CtrlK
BlogDocsLog inGet started
Tessl Logo

phoenix-cli-development

Design and implementation guide for the Phoenix CLI (`px`). Covers the noun-verb command structure, dual-audience design (humans and coding agents), Commander.js patterns, configuration resolution, output formats, exit codes, and conventions for adding or modifying commands. Triggers when working on phoenix-cli commands — adding new commands, modifying existing ones, refactoring command structure, or reviewing CLI code. Also triggers on mentions of `px` commands, CLI design, or adding a new resource to the CLI.

84

1.47x
Quality

88%

Does it follow best practices?

Impact

99%

1.47x

Average score across 2 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Evaluation results

99%

Add Experiment Management to the Phoenix CLI

New CLI resource command implementation

Criteria
Without this skill
With this skill

Noun-verb structure

100%

100%

--format flag

100%

100%

Mutating command output

100%

100%

USAGE.md documentation

100%

100%

Progress to stderr

100%

100%

Named exit codes

100%

100%

--no-input mode

100%

100%

Actionable error messages

100%

100%

StructuredError on json/raw

100%

100%

Command registration

100%

100%

Help text examples

100%

100%

Options interfaces

100%

100%

TSDoc on options fields

100%

100%

Configuration via resolveConfig

100%

100%

Formatter module

80%

80%

I/O helpers

100%

100%

Naming conventions

100%

100%

100%

64%

Test Suite for the Dataset List Command

Vitest test suite using MSW mock server for Phoenix CLI dataset command

Criteria
Without this skill
With this skill

setupMockPhoenixServer at module level

0%

100%

No global fetch stubbing

0%

100%

BASE_ARGS from testUtils

0%

100%

mockProcessExit from testUtils

0%

100%

captureCliOutput from testUtils

0%

100%

pretty format test

100%

100%

json format test

100%

100%

raw format test

100%

100%

Network error exit code

50%

100%

Empty results test

100%

100%

Missing config test

14%

100%

Unpinned generated-handler test

0%

100%

Repository
Arize-ai/phoenix
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.