huashu-image-upload

文章配图一键生成并上传图床，自动插入Markdown链接。当用户提到"配图"、"插图"、"上传图片"、"文章配图"时使用。

Quality

88%

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

77%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 highly actionable with executable commands and a clear sequenced workflow plus validation, but it is somewhat verbose (redundant sections, a promotional footer) and references external paths that are not part of the skill bundle, weakening progressive disclosure.

Suggestions

Trim redundancy: the source-priority section, execution steps, and Q&A overlap; consolidate and remove the self-promotional footer to respect token budget.

Move detailed reference material (API call docs, best-practice summary) into actual bundle files under references/ and link to them one level deep, instead of inline paths to external project locations that are not part of the skill.

The inline reference paths (/tools/README.md, /公众号写作/...) point outside the skill and are not bundled; replace with verified relative paths or remove so navigation is reliable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but redundant sections (来源优先级 re-explained, a self-promotional footer, and Q&A that restates earlier points) pad the body with content Claude could infer.	2 / 3
Actionability	Provides copy-paste-ready executable commands (python3 /tools/upload_image.py <URL>, grep -n "!\["), concrete Markdown format, and precise specs (sizes, file limits, naming).	3 / 3
Workflow Clarity	The 5-step standard flow is clearly sequenced with a checklist and a verification step (Step 5) including a feedback/validation command for the batch insertion operation.	3 / 3
Progressive Disclosure	Well-organized into sections, but it is a monolithic single-file body with inline reference paths (e.g. /tools/README.md, /公众号写作/...md) that are not actual bundle files in the skill directory and are not clearly signaled as one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

100%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 clearly answers both what the skill does and when to use it, with natural trigger terms and a distinct niche. It is a strong, well-constructed description.

Dimension	Reasoning	Score
Specificity	Lists concrete actions — '一键生成并上传图床'、'自动插入Markdown链接' — naming the domain and multiple specific operations rather than vague verbs.	3 / 3
Completeness	Explicitly states both what it does (生成配图、上传图床、插入Markdown链接) and when to use it ('当用户提到...时使用'), satisfying the what-and-when requirement.	3 / 3
Trigger Term Quality	Quotes natural user phrases ('配图'、'插图'、'上传图片'、'文章配图') that a user would genuinely say, with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Niche is clearly bounded to image generation/upload for articles, with distinct trigger terms unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alchaincyf/huashu-skills
Path: huashu-image-upload/SKILL.md
Commit: 35e7cf3

Reviewed: 12 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.