CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

65%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 skill body is well-organized with concrete commands and clear step sequencing, but it loses points because the extensive reference/*.md files it points to are missing from the bundle and the upload/convert workflows lack explicit validation feedback loops.

Suggestions

Include the missing reference/*.md files (cover_guide, illustration_guide, writing_style, viral_style, etc.) in a reference/ directory so the documented disclosure scheme actually resolves.

Add an explicit validate→fix→retry checkpoint for the drawio→PNG export and WeChat draft upload steps (e.g., verify the PNG was produced and re-run export if it failed; check API error codes and retry).

Trim the verbose manual-upload Doocs MD walkthrough and the verbatim output example block to reduce token load without losing actionability.

DimensionReasoningScore

Conciseness

The body is largely efficient—using terse tables for routing/style selection and short step lists—but the detailed manual-upload Doocs MD walkthrough and verbatim output example blocks in Step 6/7 could be trimmed. It sits above the 'mostly efficient but could be tightened' anchor but isn't fully lean.

4 / 5

Actionability

Gives concrete executable commands ('bash scripts/export-drawio.sh covers', 'node scripts/upload-to-wechat.js --title ...', 'npx wechat-article-publisher ...') with file paths and env config, but leaves the actual mxGraph XML generation to Claude and has minor gaps.

4 / 5

Workflow Clarity

Steps are clearly sequenced (Step 2–7, 风格提取 Step 1–5) but the batch/API upload and drawio→PNG conversion lack explicit validate→fix→retry feedback loops; per the rubric, missing validation in destructive/batch operations caps this at 3.

3 / 5

Progressive Disclosure

The body is structured as a well-signaled overview pointing to many one-level-deep reference/*.md files, but those reference files do not exist in the bundle, so the navigation scheme does not resolve.

3 / 5

Total

14

/

20

Passed

Description

100%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 concisely names the domain, lists concrete capabilities, and pairs them with an explicit, comprehensive set of natural trigger phrases. Both the 'what' and 'when' are clearly answered with minimal padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—'撰写文章、封面图、正文插图、风格提取' plus '支持多种写作风格'—covering the skill's capabilities comprehensively rather than at a vague high level.

5 / 5

Completeness

Explicitly states both what it does ('撰写文章、封面图、正文插图、风格提取') and when to use it ('当用户提到...时使用') with concrete trigger phrases, fully answering both questions.

5 / 5

Trigger Term Quality

Provides comprehensive natural triggers a user would actually say ('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'), including synonyms like 模仿爆款/克隆文风 and 分析写作风格/提取风格.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (公众号/自媒体 creation) with domain-specific triggers unlikely to fire for unrelated skills, keeping conflict risk minimal.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 12 missing

Warning

Total

15

/

16

Passed

Repository
xstongxue/best-skills
Reviewed

Table of Contents

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.