CtrlK
BlogDocsLog inGet started
Tessl Logo

wechat-article

AI Berkshire skill: 微信公众号文章:作者-编辑-读者三Agent协作. Source: skills/wechat-article.md.

58

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/wechat-article/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 a clear, validated four-stage workflow and concrete commands, but it is delivered as one monolithic file whose bulky prompt templates would benefit from being split out. Moving the templates into references would improve both conciseness and progressive disclosure.

Suggestions

Extract the author/editor/reader prompt templates into separate files under references/ and link to them from SKILL.md to improve progressive disclosure and reduce inline bulk.

Tighten repeated guidance between stages (e.g., the LaTeX and image rules that reappear in both the author prompt and the 写作红线) by stating once and cross-referencing.

Keep the validated workflow steps but consider trimming the boilerplate prose around the prompt templates to earn the top conciseness anchor.

DimensionReasoningScore

Conciseness

The body is mostly efficient—prompt templates, command flags, and red-lines add value Claude would not trivially know—but the large verbatim prompt-template blocks and some repetition across stages could be tightened, so it is not fully lean.

2 / 3

Actionability

It gives concrete, copy-paste-ready guidance: full author/editor/reader prompt templates, executable commands with exact flags (pdftoppm -png -r 900, PIL compress_level=1), file-naming formats, and defined output structures.

3 / 3

Workflow Clarity

A clear four-stage sequence with sub-steps is laid out, supported by tables, explicit feedback-prioritization rules, and a recovery checkpoint in the image-extraction checklist (escalate DPI when output is under 500KB).

3 / 3

Progressive Disclosure

No bundle files exist and everything is inline in a single ~240-line file; the large prompt templates are content that could be split into separate reference files, matching 'content that should be separate is inline' rather than a clean overview-with-references structure.

2 / 3

Total

10

/

12

Passed

Description

57%

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 identifies a distinct niche and includes a natural trigger term, but it omits explicit 'when to use' guidance and buries its useful keywords under source-metadata boilerplate. Tightening it to lead with the user-facing task and add a 'Use when...' clause would lift the weaker dimensions.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to write, research, or polish a 微信公众号 article' to satisfy the completeness 'when' requirement.

Remove metadata noise like 'AI Berkshire skill:' and 'Source: skills/wechat-article.md.' from the description and move it elsewhere, so the natural trigger term stands out.

List a few concrete actions (e.g., '深度研究素材、写初稿、编辑精修、读者视角审读、定稿') to raise specificity from domain-naming to multiple concrete actions.

DimensionReasoningScore

Specificity

The description names the domain ("微信公众号文章") and a structural mechanism ("作者-编辑-读者三Agent协作") but does not list concrete actions like research, draft, edit, or review, so it sits at 'names domain and some actions' rather than 'multiple specific concrete actions'.

2 / 3

Completeness

It states what the skill does (produce a WeChat article via three-agent collaboration) but lacks any 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

It includes the natural trigger term a user would say ("微信公众号文章") but interleaves it with non-trigger metadata noise ("AI Berkshire skill:" and "Source: skills/wechat-article.md."), so coverage of natural terms is present but diluted rather than strong.

2 / 3

Distinctiveness Conflict Risk

The combination of WeChat-specific articles and an author-editor-reader three-agent workflow is a clear niche with distinct triggers, making it unlikely to fire for an unrelated skill.

3 / 3

Total

9

/

12

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: 1 missing, 1 suspicious

Warning

Total

15

/

16

Passed

Repository
xbtlin/ai-berkshire
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.