superlocalmemory 3.6.13 → 3.6.15

package/skills/slm-show-patterns/SKILL.md

@@ -1,224 +0,0 @@
----
-name: slm-show-patterns
-description: Show what SuperLocalMemory has learned about your preferences, workflow patterns, and project context. Use when the user asks "what have you learned about me?" or wants to see their coding identity patterns. Shows tech preferences, workflow sequences, and engagement health.
-version: "2.7.0"
-license: AGPL-3.0-or-later
-compatibility: "Requires SuperLocalMemory V2.7+ with learning features"
-attribution:
-  creator: Varun Pratap Bhardwaj
-  role: Solution Architect & Original Creator
-  project: SuperLocalMemory V2
----
-
-# SuperLocalMemory: Show Patterns
-
-Show what SuperLocalMemory has learned about your preferences, workflow, and coding identity.
-
-## Usage
-
-```bash
-slm patterns list [threshold]
-slm learning status
-slm engagement
-```
-
-## Example Output
-
-### Learned Patterns
-```bash
-$ slm patterns list 0.5
-```
-
-**Output:**
-```
-Learned Patterns (confidence >= 0.5)
-=====================================
-
-TECH PREFERENCES (cross-project):
-  #1  preferred_framework: React        confidence: 0.92  (seen in 3 profiles)
-  #2  preferred_language: Python         confidence: 0.88  (seen in 2 profiles)
-  #3  preferred_backend: FastAPI         confidence: 0.85  (seen in 2 profiles)
-  #4  testing_style: pytest              confidence: 0.78  (seen in 1 profile)
-  #5  preferred_db: PostgreSQL           confidence: 0.71  (seen in 2 profiles)
-
-WORKFLOW PATTERNS:
-  #6  morning_sequence: recall -> code -> remember    frequency: 34
-  #7  debug_sequence: recall -> recall -> remember    frequency: 18
-  #8  review_sequence: list -> recall -> remember     frequency: 12
-
-PROJECT CONTEXT:
-  #9  active_project: SuperLocalMemoryV2    last_seen: 2 hours ago
-  #10 active_project: client-dashboard      last_seen: 1 day ago
-
-Total: 10 patterns (7 high confidence)
-```
-
-### Learning Status
-```bash
-$ slm learning status
-```
-
-**Output:**
-```
-SuperLocalMemory v2.7 -- Learning System Status
-==================================================
-LightGBM:  installed (4.5.0)
-SciPy:     installed (1.14.1)
-ML Ranking:  available
-Full Learning: available
-
-Feedback signals: 247
-Unique queries:   89
-Patterns learned: 34 (12 high confidence)
-Workflow patterns: 8
-Sources tracked:  4
-Models trained:   2
-Learning DB size: 128 KB
-```
-
-### Engagement Metrics
-```bash
-$ slm engagement
-```
-
-**Output:**
-```
-SuperLocalMemory -- Engagement Health
-======================================
-Status: HEALTHY
-
-This Week:
-  Memories saved:    12
-  Recalls performed: 28
-  Memories marked useful: 8
-  Feedback ratio:    28.6%
-
-Trends:
-  Recall frequency:  increasing (up 15% from last week)
-  Save frequency:    stable
-  Useful feedback:   increasing (up 40% from last week)
-
-Streaks:
-  Current daily streak: 5 days
-  Longest streak:       14 days
-```
-
-## What the Patterns Mean
-
-### Tech Preferences
-Cross-project patterns that transfer between profiles. These represent your coding identity -- which frameworks, languages, and tools you consistently choose.
-
-**How they are learned:**
-- Extracted from memory content (mentions of frameworks, tools)
-- Weighted by recency and frequency
-- Confidence increases when the same preference appears across multiple profiles
-
-**How they help:**
-- When you `recall`, results matching your preferred stack rank higher
-- Your AI tools can reference these to tailor suggestions
-
-### Workflow Patterns
-Sequences of actions you repeat. The system learns your work rhythm.
-
-**Examples:**
-- `recall -> code -> remember` = "Research, build, document" workflow
-- `recall -> recall -> remember` = "Deep investigation" workflow
-
-**How they help:**
-- System predicts what you will need next
-- Can pre-load relevant context based on your current workflow stage
-
-### Engagement Health
-Overall system usage metrics (fully local, zero telemetry).
-
-**Healthy indicators:**
-- Regular daily usage (streaks)
-- Balanced save/recall ratio
-- Increasing useful feedback
-
-**Warning signs:**
-- No recalls for 7+ days = stale memories
-- No saves for 7+ days = not capturing knowledge
-- Zero feedback = system cannot learn your preferences
-
-## Correcting Patterns
-
-If the system learned something wrong, correct it:
-
-```bash
-# See all patterns
-slm patterns list
-
-# Correct pattern #3 from "FastAPI" to "Django"
-slm patterns correct 3 Django
-```
-
-The correction increases confidence to 1.0 and records the change history.
-
-## Options
-
-| Command | Description | Use Case |
-|---------|-------------|----------|
-| `slm patterns list` | All patterns (no threshold) | See everything learned |
-| `slm patterns list 0.7` | High confidence only | See reliable patterns |
-| `slm patterns correct <id> <value>` | Fix a wrong pattern | Override incorrect learning |
-| `slm learning status` | System health | Check deps and stats |
-| `slm learning retrain` | Force model retrain | After bulk feedback |
-| `slm learning reset` | Delete all learning data | Fresh start (memories preserved) |
-| `slm engagement` | Usage metrics | Track your engagement health |
-
-## Use Cases
-
-### 1. "What Have You Learned About Me?"
-```bash
-slm patterns list
-# Shows all preferences, workflows, and project context
-```
-
-### 2. Pre-Session Context Loading
-```bash
-slm patterns context
-# Returns structured context for AI tools to consume
-```
-
-### 3. Onboarding a New AI Tool
-```bash
-slm learning status
-# Verify learning is active, then use your existing memories
-# New tool benefits from all previously learned patterns
-```
-
-### 4. Weekly Review
-```bash
-slm engagement
-# Check if you are using your memory system effectively
-```
-
-## Requirements
-
-- SuperLocalMemory V2.7+
-- Optional: `lightgbm` and `scipy` for ML-powered ranking
-- Works without optional deps (uses rule-based ranking as fallback)
-
-## Notes
-
-- **Privacy:** All learning is local. Zero telemetry, zero cloud calls.
-- **Separate storage:** Learning data lives in `learning.db`, separate from `memory.db`.
-- **Non-destructive:** `slm learning reset` only deletes learning data, never memories.
-- **Graceful degradation:** If learning deps are missing, core features work normally.
-
-## Related Commands
-
-- `slm recall` - Search memories (results ranked by learned patterns)
-- `slm useful <id>` - Mark memory as useful (feedback for learning)
-- `slm status` - Overall system status
-- `slm patterns update` - Re-learn patterns from existing memories
-
----
-
-**Created by:** [Varun Pratap Bhardwaj](https://github.com/varun369) (Solution Architect)
-**Project:** SuperLocalMemory V2
-**License:** MIT (see [LICENSE](../../LICENSE))
-**Repository:** https://github.com/varun369/SuperLocalMemoryV2
-
-*Open source doesn't mean removing credit. Attribution must be preserved per MIT License terms.*

package/skills/slm-status/SKILL.md

@@ -1,363 +0,0 @@
----
-name: slm-status
-description: Check SuperLocalMemory system status, health, and statistics. Use when the user wants to know memory count, graph stats, patterns learned, database health, or system diagnostics. Shows comprehensive system health dashboard.
-version: "3.4.23"
-license: AGPL-3.0-or-later
-compatibility: "Requires SuperLocalMemory V2 installed at ~/.claude-memory/"
-attribution:
-  creator: Varun Pratap Bhardwaj
-  role: Solution Architect & Original Creator
-  project: SuperLocalMemory V2
----
-
-# SuperLocalMemory: Status
-
-Check system status, health metrics, and statistics for your local memory system.
-
-## Usage
-
-```bash
-slm status [--verbose] [--check-integrity]
-```
-
-## Example Output
-
-### Basic Status
-```bash
-$ slm status
-```
-
-**Output:**
-```
-╔══════════════════════════════════════════════════════╗
-║  SuperLocalMemory V2 - System Status                ║
-╚══════════════════════════════════════════════════════╝
-
-📊 Memory Statistics
-   Total Memories:        1,247
-   This Month:            143
-   This Week:             28
-   Today:                 5
-
-📈 Knowledge Graph
-   Nodes (Entities):      892
-   Edges (Relationships): 3,456
-   Clusters:              47
-   Avg Cluster Size:      19 memories
-
-🎯 Pattern Learning
-   Coding Patterns:       34
-   Framework Preferences: React (72%), Vue (18%), Angular (10%)
-   Testing Style:         TDD (65%), BDD (35%)
-   Performance Priority:  High (78%)
-
-💾 Database Health
-   Size:                  4.2 MB
-   Integrity:             ✅ OK
-   Last Backup:           2026-02-07 09:15
-   Backup Count:          12
-
-🔧 Current Profile
-   Name:                  default
-   Created:               2026-01-15
-   Last Used:             2026-02-07 14:23
-
-⚙️  System Info
-   Install Path:          ~/.claude-memory
-   Database:              memory.db
-   Python Version:        3.11.7
-   SQLite Version:        3.43.2
-
-✅ Status: HEALTHY
-```
-
-### Verbose Mode
-```bash
-$ slm status --verbose
-```
-
-**Additional information:**
-- Recent memory IDs
-- Top entities in graph
-- Pattern confidence scores
-- Database table sizes
-- Index statistics
-
-### Integrity Check
-```bash
-$ slm status --check-integrity
-```
-
-**Runs full database integrity check:**
-```
-Running integrity check...
-
-Database Structure:       ✅ OK
-FTS5 Index:              ✅ OK
-Graph Consistency:        ✅ OK
-Orphaned Nodes:          0 found
-Duplicate Memories:      0 found
-Corrupted Entries:       0 found
-
-✅ All checks passed
-```
-
-## What This Shows
-
-### 1. Memory Statistics
-- **Total:** All memories ever saved
-- **This Month:** Memories added in current month
-- **This Week:** Last 7 days
-- **Today:** Memories added today
-
-**Useful for:**
-- Understanding usage patterns
-- Tracking growth
-- Identifying active periods
-
-### 2. Knowledge Graph
-- **Nodes:** Unique entities extracted (people, technologies, concepts)
-- **Edges:** Relationships between entities
-- **Clusters:** Auto-discovered topic groups
-- **Avg Cluster Size:** Memories per cluster
-
-**Health indicators:**
-- High edges/nodes ratio = well-connected knowledge
-- Many clusters = diverse topics
-- Large clusters = focused work
-
-### 3. Pattern Learning
-- **Coding Patterns:** Identified preferences and decisions
-- **Framework Preferences:** Usage distribution
-- **Testing Style:** TDD vs BDD preference
-- **Performance Priority:** How important performance is to you
-
-**Based on:**
-- Keywords in memories ("prefer", "use", "avoid")
-- Frequency of mentions
-- Importance levels
-- Recency (recent patterns weighted higher)
-
-### 4. Database Health
-- **Size:** Database file size
-- **Integrity:** PRAGMA integrity_check result
-- **Last Backup:** Most recent backup timestamp
-- **Backup Count:** Total backups available
-
-**Warning signs:**
-- ❌ Integrity: NOT OK → Database corrupted
-- ⚠️  Size > 100MB → Consider archiving old memories
-- ⚠️  No backups → Enable backup system
-
-### 5. Current Profile
-- **Name:** Active profile (default, work, personal, etc.)
-- **Created:** When profile was created
-- **Last Used:** Last access timestamp
-
-**Profiles allow:**
-- Profile isolation
-- Context switching
-- Separate memory spaces
-
-### 6. System Info
-- **Install Path:** Where SuperLocalMemory is installed
-- **Database:** Database filename
-- **Python Version:** Python interpreter version
-- **SQLite Version:** SQLite engine version
-
-## Options
-
-| Option | Description | Use Case |
-|--------|-------------|----------|
-| `--verbose` | Show detailed stats | Debugging, analysis |
-| `--check-integrity` | Run full DB check | Troubleshooting |
-| `--format json` | JSON output | Scripting |
-| `--format text` | Human-readable (default) | Terminal use |
-
-## Use Cases
-
-### 1. Health Check Before Important Work
-```bash
-slm status --check-integrity
-# Ensure DB is healthy before big import
-```
-
-### 2. Understanding Memory Usage
-```bash
-slm status
-# "Do I have enough memories for pattern learning?"
-# (Need 20+ for basic patterns, 50+ for advanced)
-```
-
-### 3. Performance Monitoring
-```bash
-slm status --verbose
-# Check graph stats, optimize if needed
-```
-
-### 4. Backup Verification
-```bash
-slm status | grep "Last Backup"
-# Ensure recent backup exists
-```
-
-### 5. Profile Switching Context
-```bash
-# Before switching
-slm status
-# Note: "Current Profile: work"
-
-slm switch-profile personal
-
-slm status
-# Note: "Current Profile: personal"
-```
-
-## Advanced Usage
-
-### Scripting & Automation
-
-**Daily health check (cron job):**
-```bash
-#!/bin/bash
-# Daily at 9 AM
-
-status=$(slm status --check-integrity)
-if echo "$status" | grep -q "NOT OK"; then
-  echo "SuperLocalMemory: Integrity check FAILED" | mail -s "Alert" you@example.com
-fi
-```
-
-**Monitoring script:**
-```bash
-#!/bin/bash
-# Monitor memory growth
-
-count=$(slm status | grep "Total Memories:" | awk '{print $3}' | tr -d ',')
-echo "$(date),${count}" >> memory-growth.csv
-```
-
-**JSON output for dashboards:**
-```bash
-slm status --format json > status.json
-# Parse with jq, send to monitoring system
-```
-
-### Performance Indicators
-
-**Good indicators:**
-- Graph nodes > 100 → Rich knowledge base
-- Edges/nodes ratio > 2 → Well-connected
-- Patterns learned > 10 → AI understands your style
-- Integrity: OK → Database healthy
-
-**Warning signs:**
-- Database size > 50MB but <100 memories → Possible issue
-- Backup count: 0 → No disaster recovery
-- Last used: >30 days ago → Stale data
-
-## Troubleshooting
-
-### "Status command hangs"
-**Cause:** Database locked by another process
-
-**Solution:**
-```bash
-# Check for locks
-lsof ~/.claude-memory/memory.db
-
-# Kill hanging processes
-killall python3
-
-# Try again
-slm status
-```
-
-### "Integrity check fails"
-**Cause:** Database corruption
-
-**Solution:**
-```bash
-# Restore from backup
-cp ~/.claude-memory/backups/memory.db.backup.* ~/.claude-memory/memory.db
-
-# Verify
-slm status --check-integrity
-```
-
-### "Pattern stats missing"
-**Cause:** Need more memories (minimum 20)
-
-**Solution:**
-```bash
-# Check memory count
-slm status | grep "Total Memories"
-
-# Add more memories
-slm remember "Prefer React hooks over classes"
-# ... add 20+ memories ...
-
-# Rebuild patterns
-slm build-graph
-```
-
-## Output Interpretation
-
-### Status: HEALTHY
-✅ All systems operational
-- Database intact
-- Graph built
-- Patterns learned
-- Backups available
-
-### Status: WARNING
-⚠️  Minor issues detected
-- Old backups
-- Large database
-- Few patterns learned
-
-**Action:** Review verbose output
-
-### Status: ERROR
-❌ Critical issues
-- Database corrupted
-- Integrity check failed
-- No accessible data
-
-**Action:** Restore from backup immediately
-
-## Performance Benchmarks
-
-| Command | Typical Time | Notes |
-|---------|-------------|-------|
-| `slm status` | ~200ms | Fast, lightweight |
-| `slm status --verbose` | ~500ms | More data fetching |
-| `slm status --check-integrity` | ~2s | Full DB scan |
-
-**For large databases (10,000+ memories):**
-- Basic status: ~500ms
-- Verbose: ~1.5s
-- Integrity check: ~10s
-
-## Notes
-
-- **Non-destructive:** Status check never modifies data
-- **Real-time:** Shows current state (not cached)
-- **Cross-tool:** Same status from all AI tools
-- **Privacy:** All checks local, no external calls
-
-## Related Commands
-
-- `slm list` - List recent memories
-- `slm build-graph` - Rebuild knowledge graph
-- `slm switch-profile` - Switch memory profile
-- `slm recall` - Search memories
-
----
-
-**Created by:** [Varun Pratap Bhardwaj](https://github.com/varun369) (Solution Architect)
-**Project:** SuperLocalMemory V2
-**License:** MIT (see [LICENSE](../../LICENSE))
-**Repository:** https://github.com/varun369/SuperLocalMemoryV2
-
-*Open source doesn't mean removing credit. Attribution must be preserved per MIT License terms.*