97d565e3cd
* feat: add mem-search skill with progressive disclosure architecture Add comprehensive mem-search skill for accessing claude-mem's persistent cross-session memory database. Implements progressive disclosure workflow and token-efficient search patterns. Features: - 12 search operations (observations, sessions, prompts, by-type, by-concept, by-file, timelines, etc.) - Progressive disclosure principles to minimize token usage - Anti-patterns documentation to guide LLM behavior - HTTP API integration for all search functionality - Common workflows with composition examples Structure: - SKILL.md: Entry point with temporal trigger patterns - principles/: Progressive disclosure + anti-patterns - operations/: 12 search operation files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add CHANGELOG entry for mem-search skill Document mem-search skill addition in Unreleased section with: - 100% effectiveness compliance metrics - Comparison to previous search skill implementation - Progressive disclosure architecture details - Reference to audit report documentation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add mem-search skill audit report Add comprehensive audit report validating mem-search skill against Anthropic's official skill-creator documentation. Report includes: - Effectiveness metrics comparison (search vs mem-search) - Critical issues analysis for production readiness - Compliance validation across 6 key dimensions - Reference implementation guidance Result: mem-search achieves 100% compliance vs search's 67% 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: Add comprehensive search architecture analysis document - Document current state of dual search architectures (HTTP API and MCP) - Analyze HTTP endpoints and MCP search server architectures - Identify DRY violations across search implementations - Evaluate the use of curl as the optimal approach for search - Provide architectural recommendations for immediate and long-term improvements - Outline action plan for cleanup, feature parity, DRY refactoring * refactor: Remove deprecated search skill documentation and operations * refactor: Reorganize documentation into public and context directories Changes: - Created docs/public/ for Mintlify documentation (.mdx files) - Created docs/context/ for internal planning and implementation docs - Moved all .mdx files and assets to docs/public/ - Moved all internal .md files to docs/context/ - Added CLAUDE.md to both directories explaining their purpose - Updated docs.json paths to work with new structure Benefits: - Clear separation between user-facing and internal documentation - Easier to maintain Mintlify docs in dedicated directory - Internal context files organized separately 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * Enhance session management and continuity in hooks - Updated new-hook.ts to clarify session_id threading and idempotent session creation. - Modified prompts.ts to require claudeSessionId for continuation prompts, ensuring session context is maintained. - Improved SessionStore.ts documentation on createSDKSession to emphasize idempotent behavior and session connection. - Refined SDKAgent.ts to detail continuation prompt logic and its reliance on session.claudeSessionId for unified session handling. --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Alex Newman <thedotmack@gmail.com>
3.5 KiB
3.5 KiB
Search Sessions (Full-Text)
Search session summaries using natural language queries.
When to Use
- User asks: "What did we work on last week?"
- User asks: "What sessions involved database work?"
- User asks: "Show me sessions where we fixed bugs"
- Looking for past sessions by topic or theme
Command
curl -s "http://localhost:37777/api/search/sessions?query=authentication&format=index&limit=5"
Parameters
- query (required): Search terms (e.g., "authentication", "database migration", "bug fixes")
- format: "index" (summary) or "full" (complete details). Default: "full"
- limit: Number of results (default: 20, max: 100)
- project: Filter by project name (optional)
- dateRange: Filter by date range (optional)
When to Use Each Format
Use format=index for:
- Quick overviews of past sessions
- Finding session IDs for deeper investigation
- Listing multiple sessions
- Token cost: ~50-100 per result
Use format=full for:
- Complete session summaries with requests, completions, learnings
- Understanding the full context of a session
- Token cost: ~500-1000 per result
Example Response (format=index)
{
"query": "authentication",
"count": 3,
"format": "index",
"results": [
{
"id": 545,
"session_id": "S545",
"title": "Implemented JWT authentication system",
"subtitle": "Added token-based auth with refresh tokens",
"created_at_epoch": 1699564800000,
"project": "api-server"
}
]
}
How to Present Results
For format=index, present as a compact list:
Found 3 sessions about "authentication":
🎯 **Session #545** Implemented JWT authentication system
> Added token-based auth with refresh tokens
> Nov 9, 2024 • api-server
🎯 **Session #546** Fixed authentication token expiration
> Resolved race condition in token refresh flow
> Nov 8, 2024 • api-server
For complete formatting guidelines, see formatting.md.
Session Summary Structure
Full session summaries include:
- Session request: What the user asked for
- What was completed: Summary of work done
- Key learnings: Important insights and discoveries
- Files modified: List of changed files
- Observations: Links to detailed observations
Error Handling
Missing query parameter:
{"error": "Missing required parameter: query"}
Fix: Add the query parameter
No results found:
{"query": "foobar", "count": 0, "results": []}
Response: "No sessions found for 'foobar'. Try different search terms."
Tips
- Be specific: "JWT authentication implementation" > "auth"
- Start with format=index and limit=5-10
- Use dateRange for recent sessions:
?query=auth&dateRange[start]=2024-11-01 - Sessions provide high-level overview, observations provide details
- Use project filtering when working on one codebase
Token Efficiency:
- Start with format=index (~50-100 tokens per result)
- Use format=full only for relevant items (~500-1000 tokens per result)
- See ../principles/progressive-disclosure.md
When to Use Sessions vs Observations
Use sessions search when:
- Looking for high-level work summaries
- Understanding what was done in past sessions
- Getting overview of recent activity
Use observations search when:
- Looking for specific implementation details
- Finding bugs, features, or decisions
- Need fine-grained context about code changes