@skills · Owner

Agent skills by arize-ai

79 skills indexed from github.com/arize-ai. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.

• .agents · Collection · 10,926 stars
• .agents · Collection · 10,926 stars
• .agents · Collection · 10,926 stars
• .agents · Collection · 10,926 stars
• agent-browser · Skill · 10,926 stars

  Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, takin

• agents · Collection · 10,926 stars
• annotate-spans · Skill · 10,926 stars

  Write effective, consistent annotations on LLM/agent spans and traces, and coach the user on annotation practice. Load this whenever you are about to recor

• datasets · Skill · 10,926 stars

  Understand what a Phoenix dataset is and reason well about its examples, outputs, splits, and how it feeds evaluators and experiments. Load this whenever a

• debug-trace · Skill · 10,926 stars

  Diagnose failure modes by systematically investigating traces. Trigger when the user explicitly asks for cross-trace diagnosis: "what's going wrong?", "wer

• evaluators · Skill · 10,926 stars

  Author or refine a Phoenix evaluator — code or LLM-as-a-judge — that scores a run's output. Trigger when the user wants to create a new evaluator, improve

• experiments · Skill · 10,926 stars

  Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving. Trigger when the user wants to iterate over a da

• gh-stack · Skill · 10,926 stars

  Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase,

• js · Collection · 10,926 stars
• mintlify · Skill · 10,926 stars

  Build and maintain documentation sites with Mintlify. Use when creating docs pages, configuring navigation, adding components, or setting up API references

• packages · Collection · 10,926 stars
• phoenix · Collection · 10,926 stars
• phoenix · Collection · 10,926 stars
• phoenix-cli · Skill · 10,926 stars

  Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, rev

• phoenix-cli · Collection · 10,926 stars
• phoenix-cli-development · Skill · 10,926 stars

  Design and implementation guide for the Phoenix CLI (`px`). Covers the noun-verb command structure, dual-audience design (humans and coding agents), Comman

• phoenix-client · Collection · 10,926 stars
• phoenix-client-development · Skill · 10,926 stars

  Development guide for the @arizeai/phoenix-client TypeScript SDK — run and resume experiments, manage OpenTelemetry tracer providers with stack-based attac

• phoenix-design · Skill · 10,926 stars

  Design system conventions for the Phoenix frontend — layout, dialogs, error display, BEM CSS class naming, and CSS design tokens. Use when building UI, nam

• phoenix-docs-gap-audit · Skill · 10,926 stars

  Audit documentation gaps across the Phoenix repo by analyzing recent commits to main (default: last 7 days). Use this skill whenever the user asks to find

• phoenix-evals · Skill · 10,926 stars

  Build and run evaluators for AI/LLM applications using Phoenix.

• phoenix-evals-new-metric · Skill · 10,926 stars

  Create a new built-in classification evaluator for Phoenix evals. Use this skill whenever the user asks to create a new eval, build a new metric, add a new

• phoenix-frontend · Skill · 10,926 stars

  Frontend development guidelines for the Phoenix AI observability platform. Use when writing, reviewing, or modifying React components, TypeScript code, sty

• phoenix-github · Skill · 10,926 stars

  Manage GitHub issues, labels, project boards, sprint operations, and roadmap health for the Arize-ai/phoenix repository. Use when filing roadmap issues, tr

• phoenix-graphql · Skill · 10,926 stars

  Write efficient GraphQL queries against the Phoenix API. Load this skill in two cases: (1) before composing any non-trivial GraphQL query yourself for data

• phoenix-integration-snippets · Skill · 10,926 stars

  Generates onboarding code snippets for Phoenix tracing integrations and wires them into the project onboarding UI. Produces install dependencies and implem

• phoenix-llms-txt · Skill · 10,926 stars

  Maintain the Phoenix llms.txt documentation index at docs/phoenix/llms.txt — the machine-readable docs map used by AI agents and the `px docs fetch` CLI. U

• phoenix-otel · Collection · 10,926 stars
• phoenix-otel-development · Skill · 10,926 stars

  Guide for the phoenix-otel TypeScript package — OTel registration, stack-based global provider management, and provider lifecycle.

• phoenix-playwright-tests · Skill · 10,926 stars

  Write Playwright E2E tests for the Phoenix AI observability platform. Use when creating, updating, or debugging Playwright tests, or when the user asks abo

• phoenix-pr-screenshot · Skill · 10,926 stars

  Screenshot a running Phoenix feature and attach images to a GitHub PR. Builds the frontend, starts Phoenix with env vars, uses agent-browser to capture scr

• phoenix-pxi-playwright · Skill · 10,926 stars

  Write, extend, and debug PXI Playwright E2E tests for Phoenix. Use when adding PXI agent frontend specs, authoring LLM-as-judge rubrics, asserting PXI tool

• phoenix-release-notes · Skill · 10,926 stars

  Create Phoenix release documentation grounded in actual code changes. Use this skill whenever the user asks to write release notes, document a release, upd

• phoenix-release-please · Skill · 10,926 stars

  Bump the next release-please version for a Phoenix Python package (arize-phoenix, arize-phoenix-client, arize-phoenix-evals, arize-phoenix-otel) by opening

• phoenix-rest-api · Skill · 10,926 stars

  REST API development for Phoenix. Use when adding, modifying, or reviewing endpoints in src/phoenix/server/api/routers/v1/.

• phoenix-server · Skill · 10,926 stars

  Backend development guide for the Phoenix AI observability platform (Strawberry GraphQL, SQLAlchemy async, FastAPI). Use this skill when writing or modifyi

• phoenix-skills-audit · Skill · 10,926 stars

  Audit recent changes to Phoenix's user-facing surfaces (Python clients, TypeScript clients, CLI, REST/GraphQL APIs) and patch the three external-facing age

• phoenix-sqlean · Skill · 10,926 stars

  Maintaining packages/phoenix-sqlean, the vendored fork of nalgeon/sqlean.py published as arize-phoenix-sqlean. Use when bumping the bundled SQLite, sqlean,

• phoenix-tracing · Skill · 10,926 stars

  OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying

• phoenix-typescript · Skill · 10,926 stars

  TypeScript conventions and patterns for any TypeScript code in the Phoenix monorepo — including js/packages/, js/app/, and any other TS directories. Use th

• phoenix-typescript-package-docs · Skill · 10,926 stars

  Maintain the bundled TypeScript package docs that ship inside Phoenix npm packages. Use this skill whenever adding or updating docs for `@arizeai/phoenix-c

• playground · Skill · 10,926 stars

  Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset. Load before any playground `ui.*` opera

• prompts · Collection · 10,926 stars
• pxi-eval-dataset · Skill · 10,926 stars

  Generate synthetic evaluation datasets for the PXI eval harness (evals/pxi/). Use whenever the user asks to create, author, draft, expand, or audit an eval

• server · Collection · 10,926 stars
• skills · Collection · 10,926 stars
• skills · Collection · 10,926 stars
• skills · Collection · 10,926 stars
• skills · Collection · 10,926 stars
• skills · Collection · 10,926 stars
• span-coding · Skill · 10,926 stars

  Open-code Phoenix spans with PXI-owned notes, recover those notes for axial coding, and promote stable categories into structured annotations. Load this wh

• src · Collection · 10,926 stars
• typescript-tooling-migration · Skill · 10,926 stars

  Migrate or upgrade TypeScript tooling in the Phoenix monorepo. Use when upgrading TypeScript versions, switching tools (ESLint to oxlint, Prettier to oxfmt

• vercel-react-best-practices · Skill · 10,926 stars

  React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next

• arize-admin · Skill · 41 stars

  Manages Arize users, organizations, spaces, projects, roles, role bindings, resource restrictions, and API keys via the ax CLI. Use for enterprise admin wo

• arize-ai-provider-integration · Skill · 41 stars

  Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LL

• arize-annotation · Skill · 41 stars

  Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Applies h

• arize-compliance-audit · Skill · 41 stars

  INVOKE THIS SKILL when auditing an AI agent or LLM app for regulatory compliance. Covers EU AI Act, GPAI Code of Practice, GDPR, NIST AI RMF, Colorado AI A

• arize-dataset · Skill · 41 stars

  Creates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using t

• arize-evaluator · Skill · 41 stars

  Handles LLM-as-judge and code evaluator workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing ta

• arize-experiment · Skill · 41 stars

  Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, an

• arize-instrumentation · Skill · 41 stars

  Adds Arize AX tracing to an LLM application for the first time. Detects the stack, routes to the single matching integration doc, wires auto-instrumentatio

• arize-instrumentation-health · Skill · 41 stars

  Audits instrumentation health of existing Arize traces. Runs deterministic checks over a bounded span sample (orphaned/uncategorized/duplicate spans, flat

• arize-link · Skill · 41 stars

  Generates deep links to the Arize UI for projects, traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs. Discovers organi

• arize-prompt-optimization · Skill · 41 stars

  Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance sig

• arize-prompts · Skill · 41 stars

  INVOKE THIS SKILL for Arize Prompt Hub and `ax prompts` workflows: author or import templates and save (Workflows A–B), label/promote (C), or list/get/edit

• arize-skills · Collection · 41 stars
• arize-span-routing · Skill · 41 stars

  Use when one Python service must send each agent's, tenant's, team's, or request's spans to its correct Arize space and project using application metadata.

• arize-trace · Skill · 41 stars

  Downloads, exports, and inspects existing Arize traces and spans to understand what an LLM app is doing or debug runtime issues. Covers exporting traces by

• skills · Collection · 41 stars
• general · Collection
• mcp · Collection
• phoenix-harbor · Skill

  Configure and interpret the Phoenix plugin for Harbor agent evaluations. Use when adding `arize-phoenix` to Harbor jobs, choosing ATIF tracing, mapping Har

• project-overview · Skill

  Get oriented in a Phoenix project before answering questions about it: which projects exist, how much traffic each carries, and where the errors and latenc

• skills · Collection

Browse the @skills marketplace