Loading...
Loading...
Found 20 Skills
Bootstrap evaluators from production traces — emit SDK code, a framework-agnostic JSON spec, or publish online LLM-judge evaluators directly to Datadog. Use when user says "bootstrap evaluators", "generate evaluators", "create evals from traces", "eval bootstrap", "write evaluators", "build eval suite", "publish evaluators", or wants to generate BaseEvaluator/LLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, ingestion of customer-supplied pre-generated AnomalyGen images, k-NN mining, retraining, and deployment gating until FAR / recall KPI targets are met. EA variant — does not run AnomalyGen inline; the customer pre-generates synthetic NG/OK pairs out-of-band and the loop ingests them. Use for prompts like "run the DEFT loop", "fine-tune until FAR below 0.1% at recall=100%", or "improve my AOI ChangeNet model with RCA and pre-generated synthetic defects"; do not use for standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.
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.
Use when investigating and documenting a production incident, outage, data corruption event, or post-mortem — guides evidence collection during the investigation AND produces a rich, reproducible Root Cause Analysis report. Trigger on phrases like "write an RCA", "post-mortem for X", "document this incident", "what went wrong with...", "the pipeline broke yesterday, help me investigate", or any time the user is debugging a recently-resolved incident and wants a writeup. Also use proactively when the user finishes resolving an incident in-session and the resolution context is fresh — offer to capture it as an RCA before details fade.
UiPath Process Mining via `uip pm` — build and operate a process app end-to-end from a CSV / event log: templates, data mapping, upload, ingest, the dbt (Snowflake) transformation layer, publish, and query it (metrics, percentiles, RCA). Covers `uipath.custom`, the `Cases.sql` optional-column gotcha, Case-linked data-model tables (add-table + re-ingest), the apply-not-reingest fix loop, fixing a wrong mapping in place via `apps data-mapping get|update` (no app rebuild), and editing the app model via `apps model fields` — a field's data kind / calculated fields, including the numeric→duration mismatch that locks dashboards open (DNA-46960). For Orchestrator/Data Fabric/Integration Service→uipath-platform. For `.flow`/Maestro→uipath-maestro-flow. For IXP→uipath-ixp.
Bug investigation and fix workflow. Triggers: 'debug', 'fix bug', 'investigate issue', 'something is broken', or /debug. Hotfix track for quick fixes, thorough track for root cause analysis. Do NOT use for feature development or refactoring. Do NOT escalate to /ideate unless the fix requires architectural redesign.
Conduct systematic root cause analysis to identify underlying problems. Use structured methodologies to prevent recurring issues and drive improvements.
Elastic ML anomaly detection skill — investigation/RCA, score explanation, job operations (create, datafeed, start/stop, results), and troubleshooting (missing docs, memory limits, datafeed health, lifecycle). Operates against Kibana Agent Builder MCP tools (`ad_*`) on `.ml-anomalies-*`, `.ml-config`, `.ml-notifications-*`, `.ml-annotations-*`. Use when answering "what broke?"/"which entity?"/RCA, "why is score high/low?"/renormalization, "datafeed stopped"/"memory limit", or any request to set up or configure an ML anomaly detection job.