Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access."..." for exact phrases · Try typography, debugging or spreadsheetScan codebases for compliance gaps and check Arize instrumentation for audit trail coverage. Produces remediation checklists for selected frameworks, including the EU AI Act, GDPR, NIST AI RMF, Colorado AI Act, HIPAA, and ISO 42001.
Manages dataset creation, updates, deletion, versions, and example appends in Arize. Supports file-based creation and exports for test sets, golden datasets, and evaluation examples using the ax CLI.
Manages evaluator creation, updates, tasks, column mappings, and evaluation runs on spans or experiments. Supports LLM judges, code evaluators, evaluator prompt improvements, and continuous monitoring of qualities such as correctness and faithfulness.
Creates and updates evaluators, scores spans and experiments, and manages evaluation tasks and trigger runs. Covers column mapping, continuous monitoring, and evaluator prompt improvements for qualities such as correctness, relevance, and faithfulness.
Creates and manages experiments using the ax CLI, exports runs, and compares results. Supports AI evaluation workflows, model benchmarks, A/B comparisons, and accuracy measurement.
Detects an application's stack, selects its matching integration documentation, and configures auto-instrumentation after confirmation. Supports initial LLM observability setup with Arize, OpenTelemetry, or OpenInference and verifies trace delivery.
Discovers organization and project IDs with the ax CLI and constructs clickable Arize UI URLs. Supports sharing projects, traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configurations.
Extracts prompts from spans and gathers performance evidence through the ax CLI. Uses traces, evaluations, and annotations in an iterative optimization workflow to debug prompts and improve output quality.
Extracts prompts from spans and gathers performance signals from trace data, evaluations, and annotations. Runs a data-driven optimization loop with the ax CLI to improve prompts and output quality.
Supports creating, importing, saving, listing, retrieving, editing, deleting, and duplicating prompt templates. Manages variable placeholders and labels for promotion between environments such as staging and production.
Retrieves traces, spans, and sessions by ID using the ax CLI. Supports runtime error investigation, behavior regression analysis, and root-cause diagnosis from existing trace data.
Provides a magazine article layout inspired by Huashu and huashu-md-html. Transforms Markdown or notes into polished, long-form HTML essays.
A growing collection of real, public skills. Descriptions and instructions indexed 24 Sept 2026.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name