Menu
Display QAVR (Q-Value Augmented Vector Retrieval) system status including mode, interaction counts, top memories by Q-value, and configuration.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.
Guide for manually creating custom skills from scratch with templates and validation. Use when designing NEW skills with specific requirements. For auto-generating skills from existing git repos, use /generate-skills instead.
Enables continuous self-improvement through learning from failures, user corrections, and capability gaps. Integrates with QAVR for learned memory ranking.
Stress-test solutions using the STRIKE framework. Systematically attack proposals to find weaknesses before deployment.
Exhaustive solution space exploration. Use when you need ALL viable options (not just the best), solution space is unknown, or you can't afford to miss alternatives.
Diagnostic reasoning for finding root causes. Generates multiple hypotheses, designs tests to eliminate each, and converges on the true cause through evidence.
| name | qavr-status |
| description | Display QAVR (Q-Value Augmented Vector Retrieval) system status including mode, interaction counts, top memories by Q-value, and configuration. |
| version | 1.0.0 |
| command | qavr-status |
Purpose: Quick diagnostic view of the QAVR learned memory system.
/qavr-status [context]
Arguments:
context (optional): Specific context to check (e.g., "debugging", "research"). Defaults to showing all contexts.For each context (or specified context):
Top 5 memories by Q-value for each warm context:
Current QAVR settings from ~/.claude/qavr/config.yaml
When this skill is invoked, execute the following:
import sys
sys.path.insert(0, '/home/kim/.claude/qavr')
from q_value_store import QValueStore
store = QValueStore('/home/kim/.claude/qavr/q_values.json')
stats = store.get_stats()
print("=" * 50)
print("QAVR System Status")
print("=" * 50)
print(f"Memories tracked: {stats['memory_count']}")
print(f"Contexts: {stats['context_count']}")
print(f"Warm contexts: {', '.join(stats['warm_contexts']) or 'None'}")
print(f"Cold contexts: {', '.join(stats['cold_contexts']) or 'None'}")
print(f"Total interactions: {stats['total_interactions']}")
print()
# Per-context details
for ctx in store.context_interactions:
mode = store.get_mode(ctx)
interactions = store.context_interactions[ctx]
remaining = store.interactions_to_warm(ctx)
print(f"Context: {ctx}")
print(f" Mode: {mode}")
print(f" Interactions: {interactions}")
if mode == 'cold':
print(f" To warm: {remaining} more interactions")
else:
print(f" Top memories:")
for mem in store.get_top_memories(ctx, 5):
print(f" {mem['memory_id']}: Q={mem['q']:.3f} ({mem['visits']} visits)")
print()
# Config summary
print("Configuration:")
print(f" Learning rate: {store.config.learning_rate}")
print(f" Cold threshold: {store.config.cold_start_threshold}")
print(f" Min Q threshold: {store.config.min_q_threshold}")
==================================================
QAVR System Status
==================================================
Memories tracked: 42
Contexts: 3
Warm contexts: debugging, research
Cold contexts: implementation
Total interactions: 287
Context: debugging
Mode: warm
Interactions: 156
Top memories:
seed_debug_001: Q=0.997 (76 visits)
mem_debug_042: Q=0.891 (23 visits)
mem_debug_018: Q=0.834 (41 visits)
seed_explore_001: Q=0.812 (19 visits)
mem_debug_033: Q=0.756 (12 visits)
Context: research
Mode: warm
Interactions: 112
Top memories:
mem_research_007: Q=0.923 (34 visits)
mem_research_012: Q=0.867 (28 visits)
seed_research_001: Q=0.801 (19 visits)
Context: implementation
Mode: cold
Interactions: 19
To warm: 81 more interactions
Configuration:
Learning rate: 0.1
Cold threshold: 100
Min Q threshold: 0.3
confidence-check-skills - Pre-implementation validation (uses QAVR for duplicate detection)agent-memory-skills - Agent memory framework with QAVR integrationchromadb-integration-skills - ChromaDB patterns (QAVR wraps these)