prompts
There is **no `getPromptByName`** — fetch via `node(id:)` or the `prompts(filter: PromptFilter, labelIds)` 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 `getPromptByName`** — fetch via `node(id:)` or the `prompts(filter: PromptFilter, labelIds)` connection.
Agent definition
prompts.mdPrompt, PromptVersion
Reaching a prompt
There is **no `getPromptByName`** — fetch via `node(id:)` or the `prompts(filter: PromptFilter, labelIds)` connection.
Prompt fields
- `name`, `description`, `metadata`
- `version(versionId: GlobalID, tagName: Identifier)` → `PromptVersion` — **call with no args to get the latest version**; pass `versionId` or `tagName` to pin one.
- `promptVersions(first, after)` → `PromptVersionConnection`
- `versionTags`, `labels`
PromptVersion fields
- `modelName`, `modelProvider`
- `templateType`, `templateFormat`
- `template` — union `PromptStringTemplate | PromptChatTemplate`. Chat templates expose `messages { role content { ... } }`; string templates expose `template`.
- `invocationParameters`, `tools`, `responseFormat`
- `tags`, `isLatest`, `sequenceNumber`, `previousVersion`
Example
query LatestPrompt($id: ID!) {
node(id: $id) {
... on Prompt {
name
version {
modelName
modelProvider
template {
... on PromptChatTemplate { messages { role } }
... on PromptStringTemplate { template }
}
}
}
}
}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 - datasets
There is **no `getDatasetByName`** — fetch via `node(id:) { ... on Dataset { ... } }` or the `datasets(filter: DatasetFilter, sort)` connection.
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 - sessions
A session groups the traces of one multi-turn conversation.
Open agent

