phoenix-harbor

Configure and interpret the Phoenix plugin for Harbor agent evaluations. Use when adding `arize-phoenix` to Harbor jobs, choosing ATIF tracing, mapping Harbor tasks and rewards to Phoenix experiments, comparing agents or models, resuming jobs, or troubleshooting Harbor records in Phoenix.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

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

A thorough, executable reference for the Phoenix-Harbor plugin with concrete commands, mapping tables, and validation guidance for risky resume/batch operations. It is dense and well-structured but entirely inline with no progressive file split, and a few sections could be tightened.

Suggestions

Move the detailed ATIF trace span taxonomy and the Harbor->Phoenix mapping tables into a reference file linked from SKILL.md to improve progressive disclosure and reduce inline length.

Frame the resume/conflict and unsupported-source-shape checks as explicit validate->stop->retry feedback loops so workflow_clarity checkpoints are unmistakable.

Tighten the multi-step trace interpretation section by collapsing the per-operation naming rules into a compact table to trim token usage.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich, assuming Claude's competence without explaining what Phoenix/Harbor/ATIF are; minor tightening possible in a few list-heavy sections, but padding is minimal.	4 / 5
Actionability	Provides concrete, executable commands ('pip install "arize-phoenix-client[harbor]"', env var exports, '--plugin arize-phoenix', '--plugin-kwarg ...') plus mapping tables, with only minor gaps for advanced edge cases.	4 / 5
Workflow Clarity	Clear sequenced setup flow and a numbered comparison procedure with explicit checkpoints ('Stop and explain the constraint...', 'Do not run multiple ingesters', conflict handling); validation is present for batch/resume operations, though a couple of checkpoints are implicit rather than framed as validate->fix->retry loops.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections, but all content lives inline in SKILL.md with no bundle files and no one-level-deep references (only external doc links), so the split-across-files ideal is not fully met.	4 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

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

A strong, specific description that concretely states both capabilities and trigger conditions in third-person imperative voice. Minor room for more colloquial trigger synonyms, but otherwise low conflict risk and high completeness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Configure and interpret the Phoenix plugin', 'adding `arize-phoenix` to Harbor jobs', 'choosing ATIF tracing', 'mapping Harbor tasks and rewards to Phoenix experiments', 'comparing agents or models', 'resuming jobs', 'troubleshooting' — giving comprehensive, non-abstract coverage.	5 / 5
Completeness	Explicitly answers both 'what' ('Configure and interpret the Phoenix plugin for Harbor agent evaluations') and 'when' with a concrete 'Use when...' clause enumerating specific trigger scenarios.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('comparing agents or models', 'resuming jobs', 'troubleshooting', 'adding arize-phoenix to Harbor jobs') with good coverage, but a few natural synonyms are missing and several terms lean domain-technical rather than colloquial.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Phoenix plugin for Harbor agent evaluations) with distinct, specific triggers, making overlap with other skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Arize-ai/phoenix
Path: .agents/skills/phoenix-harbor/SKILL.md
Commit: e127482

Reviewed: 6 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.