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.

91

2.25x
Quality

88%

Does it follow best practices?

Impact

99%

2.25x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Evaluation results

100%

62%

Span Query Commands for Phoenix CLI

New span resource command implementation

Criteria
Without context
With context

Noun-verb structure

100%

100%

Singular resource name

100%

100%

Formatter module created

100%

100%

Formatter accepts format param

0%

100%

resolveConfig usage

0%

100%

No console.log

0%

100%

Named exit codes

0%

100%

--format flag

0%

100%

Help examples

0%

100%

Options interface naming

70%

100%

Global options on verb

37%

100%

97%

63%

Automating Dataset Lifecycle in CI/CD Pipelines

Idempotent dataset commands for CI/CD automation

Criteria
Without context
With context

--if-not-exists flag

41%

100%

Delete idempotency

66%

100%

--no-input suppresses confirmation

33%

100%

Mutating output is resource data

100%

100%

--format raw for scripting

0%

100%

StructuredError on failure

33%

100%

Missing arg exits INVALID_ARGUMENT

10%

100%

InteractiveCommandOptions interface

0%

70%

--no-input in automation script

0%

100%

100%

38%

Modernizing the Reports Command

Legacy command antipattern refactor

Criteria
Without context
With context

No console.log

100%

100%

writeOutput/writeError used

0%

100%

Named exit codes

66%

100%

resolveConfig replaces env reads

100%

100%

Descriptive option names

100%

100%

Formatter module created

66%

100%

Formatter accepts format param

50%

100%

Singular resource name

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.