article-writing

编写文章、指南、博客、教程、时事通讯（Newsletter）等长内容，支持从示例或品牌指南中提取独特的语感语调。适用于需要撰写超过一个段落的精炼文本，尤其是对语气一致性、结构和可信度有较高要求时。

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

The body is lean, well-structured, and includes a sequenced process with a pre-delivery validation checklist. Its main gap is the absence of worked before/after examples that would make the concrete rules immediately copy-applicable.

Suggestions

Add one or two short before/after examples (e.g., a banned opening rewritten into a concrete, evidence-led one) so the rules are demonstrable rather than only descriptive.

Turn the Quality Gate into an explicit feedback loop: state that if any gate item fails, Claude should revise and re-check before delivery.

Dimension	Reasoning	Score
Conciseness	Lean, directive, and well-sectioned with no explaining of concepts Claude already knows; bilingual labels add minimal tokens and every section earns its place.	3 / 3
Actionability	Gives concrete directives and specific banned phrases ('在当今快速演变的格局中', 'Game-changer', 'Revolutionary'), but provides no worked before/after examples that show the transformation in practice — a key detail for an instruction-only skill.	2 / 3
Workflow Clarity	A sequenced 5-step '写作流程' is paired with an explicit pre-delivery '质量把控' checklist that acts as a validation checkpoint; this is not a destructive/batch op so no cap applies.	3 / 3
Progressive Disclosure	Self-contained and well-organized into clearly labeled sections with no nested or external file references needed; appropriate for a skill of this size with no bundle files.	3 / 3
	Total	11 / 12 Passed

Description

82%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, third-person, and answers both what and when with an explicit trigger clause and natural user terms. It is somewhat thin on the breadth of concrete actions and carries mild overlap risk with generic writing skills.

Suggestions

Broaden the capability list beyond 'write' and 'extract voice' — e.g., 'restructure and tighten existing drafts' or 'repurpose notes, transcripts, or research into articles' — so the action set is comprehensive.

Sharpen the trigger to reduce overlap with generic writing skills, e.g., 'Use when the user wants long-form published content (blog, newsletter, tutorial, essay) with a specific voice or brand tone — not short replies or code docs.'

Dimension	Reasoning	Score
Specificity	Names the long-form content domain ('文章、指南、博客、教程、时事通讯') and two actions ('编写', '从示例或品牌指南中提取独特的语感语调'), but the action set is not comprehensive — it is essentially 'write' plus 'extract voice'.	2 / 3
Completeness	Answers both what (write long-form content, extract voice) and when via the explicit trigger clause '适用于需要撰写超过一个段落的精炼文本…时' with concrete conditions (tone consistency, structure, credibility).	3 / 3
Trigger Term Quality	Includes natural terms a user would actually say — 博客, 教程, 时事通讯/Newsletter, 指南, 语调, 品牌指南 — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The long-form plus voice-capture niche is fairly specific, but 'writing' is a broad domain that could still overlap with other generic writing or content skills.	2 / 3
	Total	10 / 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: .cursor/skills/article-writing/SKILL.md
Commit: dfbf946

Reviewed: 2 months 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.