439 skills · sorted by relevance
Automate a real browser from the terminal to navigate pages, fill forms, extract data, and investigate interface problems. Use page snapshots to identify controls, and capture screenshots or traces, records of browser activity, for review.
Build AI features for Dart and Flutter applications with the Genkit Dart SDK. Provides code and documentation for conversational agents, reusable processing flows, prompt files, model integrations, interactive interfaces, and debugging through recorded execution traces.
Build AI applications in Python with Genkit, including conversational agents, generation workflows, streaming responses, and tool use. The skill also guides setup and debugging through traces, recorded details of model inputs, outputs, and actions.
Add DeepEval tracing to Python AI applications so execution steps appear in Confident AI. Choose a supported integration or manual @observe instrumentation, then capture inputs, outputs, step types, tags, and metadata.
Record and query iii engine logs, traces that show how calls flow, and operational metrics. Set up reactions to incoming errors, inspect alerts, and review metrics aggregated over time windows.
Set up distributed tracing in KubeSphere to follow requests across services. Covers extension installation, trace collection, automatic application instrumentation, and API queries for traces, individual processing steps, and service connections.
Set up and manage a local Kubernetes development environment for OpenShell using k3d, Skaffold, and Helm. Build and deploy changes, inspect traces, configure optional authentication components, and test behavior across multiple gateway replicas.
Investigate and fix production errors reported in Sentry through MCP, a connection to external tools. Analyze error details and execution history, check them against source code, implement fixes, and verify them with tests and regression checks.
Create terminal-style review slides for command-line tools, AI agents, and developer tools. Present execution traces, code differences, and performance comparisons using dark backgrounds, mint-green text, outlined bar charts, and amber, green, or red tags.
Choose diagnostic tools and collect performance traces for production .NET problems such as high CPU usage, memory growth, or slow requests. Get environment-specific collection commands and guidance on which tools to use for later analysis.
Analyze gh-aw execution traces, which record individual processing steps, to investigate slow or failing workflows. Using local JSONL files or telemetry backends, the skill checks timing, errors, missing attributes, and trace connections to support focused improvements.
Test APIs and forms with unexpected input to uncover error responses that expose internal details. The skill checks response bodies for stack traces, server paths, and library information, preserving specific evidence rather than treating every server error as a vulnerability.
Add OpenTelemetry tracing to frontend and backend flows. Connect execution records across services and background jobs, record phase durations and entity IDs, and mark failures so developers can investigate slow or broken operations.
Investigate bugs in a running local application using service logs, traces that follow requests across services, and a shared browser. Connect frontend actions to backend activity, inspect failures, and verify that tracing records appear as expected.
Run Unity tests in EditMode or PlayMode, selecting specific assemblies, namespaces, classes or methods. Review individual outcomes and durations, filter results, and include failure messages, logs or stack traces to investigate problems.
Automatically send Claude Code conversations and tool calls to Braintrust. View nested activity records that connect each session, conversation exchange, and operation, including file reads, edits, and terminal commands, to inspect how coding work unfolded.
Automate a real browser from the terminal to navigate pages, fill forms, extract data, and investigate interface problems. Use page snapshots to identify controls, and capture screenshots or traces, records of browser activity, for review.
[omh] Turn repeated lessons into written rules: extract repeated principles from skills, prompts, traces, reviews, and failures into reviewed rule candidates without auto-mutating guidance. Use when the user says: rules-distill, rules distill, distill rules, rule distillation, principle distill, skill principles, extract agent rules, turn traces into rules.
The English summary is being prepared. Showing the original description.
Instrument browser/web apps with the Application Insights JavaScript SDK (@microsoft/applicationinsights-web). Use for Real User Monitoring (RUM) — page views, clicks, AJAX/fetch dependencies, exceptions, custom events, and browser-side GenAI agent traces correlated to backend OpenTelemetry traces. Covers SDK Loader Script and npm setup, framework extensions (React, React Native, Angular), Click Analytics, telemetry initializers, and OTel GenAI semantic conventions for agent/tool/model spans emitted from the browser.
The English summary is being prepared. Showing the original description.
Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisites when the CLI itself isn't working. Triggers on: "agent not working", "wrong answer", "agent error", "tool call failing", "debug agent", "check logs", "read traces", "broken", "500 error", "424 error", "model access denied", "command not found", "stuck in DELETING", "maxVms exceeded", "cold start diagnosis", "cold start slow", "agentcore create error", "create failed", "exit code 7", "connection refused local dev". Not for deploy failures — use agents-deploy. Not for performance tuning without errors — use agents-optimize. Not for VPC configuration — use agents-build. Not for observability setup or missing logs — use agents-optimize.
The English summary is being prepared. Showing the original description.
Builds, configures, debugs, and optimizes AWS observability - operator-symptom questions and detecting Omni vs classic CloudWatch. CloudWatch on an already-reporting service: Log Insights, metric/composite/anomaly alarms, custom metrics/EMF, dashboards, X-Ray/ADOT tracing, canaries, CloudTrail, Dynamic Instrumentation (live breakpoints/snapshots), the Application Signals service map, and fleet health views. CloudWatch Omni on an existing Space: SQL over logs and traces, PromQL over metrics, Omni dashboards, Omni alerts, context graph for root cause, programmatic/IaC access (API/SDK/CLI/CloudFormation), driving Omni from a coding agent or skills, and evaluating AI agent quality from traces - on-demand and online scoring of live traffic, readback, custom evaluators. For first-time setup - creating an Omni Space, granting access, ingestion, or ADOT instrumentation for Application Signals (ServiceEvents, CI/CD metadata) or Omni - use setting-up-cloudwatch-observability. Not for app logging or threat detection.
The English summary is being prepared. Showing the original description.
Add file-based observability, tracing, and run analysis to LLM/agent experiments — per-turn transcripts, tool calls and results, reasoning traces, token/cost accounting, per-episode artifacts, plus terminal viewers and a run-comparison report. Platform-agnostic: one small adapter covers OpenAI, Gemini/Vertex, Anthropic, LiteLLM, Tinker, vLLM, or any custom inference stack, and the same tooling then works unchanged. Use this skill whenever the user wants observability, tracing, logging, or run tracking for model experiments; asks why an agent failed a task or wants to replay/debug/diff an episode; wants to compare models, arms, or ablations; wants to instrument a new folder, repo, or platform ("add observability here", "do the same for Tinker/Gemini/OpenAI"); wants to import or tie in existing experiment results so old runs show up alongside new ones; or wants eval runner scripts where many models share one protocol. Reach for this even when they only say "log what the model is doing", "I can't tell what happened in this run", or "set up traces for this experiment".
The English summary is being prepared. Showing the original description.
Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels.
The English summary is being prepared. Showing the original description.
Read and write Langfuse: browse traces and observations, list prompts and datasets, score traces, add dataset items. Trigger phrases: langfuse, llm observability.
The English summary is being prepared. Showing the original description.