evaluate-skill

Evaluate a local Codex skill in engineer-friendly terms. Use when the user says "evaluate this skill", "give me an analysis of the game dev skill", "audit this skill", "why did this score that way", "what should I fix first", or asks for a skill-specific report before benchmarking it.

Quality

90%

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

80%Weight 40%Scale 1-3

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

A compact, actionable skill body with executable commands and clear conditional routing, undermined by a broken relative reference and the absence of validation checkpoints in its benchmark/batch steps.

Suggestions

Fix or remove the broken reference '../../references/chat-first-workflows.md' — it resolves to no file, and the skill's own priorities list flags broken relative links as a concern.

Add a validation checkpoint to the benchmark workflow (e.g., verify init-benchmark produced .plugin-eval/benchmark.json before running benchmark --dry-run) to guard the batch operation.

Drop the 'Chat Requests To Recognize' section or replace it with routing guidance, since its triggers duplicate the frontmatter description.

Dimension	Reasoning	Score
Conciseness	Lean body with no concept padding (it never explains what skills or a CLI are) and every section earning its place; mild redundancy from 'Chat Requests To Recognize' re-listing frontmatter triggers is the only slack.	3 / 3
Actionability	Provides copy-paste-ready executable commands in a fenced block ('plugin-eval analyze <skill-path> --format markdown', etc.) with exact flags, plus a 10-step routing workflow specifying what to run in each situation.	3 / 3
Workflow Clarity	A clear numbered sequence with conditional routing exists, but there are no validation/verification checkpoints, and the batch/benchmark operations (init-benchmark, benchmark --dry-run) can silently produce misleading results when run incorrectly — capping clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	Signaling is one level deep and well formatted, but the single reference '../../references/chat-first-workflows.md' does not resolve to any real file (no references/ or sibling bundle exists), so the disclosure points at a broken link rather than recoverable detail.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description with explicit 'Use when...' triggers covering both what the skill does and when to invoke it. It is concise, specific, and unlikely to conflict with adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'Evaluate a local Codex skill in engineer-friendly terms' and 'asks for a skill-specific report before benchmarking it' — rather than vague language.	3 / 3
Completeness	Explicitly answers both 'what' (evaluate/audit a Codex skill in engineer-friendly terms) and 'when' via an explicit 'Use when the user says...' clause.	3 / 3
Trigger Term Quality	Five verbatim natural phrases a user would actually say ('evaluate this skill', 'audit this skill', 'what should I fix first', etc.) give strong coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	A clear niche (skill evaluation/auditing) with distinct triggers unlikely to collide with other skills; the Codex-skill framing narrows the scope sharply.	3 / 3
	Total	12 / 12 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/evaluate-skill/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.