Loading...
Loading...
Found 456 Skills
Query the otel-relay span store directly via HTTP to interrogate traces from local render runs without consuming the full SSE stream.
Hermes-native AIOps agent for evidence-driven incident response, approval-gated remediation, and runbook learning
End-to-end pipeline from unlabeled ml_app traces to a bootstrapped evaluator suite. Runs trace classification → root cause analysis → eval bootstrap in sequence with user checkpoints. Use when user says "run the eval pipeline", "go from traces to evals", "bootstrap evals end to end", "classify then RCA then bootstrap", "build an eval set from scratch", or wants a guided walkthrough from production data to evaluator code.
Configure an AI agent to send OpenTelemetry traces to Coval. Use when a user wants to add Coval tracing, instrument an agent for simulations or conversation monitoring, make traces show up in Coval, handle SIP/PSTN/WebSocket trace correlation, or replace the one-command wizard with a security-reviewable manual setup.
Consult this skill when designing data pipelines or transformation workflows. Use when data flows through fixed sequence of transformations, stages can be independently developed and tested, parallel processing of stages is beneficial. Do not use when selecting from multiple paradigms - use architecture-paradigms first. DO NOT use when: data flow is not sequential or predictable. DO NOT use when: complex branching/merging logic dominates.
Honeycomb.io integration. Manage data, records, and automate workflows. Use when the user wants to interact with Honeycomb.io data.
Logit.io integration. Manage data, records, and automate workflows. Use when the user wants to interact with Logit.io data.
Use when the user wants to create, list, get, update, rename, or delete a SigNoz saved Explorer view. Trigger on phrases like "save this query as a view", "save this filter", "bookmark this search", "list my saved views", "show me views for traces/logs/metrics", "rename the X view", "update my saved view to also filter Y", "delete the X view", or any request to manage Explorer saved views — even if they don't say "view" explicitly. Also use when someone wants to share a recurring Explorer query with their team and asks how to "save" or "bookmark" it.
Modify an existing SigNoz dashboard — add or remove panels, edit a panel's query, threshold, or unit, rename the dashboard, change a panel type (graph ↔ table ↔ value), rearrange the layout, add or edit variables, or update tags. Make sure to use this skill whenever the user says "add a panel to my dashboard", "change the query on this panel", "remove the latency widget", "rename my dashboard", "update the filters", "rearrange the layout", "add a variable", "change panel type from graph to table", or otherwise asks to change something on a dashboard that already exists — even if they don't say "modify" or "edit" explicitly.
Analyze production Agentforce agent behavior using session traces and Data Cloud. TRIGGER when: user queries STDM session data or Data Cloud trace records; investigates production agent failures, regressions, or performance issues; asks about session traces, conversation logs, or agent metrics; wants to reproduce a reported production issue in preview; runs findSessions or trace analysis queries. DO NOT TRIGGER when: user creates, modifies, or debugs .agent files during development (use developing-agentforce); writes or runs test specs (use testing-agentforce); uses sf agent preview for local development iteration; deploys or publishes agents.
Guides Site Reliability Engineering—SLI/SLO and error budgets, reliability dashboards and burn-rate alerting, production readiness reviews, capacity planning for availability, toil reduction, dependency and failure-mode analysis, release reliability (canaries, rollback criteria), and service-owner incident mitigation tied to customer impact. Use when defining or operating SLOs, measuring error budget burn, improving service reliability, running PRRs before launch, planning scalable resilient capacity, or leading technical mitigation during outages—not for CI/CD pipeline implementation (devops), incident program and paging policy design (incident-management-engineer), cloud access and patch tickets (cloud-system-administrator), load-test profiling (performance-engineer), rollout cutover strategy (deployment-strategist), or greenfield cloud build-out (cloud-engineer).
Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says "generate Python experiment", "write an SDK experiment", "create a ddtrace experiment", "Python notebook experiment", "use the LLM Obs SDK", or has `ddtrace` installed and wants idiomatic SDK code.