phoenix

Open-source AI observability platform for tracing, evaluating, and improving LLM applications with OpenTelemetry integration

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

Design system conventions for the Phoenix frontend — layout, dialogs, error display, BEM CSS class naming, and CSS design tokens. Use when building UI, naming CSS classes, creating or consuming tokens, handling errors, or designing dialog interactions in app/src/.

Frontend development guidelines for the Phoenix AI observability platform. Use when writing, reviewing, or modifying React components, TypeScript code, styles, or UI features in the app/ directory. Triggers on any frontend task — new components, UI changes, styling, accessibility fixes, form handling, or component refactoring. Also use when the user asks about frontend conventions or component patterns for this project. For design system rules (error display, layout, dialogs, tokens), use the phoenix-design skill.

Write Playwright E2E tests for the Phoenix AI observability platform. Use when creating, updating, or debugging Playwright tests, or when the user asks about testing UI features, writing E2E tests, or automating browser interactions for Phoenix.

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

Development guide for the @arizeai/phoenix-client TypeScript SDK — run and resume experiments, manage OpenTelemetry tracer providers with stack-based attach/detach, and write vitest unit and integration tests. Use when adding features to phoenix-client, debugging experiment lifecycle or provider cleanup, modifying dataset/prompt/session/span APIs, or writing tests for the js/packages/phoenix-client/ directory.

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 analysis (via the `phoenix-gql` bash command) — it contains schema entrypoints and patterns that eliminate the need for introspection; (2) when the user asks for help writing GraphQL queries for their own scripts, tools, or integrations against Phoenix — it covers the endpoint, authentication, and client examples.

Diagnose failure modes by systematically investigating traces. Trigger when the user explicitly asks for cross-trace diagnosis: "what's going wrong?", "were there errors?", "debug this", "where is my agent struggling?". Do NOT trigger on: (1) advice questions ("what should I do?"), (2) statistical questions ("what's the average latency?"), (3) summarize requests, (4) trace filtering ("show me traces with errors"), (5) vague questions ("is there a problem?"), (6) unrelated requests.

Create Phoenix release documentation grounded in actual code changes. Use this skill whenever the user asks to write release notes, document a release, update release documentation, or mentions undocumented releases. Also trigger when the user wants to update GitHub release descriptions, add entries to the release notes page, or asks what changed in a recent Phoenix version.

TypeScript conventions and patterns for any TypeScript code in the Phoenix monorepo — including js/packages/, app/, and any other TS directories. Use this skill whenever writing, reviewing, or modifying TypeScript code — new functions, types, exports, tests, or refactors. Also trigger when the user asks about TS patterns, naming conventions, or best practices for this project.

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 an existing one's logic or rubric, choose labels, or decide what to measure on a dataset or experiment. Do NOT trigger on: (1) manual prompt drafting (use `playground`), (2) running or comparing experiments themselves (use `experiments`), (3) cross-trace failure diagnosis with no evaluator in scope (use `debug-trace`).

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 dataset with experiments, compare experiment runs, read experiment quality/latency/cost, or decide whether a change actually helped. Running a prompt over a dataset is implicitly an experiment — load this skill when dataset-backed work begins, before authoring evaluators for the experiment and before starting the recorded run, not only when reading results. Do NOT trigger on: (1) manual prompt drafting with no dataset-backed evaluation in scope (use `playground`), (2) authoring or refining an evaluator's logic or rubric (use `evaluators`), (3) cross-trace failure diagnosis with no experiment in scope (use `debug-trace`).

Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset. Load before any playground tool call, including single-shot prompt rewrites.

Maintain the bundled TypeScript package docs that ship inside Phoenix npm packages. Use this skill whenever adding or updating docs for `@arizeai/phoenix-client`, `@arizeai/phoenix-evals`, or `@arizeai/phoenix-otel`, when changing the Mintlify package-doc pages, when keeping `node_modules/.../docs` content aligned with actual exports, or when modifying the sync and publish flow for packaged docs.

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 dataset is in view or the user asks what a dataset is, how splits work, what an output "means", or how datasets relate to experiments and evals. This skill governs the judgment; any tool descriptions govern the mechanics.

Write effective, consistent annotations on LLM/agent spans and traces, and coach the user on annotation practice. Load this whenever you are about to record structured feedback with the `batch_span_annotate` tool, or when the user asks how to annotate, label, score, or review spans/traces, build a failure taxonomy, or set up human/LLM review. Do NOT load for: pure analysis with no intent to save feedback (use debug-trace), latency or cost statistics, or prompt authoring (use playground).

Manage GitHub issues, labels, and project boards for the Arize-ai/phoenix repository. Use when filing roadmap issues, triaging bugs, applying labels, managing the Phoenix roadmap project board, or querying issue/project state via the GitHub CLI.

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 use, persisting PXI test runs as Phoenix experiments, or debugging PXI E2E failures.

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.

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 dataset for a PXI tool, skill, or behavior — including phrases like "write evals for <tool>", "test PXI behavior", "synthetic dataset for PXI", "cover this tool with eval examples", or "find gaps in our PXI eval coverage". Inspects whichever evaluators currently live under evals/pxi/evaluators/ at use time and pauses to recommend a new evaluator if the behavior under test can't be scored by what already exists.

Backend development guide for the Phoenix AI observability platform (Strawberry GraphQL, SQLAlchemy async, FastAPI). Use this skill when writing or modifying Python server code in the phoenix repo — adding mutations, types, migrations, or tests. Trigger on any backend task touching src/phoenix/server/, src/phoenix/db/, or tests/unit/server/.

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

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. Use this skill whenever adding, auditing, or reorganizing llms.txt entries. Trigger when the user mentions llms.txt, docs index, px docs, or LLM-friendly documentation.

Bump the next release-please version for a Phoenix Python package (arize-phoenix, arize-phoenix-client, arize-phoenix-evals, arize-phoenix-otel) by opening a PR with a Release-As commit footer. Use this skill when the user asks to "set the release-please version", "force a 2.0.0 release", "release X as Y", "skip a version", or otherwise wants release-please to propose a specific version on its next run instead of the version it would pick from conventional commits.

Audit recent changes to Phoenix's user-facing surfaces (Python clients, TypeScript clients, CLI, REST/GraphQL APIs) and patch the three external-facing agent skills — `phoenix-tracing`, `phoenix-cli`, and `phoenix-evals` — so they stay in sync with what actually shipped. Use this skill whenever a user asks to update those skills, sync the skills with recent changes, audit skill drift, check what client/CLI/API changes need to land in the skills, or mentions "skill freshness", "skill drift", "stale skills", or "are the skills up to date". Also trigger when shipping a notable client/CLI/API change and the user asks "do the skills need updating?". Default window is the last 7 days on `origin/main`; user may override.

Design and implementation guide for the Phoenix CLI (`px`). Covers the noun-verb command structure, dual-audience design (humans and coding agents), Commander.js patterns, configuration resolution, output formats, exit codes, and conventions for adding or modifying commands. Triggers when working on phoenix-cli commands — adding new commands, modifying existing ones, refactoring command structure, or reviewing CLI code. Also triggers on mentions of `px` commands, CLI design, or adding a new resource to the CLI.

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 undocumented features, identify docs gaps, audit what shipped without docs, check which recent changes need documentation, review stale docs against current code, or mentions "documentation debt", "doc coverage", "undocumented APIs", or "what's missing from /docs". Also trigger on requests like "what from last week needs docs", "find stale READMEs", or "check docstring coverage for recent changes". Covers /docs (Mintlify), package READMEs, package-level built-in docs (Sphinx, TypeDoc), Python docstrings, TSDoc, and code comments.

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 screenshots, uploads to GCS, and updates the PR body.

Generates onboarding code snippets for Phoenix tracing integrations and wires them into the project onboarding UI. Produces install dependencies and implementation sections for SDKs like OpenAI, LangChain, Vercel AI SDK, and others. Supports Python and TypeScript. Use when asked to create onboarding code, tracing setup snippets, quickstart examples, or getting-started code for a framework integration.

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

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 builtin evaluator, create an LLM-as-a-judge metric, or add a new classification evaluator to Phoenix.

Migrate or upgrade TypeScript tooling in the Phoenix monorepo. Use when upgrading TypeScript versions, switching tools (ESLint to oxlint, Prettier to oxfmt), upgrading bundlers (Vite, esbuild), or making major dependency upgrades. Triggers on requests to migrate, upgrade, or replace TypeScript/JavaScript tooling.

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

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.