القائمة
Designs actionable logs, metrics, traces, dashboards and alerts for reliable operations. Use when instrumenting services, defining SLIs, or improving on-call signal quality.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Governs AI models through inventory, purpose, risk tier, approval, monitoring, drift, kill-switch and retirement. Use when introducing, changing or operating models in production or agent workflows.
Applies an Asimov-inspired hierarchy of AI safety laws when material AI or instruction risk is present. Use when harm, unlawful requests, authority conflicts, or safety trade-offs need an explicit law hierarchy. Also known as apply_laws_of_AI.
Use when implementing input validation, output filtering, tool restrictions, policy enforcement, secure coding controls, destructive-tool guardrails, approval gates, or safe agent behaviour.
Use when starting a session or deciding which local skill applies; acts as the meta-skill for discovering and loading the smallest relevant skill.
Use when measuring coding-agent quality, RAG evaluation, regression risk, latency, cost, reliability, safety, or production performance for agent systems.
Designs ontology-driven knowledge graphs for explainable KG-RAG. Use when modelling semantic graphs, ontologies, or graph schemas for retrieval.
| name | observability-and-telemetry |
| description | Designs actionable logs, metrics, traces, dashboards and alerts for reliable operations. Use when instrumenting services, defining SLIs, or improving on-call signal quality. |
| aliases | ["improve-telemetry","telemetry"] |
Use this skill when adding or reviewing logs, metrics, traces, dashboards, alerts, telemetry standards, OpenTelemetry instrumentation, service health checks, operational evidence or workflow monitoring.
Make service behaviour understandable from the outside so operators can detect, diagnose and respond to user-impacting issues quickly.
| Type | Use for | Anti-pattern |
|---|---|---|
| Metrics | trends, rates, thresholds, SLOs | high-cardinality unbounded labels |
| Logs | discrete events, decisions, errors | unstructured noisy dumps |
| Traces | request/workflow path and latency | tracing without useful spans |
| Dashboards | operational review and triage | vanity metrics |
| Alerts | urgent action | non-actionable noise |
workflow_id: "uuid"
request_id: "uuid"
source_id: "uuid"
batch_id: "uuid"
tenant_id: "string"
workflow_type: "string"
step_name: "string"
status: "success | failure | partial"
error_type: "string"
For product-specific DataOps/MCP examples, load skills_docs/overlays/mas-dataops-mcp-overlay.md.
Before adding an alert, answer what user impact it represents, who owns it, what action the responder should take, what dashboard or runbook helps, what threshold avoids noise and how the alert will be tested.