
2. read_note("engagements/active/[client]/context.md")
3. If decisions folder exists: list_directory + get_frontmatter on ADRs
When making a technical choice:
1. search_notes(query: "[technology]", searchFrontmatter: true)
2. Filter results for type: decision
3. read_multiple_notes on relevant ADRs
When someone is mentioned:
1. list_directory("people")
2. Look for matching filename
3. read_note("people/[name].md")
When resuming previous work:
1. list_directory("agent-workspaces")
2. Find relevant session folder by date/context
3. read_note("agent-workspaces/[session]/context.md")
get_notes_info before reading full notes (check if worth reading)read_multiple_notes instead of multiple read_note callslimit parameter in search to avoid overwhelming resultshasFrontmatter in get_notes_info - files without it need full read| Path | Contains |
|---|---|
engagements/active/ | Current client work |
engagements/completed/ | Archived engagements |
knowledge-base/ | Reference material by technology |
playbooks/ | Reusable methodologies |
people/ | Information about individuals |
career/ | Brag doc, promotion materials |
agentic-platform-program/ | Tech lead domain work |
agent-workspaces/ | Session workspaces |
agent-workspaces/shared/ | Cross-session persistent notes |
| Looking for... | Search approach |
|---|---|
| Active blockers | search_notes("#blocker", searchFrontmatter: true) |
| Decisions on X | search_notes("type: decision", searchFrontmatter: true) + filter |
| Lessons learned | list_directory("knowledge-base/lessons-learned") |
| Person info | list_directory("people") + read_note |
| Recent session | get_vault_stats(recentCount: 5) |
obsidian-memory:memory-system skill for when/what to storeCLAUDE.md in vault root for vault-specific conventionsnpx claudepluginhub cajias/claude-skills --plugin obsidian-memoryGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.