datasets
There is **no `getDatasetByName`** — fetch via `node(id:) { ... on Dataset { ... } }` or the `datasets(filter: DatasetFilter, sort)` connection.
$ npx -y skills add arize-ai/phoenix --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
There is **no `getDatasetByName`** — fetch via `node(id:) { ... on Dataset { ... } }` or the `datasets(filter: DatasetFilter, sort)` connection.
Agent definition
datasets.mdDataset, DatasetExample
Reaching a dataset
There is **no `getDatasetByName`** — fetch via `node(id:) { ... on Dataset { ... } }` or the `datasets(filter: DatasetFilter, sort)` connection.
Dataset fields
- `name`, `description`, `metadata`
- `exampleCount(datasetVersionId)`
- `examples(datasetVersionId, splitIds, first, after, filter: String, filterIds)` → `DatasetExampleConnection`
- `versions(first, after, sort)` → `DatasetVersionConnection`
- `splits`, `labels`
- `experiments(first, after, filterCondition, filterIds)`, `experimentCount`
Gotchas:
- **The version argument is `datasetVersionId` everywhere** (not `versionId`); omit it to get the latest version.
- `examples` has two distinct filter args: `filter: String` (free-text search over input/output/metadata) and `filterIds: [GlobalID!]` (membership lookup).
- `experiments` uses `filterCondition: String` (not `filter`).
DatasetExample fields
- `externalId`
- `revision(datasetVersionId) { input output metadata revisionKind }` — `input`/`output`/`metadata` are `JSON`; `revisionKind` is `CREATE`/`PATCH`/`DELETE`.
- `span`
- `datasetSplits`
- `experimentRuns(experimentIds, first, after)`
Example
query DatasetExamples($id: ID!, $first: Int = 20) {
node(id: $id) {
... on Dataset {
name
exampleCount
examples(first: $first) {
edges { node { id externalId revision { input output metadata } } }
pageInfo { hasNextPage endCursor }
}
}
}
}Read more
Dataset, DatasetExample
Reaching a dataset
There is **no `getDatasetByName`** — fetch via `node(id:) { ... on Dataset { ... } }` or the `datasets(filter: DatasetFilter, sort)` connection.
Dataset fields
- `name`, `description`, `metadata`
- `exampleCount(datasetVersionId)`
- `examples(datasetVersionId, splitIds, first, after, filter: String, filterIds)` → `DatasetExampleConnection`
- `versions(first, after, sort)` → `DatasetVersionConnection`
- `splits`, `labels`
- `experiments(first, after, filterCondition, filterIds)`, `experimentCount`
Gotchas:
- **The version argument is `datasetVersionId` everywhere** (not `versionId`); omit it to get the latest version.
- `examples` has two distinct filter args: `filter: String` (free-text search over input/output/metadata) and `filterIds: [GlobalID!]` (membership lookup).
- `experiments` uses `filterCondition: String` (not `filter`).
DatasetExample fields
- `externalId`
- `revision(datasetVersionId) { input output metadata revisionKind }` — `input`/`output`/`metadata` are `JSON`; `revisionKind` is `CREATE`/`PATCH`/`DELETE`.
- `span`
- `datasetSplits`
- `experimentRuns(experimentIds, first, after)`
Example
query DatasetExamples($id: ID!, $first: Int = 20) {
node(id: $id) {
... on Dataset {
name
exampleCount
examples(first: $first) {
edges { node { id externalId revision { input output metadata } } }
pageInfo { hasNextPage endCursor }
}
}
}
}Repo: arize-ai/phoenix
Other agents on phoenix.
- VENDOR
- Upstream: https://github.com/DougTrajano/pydantic-ai-skills - Original version: 0.10.1 (SHA `d1a19c8e6dbbee5e6726c8de70aadca2966fb190`) - Vendored: 2026-05-19 - License: MIT — preserved verbatim in [LICENSE](./LICENSE)
Open agent - annotations
Annotations are named labels/scores attached to spans, traces, or experiment runs by humans, code, or LLM judges.
Open agent - experiments
An experiment is one run of a prompt or pipeline over every example in a dataset.
Open agent - project-spans-traces
- `Project.spans(timeRange, first, after, sort: SpanSort, rootSpansOnly: Boolean, filterCondition: String)` → connection of `Span`. There is **no `traces` connection on `Project`** — use `spans(rootSpansOnly: true)` for root spans, which is usually one per trace though nothing
Open agent - prompts
There is **no `getPromptByName`** — fetch via `node(id:)` or the `prompts(filter: PromptFilter, labelIds)` connection.
Open agent - sessions
A session groups the traces of one multi-turn conversation.
Open agent

