article-writing

撰写文章、指南、博客、教程、时事通讯等长篇内容，并根据提供的示例或品牌指南呈现独特的语言风格。当用户需要篇幅超过一段的精炼文字，且重视风格一致性、结构和可信度时，请使用此技能。

Quality

88%

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

85%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.

A tight, actionable instruction-only skill with concrete rules, banned patterns, a sequenced writing process, and a validation quality gate. The main weakness is conciseness, due to redundant bilingual header parentheticals that add tokens without much value.

Suggestions

Drop the redundant English parenthetical translations on section headers (e.g., '(Article Writing)', '(Core Rules)', '(Writing Process)'); keep English only where it aids recognition — banned phrases and trigger terms.

Tighten the '写作流程' steps into concrete directives with verifiable outcomes (e.g., 'Write a one-line goal under each H2') rather than high-level goals like '构建骨架大纲'.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence, but pervasive bilingual parenthetical labels on every section header ('(Article Writing)', '(When to Activate)', '(Core Rules)') add tokens with limited value, matching the score-2 anchor of mostly efficient but could be tightened; not 3 due to these redundant header translations, not 1 because it does not explain concepts Claude already knows.	2 / 3
Actionability	Provides concrete do/don't guidance — '以具体事物开头：示例、输出结果、轶事、数据、截图描述或代码块', a named list of banned phrases to delete, per-format structure directives, and a delivery Quality Gate checklist — matching the score-3 anchor of specific, executable instruction; not 2 because the guidance is concrete rather than vague.	3 / 3
Workflow Clarity	The '写作流程' gives a 5-step sequence and the '质量把关' section provides an explicit pre-delivery validation checklist (verify facts, remove fluff, confirm tone, ensure each section adds info), matching the score-3 anchor of a clear sequence with a checklist; not 2 because the validation checkpoints are explicit, not implicit.	3 / 3
Progressive Disclosure	A single self-contained file with no external references, organized into clearly labeled sections with no nested or deep references and no monolithic wall of text, matching the score-3 anchor of well-organized easy navigation; not 2 because nothing that should be split is forced inline, not 1 because there is no deep reference nesting.	3 / 3
	Total	11 / 12 Passed

Description

92%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.

A strong, well-constructed description: concrete actions, natural trigger terms, and an explicit Use-when clause. Its only weakness is distinctiveness, as long-form writing is a broad niche that may collide with other writing skills.

Suggestions

Lead with the voice/style-matching capability as the primary discriminator (e.g., 'Match a founder's or brand's voice from provided samples when writing long-form content') so it does not collide with generic writing skills.

Add an exclusion phrase to sharpen the trigger, e.g. 'Not for single-paragraph replies or code comments — use when structure, sourcing, and voice consistency matter.'

Dimension	Reasoning	Score
Specificity	Enumerates concrete deliverable types (文章、指南、博客、教程、时事通讯) and a concrete voice-matching action (根据提供的示例或品牌指南呈现独特的语言风格), matching the score-3 anchor of multiple specific concrete actions; not 2 because the actions are concrete and enumerated rather than a bare domain name.	3 / 3
Completeness	Explicitly answers both what (write long-form content in a unique voice) and when (当用户需要篇幅超过一段的精炼文字…请使用此技能), an explicit Use-when trigger matching the score-3 anchor; not 2 because the when clause is stated, not merely implied.	3 / 3
Trigger Term Quality	Uses natural terms a user would actually say — 文章, 指南, 博客, 教程, 时事通讯, 品牌指南, 风格一致性 — giving good coverage matching the score-3 anchor; not 2 because common variations are well represented.	3 / 3
Distinctiveness Conflict Risk	Long-form writing is a broad domain that could overlap with generic writing or editing skills, even though the voice-capture and 'longer than one paragraph' triggers add specificity, matching the score-2 anchor; not 3 because the niche is broader than a single concrete tool domain like PDF extraction.	2 / 3
	Total	11 / 12 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: xu-xiang/everything-claude-code-zh
Path: .agents/skills/article-writing/SKILL.md
Commit: dfbf946

Reviewed: 28 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.