804 skills · sorted by relevance
Add Arize AX tracing to an LLM application, recording how model calls and tool executions connect. Inspect the existing code, select suitable integrations, add instrumentation, and verify that the application runs and traces reach Arize.
Manage the credentials Arize uses to call LLM providers such as OpenAI and Anthropic. Create, inspect, update, or delete connections, configure allowed models and authentication methods, and retrieve connection IDs for use in evaluations.
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.
Summarize web articles, YouTube videos, podcasts, and local files with the summarize command-line tool. Extract available text or transcripts from URLs, choose a summary length, and request JSON output for use in other workflows.
Create and manage Arize datasets for evaluation and experiments using the ax CLI. Import records from files, append examples, inspect dataset versions, and export a chosen version for offline analysis, with checks for field consistency and export completeness.
Organize human review in Arize by defining label choices, numeric ranges, or free-text feedback fields. Manage review queues and reviewers, submit annotations for individual records, and apply existing labels to project spans, or individual processing records, in bulk.
Azure Resource Manager SDK for Arize AI Observability and Evaluation (.NET). Use when managing Arize AI organizations on Azure via Azure Marketplace, creating/updating/deleting Arize resources, or integrating Arize ML observability into .NET applications. Triggers: "Arize AI", "ML observability", "ArizeAIObservabilityEval", "Arize organization".
The English summary is being prepared. Showing the original description.
Summarize any block of text using the `summarize` CLI (chained-in from steipete/summarize — npm package `@steipete/summarize`). Use whenever the user pastes a long piece of content and asks for a TL;DR, a summary, a digest, a gist, a condensed version, or key points — even if they don't explicitly say "use summarize". Also chains into `mktg-transcribe --summarize` for audio/video TL;DRs and source-digestion workflows to condense long articles. Requires the `summarize` CLI to be installed (`mktg doctor` will tell you if it's missing). Do NOT trigger for structured data (JSON/CSV/code), for text already shorter than ~500 words, or when the user wants the full content preserved.
The English summary is being prepared. Showing the original description.
Create and run evaluations in Arize using an LLM as the judge. Define scoring criteria, connect them to actual data fields, evaluate recorded operations or experiment results, and set up continuous scoring for new data.
Inspect existing LLM application records in Arize to investigate errors, slow operations, or behavior changes. Export traces, which group related operations, or individual operations and conversation sessions as JSON using the ax command-line tool.
Create and analyze AI model evaluation experiments in Arize using the ax CLI, a command-line tool. Collect real model outputs, export results, compare evaluation scores, and identify examples where a new model performs worse.
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.
Summarize articles, YouTube videos, podcasts, PDFs, and local files to understand their main points. Choose the summary length or extract source content, including available YouTube transcripts, for closer reading and further processing.
Summarize articles, YouTube videos, podcasts, and local files, or extract available text and transcripts. Choose the summary length to suit the task and use transcript extraction to inspect video content when available.
Create and maintain Paperclip status cards for work you want to track. Turn a plain-language request into focused task searches, produce an initial summary, and update reports using the changes or snapshots supplied to the assigned run.
Read and summarize local text files, including notes, configuration files, CSV tables, logs, and source code. Extract relevant sections, explain key fields or columns, and review recent errors without loading an entire large file.
Summarize articles, local files, YouTube videos, and podcasts to review their main points. Adjust the summary length, or extract available text and transcripts from URLs when you need the source content.
Summarize WeChat group conversations into organized digests with discussion highlights, verified speaker attribution, and message statistics. Keep group history, participant profiles, and factual notes across runs, or summarize only messages received since the previous digest.
Summarize popular Hacker News stories or find discussions on a specific topic. Get article highlights, scores, comment counts, and recurring discussion themes, including agreement, criticism, and related debates.
INVOKE THIS SKILL when adding Arize AX tracing to an application. Follow the Agent-Assisted Tracing two-phase flow: analyze the codebase (read-only), then implement instrumentation after user confirmation. When the app uses LLM tool/function calling, add manual CHAIN + TOOL spans so traces show each tool's input and output. Leverages https://arize.com/docs/ax/alyx/tracing-assistant and https://arize.com/docs/PROMPT.md.
The English summary is being prepared. Showing the original description.
Summarize a Paperclip project or workspace in plain language, starting with up to three concrete actions needed to unblock work. Review issues and comments, then save a concise Markdown update to its summary slot.
Write a single-line commit message for Ant Design by reading staged changes, the changes selected for the next commit. It summarizes the full commit intent and follows the style of recent repository commits.
Operate NVIDIA Nsight Graphics from the command line to capture application frames and GPU activity. Summarize performance traces, analyze existing capture files through ngfx-replay, and check installed versions and compatibility before starting an investigation.
Analyze threat intelligence stored in MISP, a platform for sharing security threat data. Summarize event counts, indicator types, attacker groups, and trends over time to create a threat landscape report for a chosen period.