phoenix-cli
Helps your agent debug AI applications. It allows analyzing errors and data to understand failures and improve performance.
What it does
This tool helps you understand and fix problems in AI applications. It lets you see the details of how the AI worked, analyze errors, and organize this information to find the root cause of issues.
When to use it
- ✓When an AI application isn't working as expected.
- ✓When trying to understand why the AI made a specific mistake.
- ✓To organize and categorize common failures in AI systems.
Example of what to ask your AI
“Analyze the latest errors from my AI application and help me find a pattern.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You use commands in your terminal to fetch information about the AI's operation, like 'traces' and 'spans'. Then, you can add notes or organize this data to create an error report.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add github/awesome-copilot --skill phoenix-cliOr download just the file:
curl -L https://raw.githubusercontent.com/github/awesome-copilot/main/skills/phoenix-cli/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Phoenix CLI
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.
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.
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
…
FAQ
What are 'traces' and 'spans'?
'Traces' show the complete path of a request through the AI application, and 'spans' are smaller parts of that path detailing specific operations.
How do I set up the tool?
You need to define where the tool should connect (PHOENIX_HOST) and which project to analyze (PHOENIX_PROJECT), plus an API key if required.
Can I use the tool without installing anything?
Yes, you can use the command `npx @arizeai/phoenix-cli ...` which runs the tool directly from the package registry.
Details
Original description by the author
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
repo: github/awesome-copilot
Popularity
- GitHub stars
- 40k
- Ranking position
- #5263
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
acquire-codebase-knowledge
Helps your agent understand and document an existing code project. It's useful for onboarding new people or getting an overview of the architecture.
github/awesome-copilot
acreadiness-assess
Enables your agent to assess a project's readiness for AI and generate a report. It's useful for understanding how well a project is prepared to use AI tools.
github/awesome-copilot
acreadiness-generate-instructions
Helps your agent create instructions for AI tools based on an assessment. It's useful for improving how AI interacts with code and closing identified gaps.
github/awesome-copilot
acreadiness-policy
Enables your agent to help define or apply policies for AI project assessment. It's useful for standardizing how projects are evaluated and ensuring compliance.
github/awesome-copilot
Similar skills
api-connector-builder
Has your agent build new API connections following the existing pattern. Use when you need to add one more integration without creating a new way of doing things.
affaan-m/ECC
api-design
Helps your agent design REST APIs following best practices. It's useful for defining how APIs communicate, how errors are shown, and how to organize data.
affaan-m/ECC
backend-patterns
Helps your agent with server-side architecture patterns and database optimization. It's useful for building or reviewing code that runs on the server.
affaan-m/ECC