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.

2.25x

Quality

88%

Does it follow best practices?

Impact

99%

2.25x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a strong, highly actionable CLI design specification with excellent workflow clarity, particularly the 18-step checklist for adding new commands with explicit validation checkpoints. The main weaknesses are moderate verbosity (some explanations of concepts Claude already knows) and the monolithic structure that could benefit from splitting detailed reference material into separate files. The dual-audience design philosophy is well-articulated with concrete examples throughout.

Suggestions

Trim explanatory prose that Claude already knows — e.g., remove the RFC 2119 keyword note, the explanation of what camelCase/PascalCase are, and phrases like 'they name the type of thing you're acting on, not how many'.

Consider splitting reference material (exit codes table, naming conventions, standard verbs table) into separate bundle files and linking to them, reducing the main SKILL.md to a focused overview with the checklist and key patterns.

Dimension	Reasoning	Score
Conciseness	The skill is thorough and mostly well-structured, but includes some content Claude would already know (e.g., explaining what RFC 2119 keywords are, explaining what camelCase/PascalCase are, basic TypeScript interface patterns). Some sections like the naming conventions could be more terse. The dual-audience design section, while valuable, could be tightened in places.	2 / 3
Actionability	The skill provides highly concrete, executable guidance throughout: specific CLI invocations, TypeScript interfaces, exact file paths, specific function names to use (writeOutput, resolveConfig), and a detailed 18-step checklist for adding new commands. Code examples are copy-paste ready and contextually appropriate.	3 / 3
Workflow Clarity	The checklist for adding a new resource command is a clear, sequenced workflow with explicit validation steps (step 10: run tests, step 11: run build, step 18: manual verification with --format raw). The migration workflow for backward compatibility is also clearly sequenced. Feedback loops are present (fix failures before proceeding).	3 / 3
Progressive Disclosure	The content is well-organized with clear section headers, but it's a monolithic document (~300 lines) with no references to supporting files. Some sections like the full exit code table, naming conventions, and testing details could be split into separate reference files. No bundle files are provided, so there's no external structure to leverage.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that clearly defines its scope (Phoenix CLI design and implementation), lists concrete capabilities, and provides explicit trigger conditions. The description is well-structured with a clear separation between what the skill covers and when it should be activated, using natural and specific trigger terms throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete aspects: noun-verb command structure, dual-audience design, Commander.js patterns, configuration resolution, output formats, exit codes, and conventions for adding/modifying commands. These are concrete, actionable topics.	3 / 3
Completeness	Clearly answers both 'what' (design and implementation guide covering specific patterns and conventions) and 'when' (explicit 'Triggers when...' clause listing multiple scenarios like adding commands, modifying existing ones, mentions of `px` commands, CLI design).	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'phoenix-cli', 'px', 'CLI design', 'adding new commands', 'modifying existing ones', 'refactoring command structure', 'reviewing CLI code', 'new resource to the CLI'. These cover the natural ways a user or agent would reference this work.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — scoped specifically to the Phoenix CLI (`px`), with domain-specific terms like Commander.js, noun-verb command structure, and dual-audience design. Unlikely to conflict with generic CLI or coding skills.	3 / 3
	Total	12 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	10 / 11 Passed

Repository: Arize-ai/phoenix
Commit: 5b77485

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.