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.

1.47x

Quality

96%

Does it follow best practices?

Impact

100%

1.47x

Average score across 2 eval scenarios

Securityby

High

Do not use without reviewing

Evaluation results

100%

41%

Add Experiment Tracking to the Phoenix CLI

New resource command implementation

Criteria

Baseline

With context

Noun-verb command structure

100%

Singular resource name

100%

Formatter file created

50%

100%

writeOutput/writeError used

100%

No console.log

100%

resolveConfig used

100%

Shared options types reused

28%

100%

ExitCode named constants

42%

100%

Global options on verb

28%

100%

Help examples present

100%

TSDoc on options fields

100%

create returns resource data

100%

camelCase filenames

60%

100%

PascalCase interfaces

100%

22%

Dataset Delete Command for the Phoenix CLI

Agent-friendly dataset delete command handler

Criteria

Baseline

With context

--no-input flag registered

50%

100%

--no-input suppresses confirmation

100%

Missing resource exits SUCCESS

100%

StructuredError on --format raw/json

40%

100%

ExitCode named constants used

100%

Deleted resource returned on stdout

100%

Progress to stderr via writeProgress

37%

100%

Actionable error message with syntax

62%

100%

No console.log usage

100%

DESIGN.md covers non-interactive behavior

100%

DESIGN.md covers missing dataset behavior

100%

DESIGN.md covers structured error output

50%

100%

Repository: Arize-ai/phoenix
Path: js/packages/phoenix-cli/.agents/skills/phoenix-cli-development/SKILL.md
Commit: d9421a4

Evaluated: 16 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Add Experiment Tracking to the Phoenix CLI Dataset Delete Command for the Phoenix CLI

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.