How do I install the Phoenix CLI skill?

Run npx skillmds@latest add paulasilvatech/phoenix-cli in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Phoenix CLI skill do?

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 when 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. It is listed under AI & ML on SkillMD.

Is Phoenix CLI safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Phoenix CLI?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Phoenix CLI free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Apache-2.

Who published Phoenix CLI?

paulasilvatech (@paulasilvatech) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Phoenix CLI by paulasilvatech — Agent Skill

Name: Phoenix CLI
Author: paulasilvatech

Phoenix CLI

Use the Phoenix CLI (px or npx @arizeai/phoenix-cli) to inspect traces, spans, sessions, datasets, experiments, prompts, annotation configs, profiles, and GraphQL data, then turn LLM application traffic into notes, taxonomies, eval targets, and concrete debugging evidence.

When to invoke

"What is going wrong in these Phoenix traces?"
"Fetch recent LLM spans and analyze the errors."
"Use open coding and axial coding on this agent traffic."
"Inspect Phoenix datasets, experiments, or prompts."
"Query Phoenix annotation configs or GraphQL."

Prerequisites and context

Use px <resource> <action> when installed globally, or npx @arizeai/phoenix-cli <resource> <action> when no install is available.
Set PHOENIX_HOST, PHOENIX_PROJECT, and PHOENIX_API_KEY when the Phoenix instance requires them.
Use --format raw --no-progress whenever output is piped to jq.
Use singular resource commands with list, get, annotate, and add-note subcommands.

Invocation

px <resource> <action>                          # if installed globally
npx @arizeai/phoenix-cli <resource> <action>    # no install required

The CLI uses singular resource commands with subcommands like list and get:

px trace list
px trace get <trace-id>
px trace annotate <trace-id>
px trace add-note <trace-id>
px trace-annotations delete
px span list
px span annotate <span-id>
px span add-note <span-id>
px span-annotations delete
px session list
px session get <session-id>
px session annotate <session-id>
px session add-note <session-id>
px session-annotations delete
px dataset list
px dataset get <name>
px project list
px project get <name>
px annotation-config list
px auth status
px profile list
px profile show [name]
px profile create <name>
px profile use <name>
px profile edit <name>
px profile delete <name>

Setup

export PHOENIX_HOST=http://localhost:6006
export PHOENIX_PROJECT=my-project
export PHOENIX_API_KEY=your-api-key  # if auth is enabled

Always use --format raw --no-progress when piping to jq.

Progressive disclosure and bundled resources

Read bundled references only when the workflow needs them.

references/open-coding.md: free-form notes against sampled traces, spans, or sessions; includes the unit-of-analysis diagnostic and .px/coding/<sanitized-identifier>.jsonl sidecar rules.
references/axial-coding.md: MECE taxonomy grouping, counts, eval-target selection, and .px/coding/<sanitized-identifier>-axial.jsonl handoff rules.

Quick reference

Task	Files
Look at sampled traces, spans, or sessions and write specific notes about what went wrong (no taxonomy yet)	references/open-coding
Group those notes into a structured failure taxonomy and quantify what matters	references/axial-coding

Both stages tag every artifact with one shared coding annotation identifier (descriptive shape, e.g. coding-run:chatbot-context-loss-2026-05-06) so the run is queryable, reversible, and viewable as a unit. Pass --identifier <value> explicitly on every px call — shell inheritance is unreliable across agent harnesses. Open coding writes notes via px ... add-note and records a small local JSONL sidecar at .px/coding/<sanitized-identifier>.jsonl; axial coding reads that sidecar as the deterministic handoff and records labels in .px/coding/<sanitized-identifier>-axial.jsonl. Pick the identifier once per run (see references/open-coding.md), then share the Phoenix UI link from the wrap-up section. Revert is opt-in and runs three identifier-bound DELETEs only after explicit user confirmation.

Workflow term vs. server annotation name. The skill prose calls this value the coding annotation identifier (shell-variable hint: CODING_ANNOTATION_IDENTIFIER). The server-side annotation NAME used for the UI filter is unchanged — coding_session_id — for data compatibility with rows already written by previous runs. Don't try to rename the server-side annotation; treat the asymmetry as load-bearing.

Procedure

Confirm the Phoenix target through CLI flags, environment variables, or the active profile; remember priority is CLI flags > env vars > active profile > built-in defaults.
Use px auth status before deep analysis when connection or authentication is uncertain.
Fetch the smallest entity set that answers the question: traces for whole interactions, sessions for multi-turn agent behavior, spans for mechanical failures, datasets/experiments/prompts for eval assets.
For qualitative analysis, pick one CODING_ANNOTATION_IDENTIFIER, pass --identifier <value> on every annotation or note command, then run open coding before axial coding.
Use --format raw --no-progress with jq for deterministic filtering and report the Phoenix UI link or exact blocker.

Workflows

"What do I do after instrumenting?" / "Where do I focus?" / "What's going wrong?" open-coding → axial-coding → build evals for the top categories.

Reference Categories

Prefix	Description
`references/open-coding`	Free-form notes against sampled traces, spans, or sessions — reach for it whenever the user wants to make sense of LLM traffic but has no failure categories yet. Includes a unit-of-analysis diagnostic so the workflow runs at the level the failure modes actually live at (trace for stateless single-shot calls, session for multi-turn agents, span for mechanical/in-isolation failures).
`references/axial-coding`	Inductive grouping of notes into a MECE taxonomy with counts — reach for it whenever the user has observations and needs categories or eval targets

Auth

px auth status                                # check connection and authentication
px auth status --endpoint http://other:6006   # check a specific endpoint
px auth status --profile staging              # check a named profile's connection

Profiles

Named profiles let you switch between multiple Phoenix instances (local, staging, cloud) without juggling environment variables. Profiles are stored in ~/.px/settings.json (or $XDG_CONFIG_HOME/px/settings.json).

Configuration priority (highest to lowest): CLI flags > env vars > active profile > built-in defaults.

px profile list                              # list all profiles (shows active profile)
px profile show                              # show the active profile's settings
px profile show staging                      # show a named profile's settings
px profile create prod --endpoint https://app.phoenix.arize.com --api-key <key> --activate
px profile create local --endpoint http://localhost:6006 --project my-app
px profile use prod                          # switch the active profile
px profile edit prod                         # open profile JSON in $EDITOR (validates on save)
px profile delete prod --yes                 # delete a profile (--yes skips confirmation)

Use --profile <name> on any command to target a specific profile without changing the active one:

px trace list --profile staging --limit 10 --format raw --no-progress | jq .
px auth status --profile prod

px profile create options: --endpoint <url>, --project <name>, --api-key <key>, --header <key=value> (repeatable), --activate.

Projects

px project list                                            # list all projects (table view)
px project list --format raw --no-progress | jq '.[].name' # project names as JSON
px project get my-project --format raw --no-progress       # single record by exact name
px project get my-project --format raw --no-progress | jq -r '.id'  # extract project id

project get exits with ExitCode.FAILURE (1) on a name miss and writes a StructuredError {error, code: "FAILURE", hint} to stderr in --format json|raw.

Traces

px trace list --limit 20 --format raw --no-progress | jq .
px trace list --last-n-minutes 60 --limit 20 --format raw --no-progress | jq '.[] | select(.status == "ERROR")'
px trace list --since 2025-01-15T00:00:00Z --limit 50 --format raw --no-progress | jq .
px trace list --format raw --no-progress | jq 'sort_by(-.duration) | .[0:5]'
px trace list --include-notes --format raw --no-progress | jq '.[].notes'
px trace get <trace-id> --format raw | jq .
px trace get <trace-id> --format raw | jq '.spans[] | select(.status_code != "OK")'
px trace get <trace-id> --include-notes --format raw | jq '.notes'
px trace annotate <trace-id> --name reviewer --label pass
px trace annotate <trace-id> --name reviewer --score 0.9 --format raw --no-progress
px trace annotate <trace-id> --name reviewer --label pass --identifier "<coding-annotation-id>"  # tag with a coding annotation identifier
px trace add-note <trace-id> --text "needs follow-up"
px trace add-note <trace-id> --text "needs follow-up" --identifier "<coding-annotation-id>"  # tag + upsert on identifier
px trace-annotations delete --identifier "<coding-annotation-id>" --all -y            # nuke every annotation tied to this coding annotation identifier

px <entity>-annotations delete requires --all or both --start-time and --end-time and emits {deleted: true, target, filter} on success.

Trace JSON shape

Trace
  traceId, status ("OK"|"ERROR"), duration (ms), startTime, endTime
  annotations[] (with --include-annotations, excludes note)
    name, result { score, label, explanation }
  notes[] (with --include-notes)
    name="note", result { explanation }
  rootSpan  — top-level span (parent_id: null)
  spans[]
    name, span_kind ("LLM"|"CHAIN"|"TOOL"|"RETRIEVER"|"EMBEDDING"|"AGENT"|"RERANKER"|"GUARDRAIL"|"EVALUATOR"|"UNKNOWN")
    status_code ("OK"|"ERROR"|"UNSET"), parent_id, context.span_id
    notes[] (with --include-notes)
      name="note", result { explanation }
    attributes
      input.value, output.value          — raw input/output
      llm.model_name, llm.provider
      llm.token_count.prompt/completion/total
      llm.token_count.prompt_details.cache_read
      llm.token_count.completion_details.reasoning
      llm.input_messages.{N}.message.role/content
      llm.output_messages.{N}.message.role/content
      llm.invocation_parameters          — JSON string (temperature, etc.)
      exception.message                  — set if span errored

Spans

px span list --limit 20                                    # recent spans (table view)
px span list --last-n-minutes 60 --limit 50                # spans from last hour
px span list --since 2025-01-15T00:00:00Z --limit 50       # spans since a timestamp
px span list --span-kind LLM --limit 10                    # only LLM spans
px span list --status-code ERROR --limit 20                # only errored spans
px span list --name chat_completion --limit 10             # filter by span name
px span list --trace-id <id> --format raw --no-progress | jq .   # all spans for a trace
px span list --parent-id null --limit 10                   # only root spans
px span list --parent-id <span-id> --limit 10              # only children of a span
px span list --include-annotations --limit 10              # include annotation scores
px span list --include-notes --limit 10                    # include span notes
px span list --attribute llm.model_name:gpt-4 --limit 10  # filter by string attribute
px span list --attribute llm.token_count.total:500 --limit 10  # filter by numeric attribute
px span list --attribute 'user.id:"12345"' --limit 10     # force string match for numeric-looking value
px span list --attribute session.id:sess:abc:123 --limit 20  # colon in value OK (split on first colon only)
px span list --attribute llm.model_name:gpt-4 --attribute session.id:abc --limit 10  # AND multiple filters
px span list output.json --limit 100                       # save to JSON file
px span list --format raw --no-progress | jq '.[] | select(.status_code == "ERROR")'
px span annotate <span-id> --name reviewer --label pass
px span annotate <span-id> --name checker --score 1 --annotator-kind CODE
px span annotate <span-id> --name reviewer --label pass --identifier "<coding-annotation-id>"  # tag with a coding annotation identifier
px span add-note <span-id> --text "verified by agent"
px span add-note <span-id> --text "verified by agent" --identifier "<coding-annotation-id>"  # tag + upsert on identifier
px span-annotations delete --identifier "<coding-annotation-id>" --all -y           # nuke every annotation tied to this coding annotation identifier

Span JSON shape

Span
  name, span_kind ("LLM"|"CHAIN"|"TOOL"|"RETRIEVER"|"EMBEDDING"|"AGENT"|"RERANKER"|"GUARDRAIL"|"EVALUATOR"|"UNKNOWN")
  status_code ("OK"|"ERROR"|"UNSET"), status_message
  context.span_id, context.trace_id, parent_id
  start_time, end_time
  attributes
    input.value, output.value          — raw input/output
    llm.model_name, llm.provider
    llm.token_count.prompt/completion/total
    llm.input_messages.{N}.message.role/content
    llm.output_messages.{N}.message.role/content
    llm.invocation_parameters          — JSON string (temperature, etc.)
    exception.message                  — set if span errored
  annotations[] (with --include-annotations, excludes note)
    name, result { score, label, explanation }
  notes[] (with --include-notes)
    name="note", result { explanation }

Sessions

px session list --limit 10 --format raw --no-progress | jq .
px session list --order asc --format raw --no-progress | jq '.[].session_id'
px session list --include-annotations --include-notes --format raw --no-progress | jq '.[].notes'
px session get <session-id> --format raw | jq .
px session get <session-id> --include-annotations --format raw | jq '.session.annotations'
px session get <session-id> --include-notes --format raw | jq '.session.notes'
px session annotate <session-id> --name reviewer --label pass
px session annotate <session-id> --name reviewer --score 0.9 --format raw --no-progress
px session annotate <session-id> --name reviewer --label pass --identifier "<coding-annotation-id>"  # tag with a coding annotation identifier
px session add-note <session-id> --text "verified by agent"
px session add-note <session-id> --text "verified by agent" --identifier "<coding-annotation-id>"  # tag + upsert on identifier
px session-annotations delete --identifier "<coding-annotation-id>" --all -y              # nuke every annotation tied to this coding annotation identifier

Session JSON shape

SessionData
  id, session_id, project_id
  start_time, end_time
  token_count_prompt, token_count_completion, token_count_total  — cumulative across all LLM spans in the session (int, default 0)
  annotations[] (with --include-annotations, excludes note)
    name, result { score, label, explanation }
  notes[] (with --include-notes)
    name="note", result { explanation }
  traces[]
    id, trace_id, start_time, end_time

Datasets / Experiments / Prompts

px dataset list --format raw --no-progress | jq '.[].name'
px dataset get <name> --format raw | jq '.examples[] | {input, output: .expected_output}'
px dataset get <name> --split train --format raw | jq .    # filter by split
px dataset get <name> --version <version-id> --format raw | jq .
px experiment list --dataset <name> --format raw --no-progress | jq '.[] | {id, name, failed_run_count}'
px experiment get <id> --format raw --no-progress | jq '.[] | select(.error != null) | {input, error}'
px prompt list --format raw --no-progress | jq '.[].name'
px prompt get <name> --format text --no-progress   # plain text, ideal for piping to AI

Annotation Configs

px annotation-config list                                           # list all configs (table view)
px annotation-config list --format raw --no-progress | jq '.[].name' # config names as JSON

GraphQL

For ad-hoc queries not covered by the commands above. Output is {"data": {...}}.

px api graphql '{ projectCount datasetCount promptCount evaluatorCount }'
px api graphql '{ projects { edges { node { name traceCount tokenCountTotal } } } }' | jq '.data.projects.edges[].node'
px api graphql '{ datasets { edges { node { name exampleCount experimentCount } } } }' | jq '.data.datasets.edges[].node'
px api graphql '{ evaluators { edges { node { name kind } } } }' | jq '.data.evaluators.edges[].node'

 # Introspect any type
px api graphql '{ __type(name: "Project") { fields { name type { name } } } }' | jq '.data.__type.fields[]'

Key root fields: projects, datasets, prompts, evaluators, projectCount, datasetCount, promptCount, evaluatorCount, viewer.

Docs

Download Phoenix documentation markdown for local use by coding agents.

px docs fetch                                # fetch default workflow docs to .px/docs
px docs fetch --workflow tracing             # fetch only tracing docs
px docs fetch --workflow tracing --workflow evaluation
px docs fetch --dry-run                      # preview what would be downloaded
px docs fetch --refresh                      # clear .px/docs and re-download
px docs fetch --output-dir ./my-docs         # custom output directory

Key options: --workflow (repeatable, values: tracing, evaluation, datasets, prompts, integrations, sdk, self-hosting, all), --dry-run, --refresh, --output-dir (default .px/docs), --workers (default 10).

Output template

## Phoenix CLI analysis

**Status:** complete | blocked
**Target:** `<profile | PHOENIX_HOST | endpoint>`
**Project:** `<PHOENIX_PROJECT or selected project>`
**Commands run:**
- `px auth status`
- `<px command with --format raw --no-progress>`

| Artifact | Filter | Count | Evidence |
| --- | --- | ---: | --- |
| Traces | `<filter>` | <count> | `<trace-id>` |
| Spans | `<filter>` | <count> | `<span-id>` |
| Sessions | `<filter>` | <count> | `<session-id>` |
| Datasets/experiments/prompts | `<filter>` | <count> | `<name or id>` |

### Findings
- <finding with trace/span/session evidence>

### Coding run
**Identifier:** `<coding-run:...>`
**Sidecars:** `.px/coding/<sanitized-identifier>.jsonl`, `.px/coding/<sanitized-identifier>-axial.jsonl`
**Next eval targets:** <top categories or none>

Quality gate

Connection and authentication were checked or the blocker is explicit.
Commands use singular resources such as trace, span, session, dataset, project, annotation-config, profile, and auth.
Piped JSON commands include --format raw --no-progress.
Trace, span, and session findings cite IDs and relevant fields such as status_code, exception.message, input.value, output.value, token counts, or notes.
Open coding precedes axial coding when the user has no taxonomy yet.
Every annotation or note in a coding run uses the same --identifier <coding-annotation-id> and preserves coding_session_id as the server-side annotation name.
Revert commands using px <entity>-annotations delete --identifier <coding-annotation-id> --all -y run only after explicit user confirmation.
Sidecar files under .px/coding/ are reported when created or consumed.

References

Phoenix application

Phoenix CLI

File contents

Phoenix CLI

When to invoke

Prerequisites and context

Invocation

Setup

Progressive disclosure and bundled resources

Quick reference

Procedure

Workflows

Reference Categories

Auth

Profiles

Projects

Traces

Trace JSON shape

Spans

Span JSON shape

Sessions

Session JSON shape

Datasets / Experiments / Prompts

Annotation Configs

GraphQL

Docs

Output template

Quality gate

References

Frequently asked questions

Phoenix CLI

File contents

Phoenix CLI

When to invoke

Prerequisites and context

Invocation

Setup

Progressive disclosure and bundled resources

Quick reference

Procedure

Workflows

Reference Categories

Auth

Profiles

Projects

Traces

Trace JSON shape

Spans

Span JSON shape

Sessions

Session JSON shape

Datasets / Experiments / Prompts

Annotation Configs

GraphQL

Docs

Output template

Quality gate

References

Related skills

Frequently asked questions

How do I install the Phoenix CLI skill?

What does the Phoenix CLI skill do?

Is Phoenix CLI safe to use?

Which AI agents work with Phoenix CLI?

Is Phoenix CLI free to use?

Who published Phoenix CLI?