Agent skill
dgx-health
Check DGX Spark health, Milvus status, and vector search performance. Use to monitor infrastructure.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/dgx-health
SKILL.md
DGX Spark Health Check
Monitor DGX Spark infrastructure and Milvus vector database health.
Health Checks
1. Milvus API Health
Check Milvus endpoint via Cloudflare Tunnel:
curl -s -o /dev/null -w "%{http_code}" https://dgx-milvus.pentatonic.com/v1/vector/collections
Expected: 200
2. Collection Status
Verify products_v2 collection is accessible:
curl -s https://dgx-milvus.pentatonic.com/v1/vector/collections/products_v2 | jq '.data.rowCount'
3. Search Latency Test
Run a test query to measure response time:
time curl -s -X POST https://dgx-milvus.pentatonic.com/v1/vector/search \
-H "Content-Type: application/json" \
-d '{"collectionName": "products_v2", "limit": 5}'
Target: < 100ms
4. DGX SSH Connectivity (if SSH MCP available)
Test SSH connection to DGX Spark:
ssh -o ConnectTimeout=5 dgx-spark.pentatonic.com "echo 'SSH OK'"
5. GPU Status (via SSH)
Check NVIDIA GPU status:
ssh dgx-spark.pentatonic.com "nvidia-smi --query-gpu=name,memory.used,memory.total,utilization.gpu --format=csv"
6. Milvus Container Status (via SSH)
ssh dgx-spark.pentatonic.com "docker ps | grep milvus"
Report Format
## DGX Spark Health Report
### Connectivity
- Milvus API: [OK/FAIL]
- SSH: [OK/FAIL]
- Cloudflare Tunnel: [OK/FAIL]
### Vector Database
- Collection: products_v2
- Row Count: [X]
- Search Latency: [X]ms
### GPU Status
| GPU | Memory Used | Memory Total | Utilization |
|-----|-------------|--------------|-------------|
| ... | ... | ... | ... |
### Recommendations
- [Any issues or optimizations]
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?