docs-writing-style

Export a docs style prompt or review a draft against the house rubric. Use when handing off voice to an agent or checking a docs draft. It does not place the page (that's `docs-contribution-router`).

Quality

84%

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

86%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-structured, actionable overview that splits detail into real one-level-deep references and supplies a concrete review output format. Its only slack is a brief conceptual "Core principle" paragraph that could be trimmed.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with dense, concrete rules, but the "Core principle" paragraph ("Documentation voice is a contract with the reader... makes readers confident the information is accurate") over-explains a concept Claude already grasps, keeping it just below 5.	4 / 5
Actionability	Each mode has concrete numbered steps, an exact copy-paste output template (PASS/FAIL/WARN with grouping and a single top fix), and specific rules with before/after examples — fully actionable guidance for an assistive instruction skill.	5 / 5
Workflow Clarity	Both modes are clearly sequenced (handoff: 3 steps; review: 5 steps with priority grouping and a closing top-fix), and the "Did this help?" section is a user feedback loop; it is not 5 because there is no internal validate→fix→retry checkpoint, though none is required for this non-destructive skill.	4 / 5
Progressive Disclosure	The body is an overview that signals one-level-deep references via `> Load ...` blockquotes, and all four referenced files (style-principles, scalekit-style-prompt-block, llms-judge-rubric, _template-style-prompt-block) exist in references/, giving clear navigation.	5 / 5
	Total	18 / 20 Passed

Description

82%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 cleanly states two concrete capabilities, provides an explicit "Use when" trigger, and actively disambiguates from a sibling skill. It is strong on completeness and distinctiveness, slightly less comprehensive on action coverage and trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names two concrete actions — "Export a docs style prompt" and "review a draft against the house rubric" — matching the anchor for 1-2 concrete actions without comprehensive coverage, so it stays at 3 rather than 4.	3 / 5
Completeness	Explicitly answers both what ("Export a docs style prompt or review a draft against the house rubric") and when ("Use when handing off voice to an agent or checking a docs draft") with concrete trigger phrases, satisfying the top anchor.	5 / 5
Trigger Term Quality	Natural phrases a user would say appear ("handing off voice to an agent", "checking a docs draft", "docs style prompt") with good coverage; not a 5 because synonyms like "documentation", "tone", or "writing style" are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (docs voice/tone) plus an explicit disambiguation — "It does not place the page (that's `docs-contribution-router`)" — minimizing conflict with sibling skills.	5 / 5
	Total	17 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: saif-shines/devex-kit
Path: plugins/documentation/skills/docs-writing-style/SKILL.md
Commit: df60de1

Reviewed: 1 day 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.