claude_memory 0.13.0 → 0.13.2

data/.claude/skills/check-memory/SKILL.md

@@ -1,87 +0,0 @@
----
-name: check-memory
-description: Explicitly check memory system before answering or exploring
-disable-model-invocation: true
----
-
-# Check Memory First
-
-When invoked with `/check-memory <topic>`, this skill forces a memory-first workflow.
-
-## Task
-
-**IMPORTANT: You MUST check memory BEFORE reading any files or running any code searches.**
-
-The user is asking about: $ARGUMENTS
-
-## Step-by-Step Workflow
-
-### 0. Verify Memory Health
-
-Before querying, confirm the memory system is operational:
-
-```
-memory.check_setup
-```
-
-If status is not "healthy", inform the user and suggest running `claude-memory doctor` for details.
-
-### 1. Query Memory (REQUIRED FIRST STEP)
-
-Run multiple memory queries to find existing knowledge:
-
-```
-memory.recall "$ARGUMENTS"
-```
-
-Also try specialized shortcuts:
-- `memory.decisions` (if implementing a feature)
-- `memory.architecture` (if working with frameworks)
-- `memory.conventions` (if writing code)
-- `memory.conflicts` (if encountering contradictions)
-
-### 2. Analyze Results
-
-Review what memory returns:
-- **If sufficient**: Answer using recalled facts with citations
-- **If partial**: Note what's known and what needs investigation
-- **If empty**: Memory has no knowledge on this topic yet
-
-### 3. Explore Code (ONLY IF NEEDED)
-
-If memory doesn't have enough information:
-- Use Read/Grep/Glob to explore the codebase
-- Clearly distinguish between:
-  - **Recalled knowledge** (from memory)
-  - **Discovered information** (from code exploration)
-
-### 4. Provide Complete Answer
-
-Combine:
-- Facts from memory (with fact IDs if relevant)
-- New information from code exploration (if any)
-- Clear indication of sources
-
-## Example Response Format
-
-```
-Based on memory:
-- [Fact from memory with context]
-
-From code exploration:
-- [New findings from reading files]
-
-Answer: [Complete response combining both sources]
-```
-
-## Why This Matters
-
-Memory contains distilled knowledge from previous sessions. Checking it first:
-- Saves time (no need to re-explore known areas)
-- Provides context (decisions, patterns, conventions)
-- Avoids mistakes (previous lessons learned)
-- Reduces token usage (recalled facts are concise)
-
-## Remember
-
-**ALWAYS start with memory queries. NEVER skip this step.**

data/.claude/skills/dashboard/SKILL.md

@@ -1,42 +0,0 @@
----
-name: dashboard
-description: Launch a local web dashboard for ClaudeMemory debugging and observability
----
-
-# Dashboard
-
-Launch the ClaudeMemory debugging dashboard to visualize memory system health, activity, and efficacy.
-
-## Task
-
-Start the dashboard web server so the user can inspect what's happening behind the scenes.
-
-## Steps
-
-1. Run the dashboard command:
-
-```bash
-claude-memory dashboard
-```
-
-This starts a local web server (default port 3377) and opens it in the browser.
-
-## What the Dashboard Shows
-
-- **Health Status**: Database health, hook configuration, vector index status
-- **Overview**: Fact/entity/content counts, top predicates, entity type distribution, 30-day activity timeline
-- **Activity**: Live event log of hook executions (ingest, context, sweep), memory recalls, and store extractions with timing and details
-- **Facts**: Searchable fact explorer with status filtering, predicate/object search
-- **Efficacy**: Recall hit rate, total results served, average results per query, top queries by result count
-
-## Options
-
-- `--port PORT` - Use a different port (default: 3377)
-- `--no-open` - Don't auto-open the browser
-
-## Notes
-
-- Dashboard auto-refreshes every 30 seconds
-- Activity events are recorded by hooks and MCP tools into the `activity_events` table
-- The dashboard reads from both global and project databases
-- Press Ctrl+C to stop the server

data/.claude/skills/debug-memory

@@ -1 +0,0 @@
-../../skills/debug-memory