Replace search skill with mem-search (#91)

* 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>

src/services/sqlite/SessionStore.ts

@@ -934,14 +934,37 @@ export class SessionStore {
 
   /**
    * Create a new SDK session (idempotent - returns existing session ID if already exists)
-   * Sets both claude_session_id and sdk_session_id to the same value
+   *
+   * CRITICAL ARCHITECTURE: Session ID Threading
+   * ============================================
+   * This function is the KEY to how claude-mem stays unified across hooks:
+   *
+   * - NEW hook calls: createSDKSession(session_id, project, prompt)
+   * - SAVE hook calls: createSDKSession(session_id, '', '')
+   * - Both use the SAME session_id from Claude Code's hook context
+   *
+   * IDEMPOTENT BEHAVIOR (INSERT OR IGNORE):
+   * - Prompt #1: session_id not in database → INSERT creates new row
+   * - Prompt #2+: session_id exists → INSERT ignored, fetch existing ID
+   * - Result: Same database ID returned for all prompts in conversation
+   *
+   * WHY THIS MATTERS:
+   * - NO "does session exist?" checks needed anywhere
+   * - NO risk of creating duplicate sessions
+   * - ALL hooks automatically connected via session_id
+   * - SAVE hook observations go to correct session (same session_id)
+   * - SDKAgent continuation prompt has correct context (same session_id)
+   *
+   * This is KISS in action: Trust the database UNIQUE constraint and
+   * INSERT OR IGNORE to handle both creation and lookup elegantly.
    */
   createSDKSession(claudeSessionId: string, project: string, userPrompt: string): number {
     const now = new Date();
     const nowEpoch = now.getTime();
 
-    // Try to insert - will be ignored if session already exists
-    // claude_session_id and sdk_session_id are the same value
+    // CRITICAL: INSERT OR IGNORE makes this idempotent
+    // First call (prompt #1): Creates new row
+    // Subsequent calls (prompt #2+): Ignored, returns existing ID
     const stmt = this.db.prepare(`
       INSERT OR IGNORE INTO sdk_sessions
       (claude_session_id, sdk_session_id, project, user_prompt, started_at, started_at_epoch, status)