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

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/gpt-pro/SKILL.md

Quality

Content

81%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 skill body is a well-structured, actionable instruction skill with a clear sequence and an explicit pre-finalization validation checklist. Its only weaknesses are mild redundancy across policy sections and the lack of a worked example prompt, which keep conciseness and actionability at 4.

Suggestions

Consolidate the overlapping context-inclusion rules spread across Hard Policy, Context Packing Rules, and Quality Gates into one section to tighten the token budget.

Add a short worked example of a finished paste-ready prompt (even abbreviated) to lift actionability from concrete guidance to fully copy-paste-ready.

Consider moving the Prompt Contract's requested-output list (harsh verdict, risk table, benchmark matrix, etc.) into a references/ file to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dense, bullet-driven, and free of explanations of concepts Claude already knows. Minor redundancy — "include current-state context inline" is restated across Hard Policy, Context Packing Rules, and Quality Gates — means it could be tightened, matching anchor 4 rather than the lean anchor 5.	4 / 5
Actionability	Guidance is concrete and executable for an instruction-only skill: a 12-item Prompt Contract, an explicit list of requested outputs, a Quality Gates checklist, and a concrete output format with a wrapper example. It stops short of anchor 5 only because there is no worked example of a finished prompt.	4 / 5
Workflow Clarity	The multi-step process is clearly sequenced (Read First 1–7, Workflow 1–8, Prompt Contract) and ends with an explicit Quality Gates validation checklist to run "before finalizing the prompt" — a genuine validate-before-emit feedback step. This matches the anchor with explicit validation and checklists; no destructive or batch operations require further gates.	5 / 5
Progressive Disclosure	No bundle files exist, and the single file is well-sectioned with clear headers and easy navigation. At ~165 lines some material (e.g., the Prompt Contract's requested-output lists) could plausibly live in a reference file, which fits anchor 4's "minor organization gaps" rather than the fully split anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

66%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.

The description is specific and distinctive about what it produces, with good natural trigger terms. Its main weakness is the complete absence of "when to use" guidance, which both caps completeness and weakens trigger-term coverage relative to natural user phrasings like "ChatGPT".

Suggestions

Add an explicit 'Use when' clause to the description, e.g. "Use when the user says GPT Pro, ChatGPT Pro, external review, or asks to send work to another model."

Include the natural trigger synonyms that appear in the body ("ChatGPT", "ask another model") in the description itself so users' phrasings match without reading the body.

The causal clause "because the reviewer has no local file access" explains rationale but not usage; consider replacing it with usage guidance to also trim token cost.

Dimension	Reasoning	Score
Specificity	"Create a self-contained GPT Pro or external-review prompt" plus "full repo context, current state, evidence, and pointed review questions" names the domain and several concrete deliverable components. It stops short of anchor 5 because it describes essentially one action (creating a prompt) rather than multiple comprehensive actions.	4 / 5
Completeness	The "what" is explicit and concrete, but there is no "Use when..." clause or equivalent trigger guidance — "because the reviewer has no local file access" is rationale, not usage direction. Per the guidelines a missing/weak "when" caps completeness at 3; it is not 2 because the "what" is clear, and not 4 because "when" is not merely under-specified, it is absent.	3 / 5
Trigger Term Quality	"GPT Pro", "external-review prompt", "repo context", and "review questions" are natural, relevant terms, and "no local file access" signals the scenario. Common phrasings users actually say — "ChatGPT", "send this to ChatGPT", "ask another model" — appear only in the body, not the description, so a few natural synonyms are missing (anchor 4, not 5).	4 / 5
Distinctiveness Conflict Risk	"GPT Pro", "external-review prompt", and "no local file access" carve out a distinct niche with specific triggers. There is minor overlap risk with generic code-review or planning skills, so it fits anchor 4 rather than the fully distinct anchor 5.	4 / 5
	Total	15 / 20 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: babb3c2

Reviewed: 2 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.