beautiful-prose

A hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone.

Quality

78%

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 ./skills/beautiful-prose/SKILL.md

Quality

Content

78%Scale 1-5

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

This is a strong, well-crafted style-contract skill that excels in actionability through concrete banned patterns, positive constraints, and a validation lint checklist. It is mostly concise and well-organized, though it could benefit from slightly tighter structure and verifiable bundle references. The skill effectively communicates a clear writing standard with enough specificity for Claude to execute reliably.

Suggestions

Provide the referenced `references/test-cases.md` file in the bundle, or remove the reference if it doesn't exist.

Consider consolidating the 'Quality bar' and 'Lint checklist' sections into a single ordered validation step to clarify the finalization workflow.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and well-structured. There's minor redundancy between the opening description and the 'What this skill does' section, and the examples section could be slightly tighter, but overall it respects Claude's intelligence and avoids explaining obvious concepts.	4 / 5
Actionability	Extremely actionable: provides explicit banned patterns with concrete examples, positive constraints with specific guidance, a lint checklist for validation, before/after examples, and clear activation syntax with control tags. Every instruction is specific enough to execute without ambiguity.	5 / 5
Workflow Clarity	For a style-contract skill (non-destructive, single-task), the workflow is clear: activate, apply prohibitions and positive constraints, run the lint checklist before finalizing. The quality bar and lint checklist serve as validation checkpoints. Minor gap: the relationship between the 'Quality bar' internal check and the 'Lint checklist' could be more explicitly sequenced.	4 / 5
Progressive Disclosure	The skill references `references/test-cases.md` but no bundle files are provided, making that reference unverifiable. The content is well-sectioned internally but is moderately long (~180 lines) and some sections like the full register descriptions could potentially be split out. The structure is reasonable for a single file but not optimally organized for progressive disclosure.	3 / 5
	Total	16 / 20 Passed

Description

78%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.

This is a solid skill description that clearly communicates both its purpose and when to use it. Its main strength is the explicit 'Use when' clause with concrete trigger phrases and the distinctive stylistic niche it occupies. Its primary weakness is that it describes stylistic attributes rather than listing specific concrete actions (e.g., rewrite, edit, draft), making the capability coverage somewhat abstract.

Suggestions

Add specific concrete actions like 'Rewrites drafts, edits paragraphs, generates essays' to complement the stylistic description and improve specificity.

Include additional natural trigger terms users might say, such as 'make it sound human', 'less robotic', 'natural-sounding writing', or 'remove AI tone'.

Dimension	Reasoning	Score
Specificity	Names the domain (writing style) and describes a couple of concrete qualities ('clean, exact, concrete, free of AI cadence'), but doesn't list specific actions like 'rewrite paragraphs', 'edit drafts', 'generate essays'. The capabilities are described more as stylistic attributes than concrete actions.	3 / 5
Completeness	Clearly answers both 'what' (a hard-edged writing style contract for forceful English prose without modern AI tics) and 'when' (explicitly states 'Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone'). The 'Use when' clause is explicit and contains concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes good natural trigger terms like 'prose', 'rewrites', 'AI cadence', 'filler', 'therapeutic tone', 'writing style'. Missing some common user phrases like 'make it sound human', 'less robotic', 'natural writing', or 'remove AI voice' that users might naturally say.	4 / 5
Distinctiveness Conflict Risk	Fairly distinctive with its focus on anti-AI-cadence, hard-edged prose style. Could potentially overlap with other writing style or tone-adjustment skills, but the specific emphasis on 'timeless, forceful English' and 'free of AI cadence/therapeutic tone' carves out a clear niche. Minor overlap risk with general writing/editing skills.	4 / 5
	Total	16 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/beautiful-prose/SKILL.md
Commit: 6c06908

Reviewed: ~11 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.