134 skills · sorted by relevance
Investigate LLM application failures with Phoenix CLI by reviewing execution records, recording observations, and grouping mistakes into counted categories. Inspect datasets and experiments to identify which failure types deserve evaluation tests first.
Create shareable links that open specific Arize resources, including traces, datasets, and evaluators. Use IDs from logs or exported data, with suitable time ranges, to direct teammates to the relevant view.
Improve LLM prompts using Arize production traces, evaluation results, and human feedback. Extract current instructions, identify recurring failures, revise the prompt, and compare experiments to measure changes in output quality and catch regressions.
Navigate the Composio SDK monorepo, a repository containing multiple packages, and follow its shared development rules. Use it to decide where changes belong, handle generated files and release metadata, and prepare branches and pull requests.
Evaluate a strategic choice through multiple executive roles, each forming an independent view before discussion. Produce a board memo with recommendations, votes, dissent, risks, and success or stop conditions for the founder's decision.
Track work across sessions with persistent issues, dependencies, and progress notes. Use the bd command-line tool to find unblocked work, claim issues, record completion, and recover task context after conversation compaction.
Explore relationships between functions and files using a prebuilt code graph, a map of code dependencies. Trace bugs, inspect callers and execution paths, and assess the impact of refactoring or proposed changes.
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.
Keep context for work that spans multiple sessions without belonging to a specific project phase. The skill manages lightweight persistent threads, letting you create, list, resume, check, and close them as work progresses.
Add Sentry error reporting and performance monitoring to services, scheduled jobs, and database operations. Follow examples for capturing exceptions with useful context and measuring execution time through spans, which record individual operations for investigation.
Design, review, and implement Gantt charts for project schedules. Assess source data, task dependencies, and resource needs, then define suitable views, editing behavior, rendering tools, accessibility, exports, and tests—or recommend a clearer alternative.
Coordinate Cloud Claw workflows from launching an agent deployment to managing its virtual machine. It routes work to focused skills for setup, starting and stopping machines, viewing logs, renewing usage, and accessing dashboards through local altllm commands.
Coordinate AltLLM Portal CLI tasks across wallet login, API key management, credit balances, billing history, and crypto top-ups. This umbrella skill routes each part of a broader workflow to the relevant specialized skill.
Turn a multi-file development task or technology migration into a specification with acceptance criteria, then launch background implementation and verification. The workflow clarifies missing requirements, reviews the specification, and tracks progress and blockers through linked jobs.
Plan complex coding changes by exploring existing code, clarifying requirements, and tracing effects across the system. Produce a PLAN.md with recommended changes, affected files, and verification steps, then implement after the user approves.
Review explicitly selected tests or bounded pull request changes without running or editing code. Receive a follow-up decision for each test, A–F quality bands where assessable, evidence-based notes, and concrete suggestions for improvement.
Assign incoming support tickets to the team best placed to resolve them and set priority based on customer impact. Handle cases involving two teams, and write brief internal summaries describing the problem and what the customer already tried.
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.
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.
Map the full ecosystem of touchpoints, channels, and relationships across a service. Use when the experience spans more than one product. For one persona's linear journey use `journey-map` (design-research); for backstage operations use `service-blueprint`.
The English summary is being prepared. Showing the original description.
Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization. Triggers on: "evaluate my agent", "add evaluator", "measure quality", "quality gate", "run evals", "agent too slow", "why is it slow", "reduce latency", "set up observability", "CloudWatch dashboard", "how much does my agent cost", "cost optimization", "logs not showing up", "logs missing", "spans not found", "eval failing", "eval error", "dev traces", "local traces", "agentcore dev traces", "traces to CloudWatch". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.
The English summary is being prepared. Showing the original description.
Guides migration, provisioning, search, log-analytics, trace-analytics, and Agentic AI Assistant workflows for Amazon OpenSearch Service and Serverless across six capabilities — migration (Solr/ES/self-managed into AOS/AOSS, schema/query translation, sizing, cutover); provisioning (domain + AOSS lifecycle, upgrades, FGAC, monitoring); search (vector / semantic / hybrid / RAG with Bedrock); log-analytics (PPL, OSI, anomaly detection, Dashboards); trace-analytics (OTel spans, service maps, Data Prepper); ai-assistant (natural language data exploration, incident investigation, root cause analysis). Triggers on OpenSearch, AOS, AOSS, Elasticsearch, Solr, vector/k-NN/semantic/hybrid search, RAG, log analytics, PPL, trace analytics, ISM, FAISS, HNSW, Migration Assistant, UltraWarm, OR1, query my data, analyze logs, investigate errors, root cause analysis.
The English summary is being prepared. Showing the original description.
Route broad or ambiguous AgentKit SEO work to the right module while keeping context scoped. Use when a request spans multiple surfaces, asks for overall digital-presence strategy, involves provider or install architecture, needs agent-context planning, or the correct platform skill is unclear.
The English summary is being prepared. Showing the original description.
Designs how an organization is structured — reporting lines, team boundaries, spans and layers, role definition, and workforce planning against the strategy. Use this to structure a new team, restructure an existing one, resolve unclear ownership between teams, plan headcount, or diagnose why a team underperforms for structural rather than individual reasons.
The English summary is being prepared. Showing the original description.