plugin-eval

Help engineers evaluate a local skill or plugin, explain why it scored that way, show what to fix first, measure real token usage, benchmark starter scenarios, or decide what to run next. Use when the user says things like "evaluate this skill", "give me an analysis of the game dev skill", "why did this score that way", "what should I fix first", "measure the real token usage of this skill", or "what should I run next?".

Quality

82%

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

68%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.

The body is a well-structured, highly actionable router with concrete commands and clean sections. Its main weaknesses are duplicated chat-phrase lists (conciseness) and missing validation feedback loops for batch benchmark flows (workflow clarity).

Suggestions

Remove the standalone 'Chat Requests To Recognize' list or fold it into 'Start Here' step 3 to eliminate the duplicated phrase inventory and tighten conciseness.

Add explicit validation/verification checkpoints to the benchmark and measurement-plan flows (e.g., confirm benchmark.json is valid before dry-run, verify measured results before reporting).

Convert the '../../references/*.md' links to bundle-local paths or confirm they resolve within the plugin bundle so navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient router guidance with no padding of known concepts, but 'Chat Requests To Recognize' duplicates the phrases already embedded in 'Start Here' step 3 and 'Output Expectations' restates routing already covered, so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready, executable commands throughout ('plugin-eval start <path> --request ...', 'plugin-eval analyze <path> --format markdown', etc.) covering the common routing cases.	5 / 5
Workflow Clarity	'Start Here' gives a clear numbered sequence with an ambiguity checkpoint in step 6, but batch flows (benchmark, measurement-plan) lack validation/verification feedback loops, which the rubric requires for batch operations.	3 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled one-level-deep References list; not a 5 because the references use upward relative paths ('../../references/') rather than bundle-local files.	4 / 5
	Total	15 / 20 Passed

Description

96%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 description: concrete capabilities, abundant natural trigger phrases, and an explicit 'Use when' clause that jointly answer what and when. Only minor distinctiveness overlap with sibling improve/evaluate skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('evaluate a local skill or plugin', 'explain why it scored that way', 'show what to fix first', 'measure real token usage', 'benchmark starter scenarios', 'decide what to run next'), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated capabilities) and 'when' ('Use when the user says things like...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Six natural quoted user phrases ('evaluate this skill', 'give me an analysis of the game dev skill', 'why did this score that way', etc.) provide comprehensive coverage of terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Has a clear evaluation niche with distinctive triggers, but 'show what to fix first' slightly overlaps the sibling improve-skill skill it routes to, giving minor overlap risk rather than minimal.	4 / 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: openai/plugins
Path: plugins/plugin-eval/skills/plugin-eval/SKILL.md
Commit: 1dc1958

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.