gpt-pro

Create a self-contained GPT Pro or external-review prompt with full repo context, current state, evidence, and pointed review questions because the reviewer has no local file access.

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

85%

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 instruction-only skill with a clear sequenced workflow and explicit validation gates. Its lone weakness is cross-section redundancy: the self-contained-context rule is restated in several sections and could be consolidated.

Suggestions

Consolidate the repeated 'include context inline, no repo access' guidance into one section (e.g., Hard Policy) and have Context Packing Rules and Quality Gates reference it rather than restate it, to improve conciseness.

Consider folding the Read First list into the Workflow's evidence-gathering step to remove overlap between the two sections.

Trim the restated 'do not ask the reviewer to inspect' rule, which appears in both Hard Policy and Context Packing Rules, to a single canonical statement.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with no concept-explanation fluff, but the 'include all context inline / reviewer has no repo access' theme is restated across Hard Policy, Read First, Context Packing Rules, and Quality Gates, so it could be tightened. Not a 3 because of this cross-section redundancy; not a 1 because it avoids padding and assumes Claude's competence.	2 / 3
Actionability	Provides a numbered 8-step Workflow, a 12-item Prompt Contract, an explicit requested-outputs list, concrete fact labels ('confirmed', 'benchmarked', 'inferred', 'stale', 'gap'), and a Quality Gates checklist — fully actionable instruction-only guidance. Not a 2 because the guidance is specific and copy-paste ready rather than abstract or pseudocode.	3 / 3
Workflow Clarity	A clear sequenced Workflow (8 steps) plus a 'Quality Gates' validation checklist run 'before finalizing the prompt', giving explicit checkpoints and a review-before-emit loop. Not a 2 because validation checkpoints are explicit, not merely implied.	3 / 3
Progressive Disclosure	A single self-contained file with no bundle references, organized into well-labeled sections (Use When, Hard Policy, Workflow, Prompt Contract, Quality Gates, Output) and no nested references, matching the anchor for well-organized content with no deep nesting. Not a 2 because there is no monolithic wall of text or multi-level reference chain.	3 / 3
	Total	11 / 12 Passed

Description

82%

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

The description is specific and concrete, naming the artifact (external-review prompt) and its required content, with natural trigger terms and a distinct niche. Its main weakness is the absence of an explicit 'Use when…' trigger clause, leaving the invocation condition implied rather than stated.

Suggestions

Add an explicit trigger clause such as 'Use when the user wants a paste-ready prompt for GPT Pro, ChatGPT Pro, or another external reviewer' to lift completeness to 3.

Include the common user phrasings 'ChatGPT Pro' and 'ask another model' alongside 'GPT Pro' to broaden trigger-term coverage.

State the invocation condition ('when the user asks to send something to / get a review from an external model') so the 'when' is explicit, not just the 'why'.

Dimension	Reasoning	Score
Specificity	Enumerates concrete content elements — 'full repo context, current state, evidence, and pointed review questions' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor. Not a 2 because the components are concrete and enumerated, not just a domain label.	3 / 3
Completeness	Clearly answers 'what' (create a self-contained prompt) and gives a 'why' ('because the reviewer has no local file access'), but there is no explicit 'Use when…' trigger clause, so completeness is capped at 2 per the guidelines. Not a 3 because the 'when' is only implied, never stated.	2 / 3
Trigger Term Quality	Includes natural terms users would say — 'GPT Pro', 'external-review prompt', 'review questions' — giving good coverage matching the anchor for natural user terms. Not a 2 because these are phrasings a user would actually utter rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche — external-review prompt generation — with triggers unlikely to fire for unrelated skills. Not a 2 because the scope is narrow and specific rather than broadly overlapping.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/gpt-pro/SKILL.md
Commit: 45116fd

Reviewed: about 13 hours 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.