prompts-collection

Use for translation, polishing, or de-AI-ification of academic text - provides ready-to-use prompt templates

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

92%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.

The skill body is lean, highly actionable, and clearly sequenced for a single-purpose prompt collection, scoring top marks on conciseness, actionability, and workflow clarity. The only weakness is progressive disclosure: everything is crammed into one monolithic file with no external references or content splitting.

Suggestions

Move the larger or less-frequently-used templates (e.g., the de-AI vocabulary table, the reviewer-perspective template) into references/ files and link to them from SKILL.md to reduce inline bulk and give one-level-deep navigation.

Add a short index/overview at the top listing all eight categories with anchor links so users can jump directly to the needed template instead of scanning the whole file.

Consider extracting the full prompt templates into a references/templates/ directory and keeping SKILL.md as a concise catalog of one-line descriptions plus links, which would lift progressive_disclosure to the top tier.

Dimension	Reasoning	Score
Conciseness	The body is lean: each template is a compact copy-paste block with no conceptual padding, no explanations of what translation or LaTeX is, and every section assumes Claude's competence, so every token earns its place.	3 / 3
Actionability	Every entry is a fully executable, copy-paste-ready prompt (Role/Task/Constraints/Output) plus a concrete word-substitution table, giving specific, ready-to-use guidance rather than vague direction.	3 / 3
Workflow Clarity	This is a single-purpose template collection with no destructive or multi-step operations, so the per-template Role/Task/Output structure plus the numbered '使用建议' usage tips make the intended action unambiguous, satisfying the simple-skill exception.	3 / 3
Progressive Disclosure	All ~260 lines live inline in a single monolithic SKILL.md with no references/ or other bundle files and no file-splitting, so while sections are well-organized, content that could be separate templates (e.g., the vocabulary table, reviewer template) is not split out or navigated via one-level-deep references.	2 / 3
	Total	11 / 12 Passed

Description

75%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.

The description is concise and third-person with an explicit 'Use for...' trigger and a clear niche, but its action list is partial and the coined 'de-AI-ification' term weakens trigger-term naturalness. It clears the completeness and distinctiveness bars but sits at the middle on specificity and trigger quality.

Suggestions

Expand the action list beyond 'translation, polishing, or de-AI-ification' to cover the remaining capabilities shown in the body (e.g., condensing/expanding, logic checking, generating figure/table captions, reviewer-style critique) so specificity reaches the comprehensive tier.

Add natural trigger terms users actually say — 'proofread', 'remove AI tone', 'academic writing', 'paper review', 'LaTeX' — alongside the coined 'de-AI-ification' to improve trigger-term coverage.

Mention the LaTeX/paper context explicitly in the description to sharpen distinctiveness and signal when to reach for this over a generic translation skill.

Dimension	Reasoning	Score
Specificity	Quotes 'translation, polishing, or de-AI-ification of academic text - provides ready-to-use prompt templates': it names the domain and several actions but 'provides prompt templates' describes the deliverable rather than enumerating the full set of concrete actions, so it is not comprehensive enough for a 3.	2 / 3
Completeness	'provides ready-to-use prompt templates' states what the skill does and the 'Use for translation, polishing, or de-AI-ification of academic text' clause is an explicit when-to-use trigger, answering both what and when.	3 / 3
Trigger Term Quality	The phrase 'translation, polishing, or de-AI-ification of academic text' includes some natural user terms, but 'de-AI-ification' is a coined label users would rarely say verbatim and common variants (e.g., 'remove AI tone', 'proofread', 'review') are missing, leaving coverage partial.	2 / 3
Distinctiveness Conflict Risk	The niche — academic-text translation/polishing/de-AI prompt templates — is specific and unlikely to trigger for unrelated skills, with no obvious overlap with general writing or coding skills.	3 / 3
	Total	10 / 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: Norman-bury/research-writing-skill
Path: skills/prompts-collection/SKILL.md
Commit: 6f79595

Reviewed: 10 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.