- Home
- Skills
- DevOps & Cloud
- Observability, SRE & Distributed Trace Pro
Works with the AI Agents you already use
Observability, SRE & Distributed Trace Pro
Turn your AI assistant into an on-call Site Reliability Engineer. Correlates Prometheus PromQL metrics, Grafana dashboards, Loki LogQL logs, and Tempo distributed traces (`trace_id`).
$19
Observability, SRE & Distributed Trace Pro
Example session with this skill installed
Run a canary audit for the 'order-processor' service in the 'production' namespace compared to 60 minutes ago.
- Read your context and instructions
- Compiled the observability sre
I have completed the post-deployment canary audit for the order-processor service. The analysis compared the last 10 minutes of traffic against the 60-minute baseline.
Canary Audit Report: order-processor (production)
| Metric | Baseline (avg) | Canary (avg) | Delta | Status |
|---|---|---|---|---|
| Latency P95 | 120ms | 450ms | +275% | FAIL |
| Error Rate % | 0.02% | 4.5% | +22400% | FAIL |
| Traffic (RPS) | 1.2k | 1.1k | -8.3% | PASS |
| CPU Saturation | 45% | 88% | +95% | WARN |
| Memory Saturation | 2.1Gi | 2.2Gi | +4.7% | PASS |
Verdict: ROLLBACK_RECOMMENDED
The audit detected a significant spike in P95 latency and a critical increase in 5xx error rates immediately following the deployment. CPU saturation is also approaching critical thresholds.
Next steps
- Trigger a rollback for
order-processorusingk8s-mcp. - Run
obs_correlate_metrics_logs_and_traceto capture log patterns from the failed canary pods. - Check
github-mcpfor recent changes to theorder-processorrequest handling logic.
Connects securely to your tools. The creator never sees your data.
About this skill
🚀 Production Workflows
- Cross-Signal Incident Correlation: Detects elevated error rates in Prometheus, extracts correlated
trace_idvalues from Loki error logs, and inspects the exact trace waterfall in Tempo. - Post-Deploy Golden Signal Canary Audit: Automatically compares error rates, P95/P99 latency, and saturation against pre-deploy baselines, outputting
PASSorROLLBACK_RECOMMENDED. - Microservice Latency Bottleneck Hunting: Ranks the slowest distributed spans across services, highlighting database queries or third-party API bottlenecks.
- Alertmanager Silence Governance: Silences known firing alerts during active maintenance with automated duration tracking.
- Deployment Marker Annotation: Adds Grafana deployment annotations to record code release timestamps on team dashboards.
🛡️ Safety & Governance
- Read-only autonomous telemetry querying (PromQL, LogQL, Tempo OTLP traces).
- Confirmation-gated alert silences and Grafana annotations.
Launch via: uvx observability-mcp
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for DevOps & Cloud.
Requires PROMETHEUS_URL, LOKI_URL, TEMPO_URL, and GRAFANA_URL. Mutating actions like silences require an explicit confirm=true flag.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 16 days ago
- Software
PythonObservability MCP
uv (Python tool runner)