Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding…
Review Python OpenInference instrumentation code for correctness and completeness. Use this skill when reviewing a Python instrumentor package — whether it's a new instrumentor, a PR that modifies one, or when the user asks to audit/review/check an existing instrumentor's code quality. Trigger on phrases like "review…
Run, interpret, and iterate on the OpenInference GenAI conformance MVP at python/openinference-instrumentation/scripts/conformance/. Use when the user mentions GenAI conformance, OTel GenAI semantic conventions, Weaver registry live-check, the dual-write conversion (genaiconversion.py, enablegenaisemconv), genai.…
A read-only shell skill for examining files and running diagnostic commands in a restricted environment. A shell is a text interface for operating-system commands.
Audit the running app via chrome-devtools MCP — console errors/warnings + failed/slow network by default; perf (LCP/CLS) and Lighthouse (a11y/SEO) are opt-in. Token-efficient (compacts findings in-browser via a console/network hook); the report is shown inline in the response — no files to open. Target one tab / an…
Read from a UModel object-graph semantic layer with the umctl CLI (MCP alternative noted). Three kinds of read: (1) entities & relationships / topology (.entity, .topo) and (2) the model itself (.umodel, and .entityset methods, including entity-linked listskills) return real rows; (3) metrics & logs (getmetrics /…
Model-guided autonomous root-cause analysis over a UModel object-graph semantic layer. Use with umodel-query when diagnosing service degradation, SLO breach, latency/error spikes, incidents, outages, or questions like why a service is slow, degraded, erroring, or timing out. The skill guides evidence collection across…
Use when an EntitySet exposes listskills, a user requests a UModel or RunbookSet Skill, or an entity task supplies SKILL.md. Triggers: listskills, listknowledge, RunbookSet Skill, UModel Skill, execute skill, run skill, 执行技能, 运行技能, Runbook 技能.
Use when asked to triage, investigate, or diagnose a Kubernetes incident, outage, or unhealthy workload. Gives the step-by-step order of investigation and the format for the findings.
Analyze cluster-wide Kubernetes events to identify issues and patterns. Aggregates Warning events, detects high-frequency patterns, and correlates related events.
Retrieve logs from a Kubernetes node — systemd units (journalctl) or files under /var/log. Use when you need node-level evidence: containerd, kubelet, kernel/OOM, or anything the pod's own log cannot show. Three access paths in order: hostscript (SSH), nodescript (debug pod), and localscript against the kubelet log…
Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.