wechat-article-writer

公众号/自媒体全流程。根据用户表述自动匹配：撰写文章、封面图、正文插图、风格提取。支持多种写作风格。当用户提到写公众号、技术博客、公众号封面、正文插图、步骤图、演示图、流程示意、分析写作风格、克隆文风、模仿爆款、提取风格时使用。详见 reference 目录。

Quality

82%

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

65%

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

The body is highly actionable with concrete commands and clear task routing, but is somewhat verbose in the upload section, lacks an upload validation feedback loop, and references a reference/ directory that is missing from the bundle.

Suggestions

Add a validate/retry checkpoint to the Step 7 upload flow (e.g., check API response, handle 40001 token errors with refresh-and-retry) so the external write operation has a feedback loop.

Trim Step 7 verbosity: collapse the three repeated export-option lists into one and remove the full success-output sample block, keeping only the key return fields.

Either create the referenced reference/ directory with the 12 cited .md files, or remove/inline the missing references so signaled paths match the actual bundle.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and steps with no basic-concept padding, but Step 7 is verbose — repeated export-option lists and full success-output samples could be tightened.	2 / 3
Actionability	Concrete, copy-paste-ready commands (bash scripts/export-drawio.sh covers, npx wechat-article-publisher, node scripts/upload-to-wechat.js) with specific file paths and env config.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 2–7) with routing tables, but the WeChat upload (an external/batch write) lacks a validate-then-fix feedback loop, capping it at 2.	2 / 3
Progressive Disclosure	Overview clearly signals one-level-deep reference/*.md links, but the referenced reference/ directory is absent from the bundle (only scripts/ exists), so signaled references do not match the actual structure.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 specific, well-triggered, and complete, clearly stating both capabilities and use conditions in third person. It is a strong, low-conflict skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 撰写文章、封面图、正文插图、风格提取 — matching the anchor for enumerating several specific concrete actions.	3 / 3
Completeness	Explicitly states what the skill does (公众号/自媒体全流程 and the four sub-tasks) and when to use it via the explicit 当用户提到…时使用 clause.	3 / 3
Trigger Term Quality	Provides a broad, natural set of trigger phrases (写公众号、公众号封面、步骤图、演示图、克隆文风、模仿爆款、提取风格) that users would actually say.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche — WeChat public-account / self-media creation — with distinct, domain-specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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
relative_links	Relative link issues: 12 missing	Warning

	Total	15 / 16 Passed

Repository: xstongxue/best-skills
Path: skills/wechat-article-writer/SKILL.md
Commit: fd28854

Reviewed: 5 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.