phoenix
Skills, agents and an MCP server for Phoenix, an AI observability tool. Helps build evaluators, run dataset experiments, manage prompts in the playground and query the Phoenix API.
10 skills12k
@arize-ai- 12,281Stars earned
- 1Plugin
- 10Skills
- 21Agents
- 1MCP server
Plugins
1@arize-aiSkills
10datasets
Understand what a Phoenix dataset is and reason well about its examples, outputs, splits, and how it feeds evaluators and…
@arize-aievaluators
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…
@arize-aiexperiments
Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving. Trigger when the user…
@arize-aiphoenix-cli
Debug LLM applications using the Phoenix CLI (`px`, from @arizeai/phoenix-cli). Fetch traces, spans, and sessions, annotate them,…
@arize-aiphoenix-error-analysis
Find out what is going wrong in LLM or agent traffic by reading sampled Phoenix traces, spans, or sessions, writing free-form…
@arize-aiphoenix-evals
Build, run, and validate evaluators for AI/LLM applications with Phoenix, in Python or TypeScript (including Vercel AI SDK apps)…
@arize-aiphoenix-graphql
Write efficient GraphQL queries against the Phoenix API. Load this skill in two cases: (1) before composing any non-trivial…
@arize-aiphoenix-harbor
Configure and interpret the Phoenix plugin for Harbor agent evaluations. Use when adding `arize-phoenix` to Harbor jobs, choosing…
@arize-aiphoenix-tracing
OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating…
@arize-aiplayground
Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset. Load before…
@arize-aiAgents
21annotations
AgentAnnotations are named labels/scores attached to spans, traces, sessions, or experiment runs by humans, code, or LLM judges. A…
@arize-aibug-fixer
AgentLeads one Phoenix bug from report to draft PR - reproduce, fix, review, revise.
@arize-aibug-reproducer
AgentReproduces a reported Phoenix bug before any fix exists, then verifies the fix independently of the agent that wrote it. Give it…
@arize-aicloud-triage
AgentReads a day of Phoenix Cloud production errors from Datadog, decides which are bugs a maintainer should fix, and makes sure each…
@arize-aidatasets
AgentThere is **no `getDatasetByName`** — fetch via `node(id:) { ... on Dataset { ... } }` or the `datasets(filter: DatasetFilter,…
@arize-aidocs-reviewer
AgentRead-only reviewer for Phoenix documentation changes - the Mintlify pages under docs/, docs.json and docs/phoenix/llms.txt. Give…
@arize-aidocs-writer
AgentMakes one Phoenix documentation change, grounded in the current code, and opens a draft PR.
@arize-aiexperiments
AgentAn experiment is one run of a prompt or pipeline over every example in a dataset.
@arize-aifeature-analyst
AgentAnalyst that turns a Phoenix feature request into an implementation plan grounded in the existing code, starting with an…
@arize-aifeature-builder
AgentLeads one Phoenix feature from request to draft PR - analyze, implement, review, revise.
@arize-aifilter-expressions
AgentA filter condition is a Python boolean expression that Phoenix compiles to SQL. There are three filter languages, one each for…
@arize-aifrontend-reviewer
AgentRead-only reviewer for Phoenix frontend changes in js/app/ - React, Relay, design system, stories. Give it the changed paths and…
@arize-aiIs this you? Claim your profilePut a plugin at the top of Plugins, from $9