style-learner

Learn and extract writing style patterns from exemplar text for consistent application. Use when creating a style guide from existing content, ensuring consistency across documents, learning a specific author's voice, customizing /AI output style. Do not use when detecting AI slop - use slop-detector instead. just need to clean up existing content - use doc-generator with --remediate. Use this skill to build style profiles from exemplar text.

Quality

82%

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

77%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 body is a well-sequenced, actionable instruction skill with a strong validation loop, but its progressive disclosure is undermined by references to module files that are absent from the bundle. Creating the referenced module files or removing the dangling references would resolve the weakest dimension.

Suggestions

Create the referenced module files (modules/feature-extraction.md, modules/exemplar-reference.md, modules/style-application.md) or remove the 'Load: @modules/...' lines and the frontmatter modules/progressive_loading declarations so references are not broken.

Move the inline metric tables (vocabulary, sentence, structural, punctuation) into the corresponding module files to keep SKILL.md as a lean overview, since progressive_loading is declared true.

Tighten the YAML profile and exemplar templates by replacing placeholder-heavy blocks with a single compact canonical example to reduce inline bulk.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables of metrics and templates that assume Claude's competence without over-explaining known concepts, though the inline metric tables and YAML/ exemplar templates carry some bulk that could be trimmed or offloaded.	4 / 5
Actionability	Concrete actionable guidance for an instruction-only skill: specific metrics with how-to-measure formulas, a profile-format YAML template, and a validation checklist with quantitative thresholds, though templates still use placeholders and no analysis tooling is provided.	4 / 5
Workflow Clarity	Clear five-step sequence (Collect → Extract → Select → Generate → Validate) with an explicit validation checklist and a feedback loop ('Refine profile based on feedback'), plus TodoWrite items mapped to each step.	5 / 5
Progressive Disclosure	The body has clear section structure and explicitly signaled references ('Load: @modules/feature-extraction.md', '@modules/exemplar-reference.md', 'modules/style-application.md'), but those referenced module files do not exist in the bundle, and substantial reference material (metric tables, templates) is inlined rather than split into the promised separate files.	3 / 5
	Total	16 / 20 Passed

Description

87%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 strong: it clearly states what the skill does, gives explicit use-when triggers, and actively disambiguates from neighboring skills. Minor grammar issues ('customizing /AI output style', a sentence fragment) and slightly overlapping action verbs keep specificity and trigger quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Learn and extract writing style patterns', 'build style profiles', 'creating a style guide', 'learning a specific author's voice'), but the actions overlap as variations rather than comprehensively distinct capabilities.	4 / 5
Completeness	Explicitly answers both what ('Learn and extract writing style patterns from exemplar text') and when ('Use when creating a style guide... learning a specific author's voice'), with concrete trigger phrases and negative triggers.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('style guide', 'writing style', 'author's voice', 'consistency across documents'), but a few common synonyms are missing and no file-type triggers apply.	4 / 5
Distinctiveness Conflict Risk	Clear niche (style learning from exemplars) with explicit disambiguation ('Do not use when detecting AI slop - use slop-detector instead', 'use doc-generator with --remediate') minimizing conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: slurpyb/skills
Path: wip/plugins/writing/skills/style-learner/SKILL.md
Commit: 3641e2b

Reviewed: 8 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.