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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./huashu-image-upload/SKILL.md

Quality

Content

70%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 delivers a clear, validated 5-step workflow with concrete commands and good actionability. Its main weaknesses are verbosity from repetition and promotional content, and the absence of an actual reference bundle despite inline external paths.

Suggestions

Trim repeated upload-script examples, the FAQ that restates earlier guidance, and the promotional author/footer block to improve conciseness.

Replace hardcoded absolute paths (/Users/alchain/.../tools/upload_image.py) with a parameterized or project-relative path so commands are executable for other users.

Move detailed reference material into actual ./references/ or ./scripts/ bundle files and link to them one level deep, instead of pointing at external absolute filesystem paths.

Provide the concrete AI-generation command/parameters for the doubao-seedream step rather than only saying 'call the API to generate'.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient but includes padded sections (success-case name-drops, a promotional footer, repeated upload-script examples in multiple sections, and 4 FAQ items that restate earlier content), so it is mostly tight with notable trim opportunities.	3 / 5
Actionability	It gives concrete, executable commands (the python3 upload_image.py invocation, grep verification) with mostly copy-paste-ready examples, though the hardcoded absolute /Users/alchain path and AI-generation step are left as placeholders rather than full commands.	4 / 5
Workflow Clarity	The 5-step standard flow is explicitly sequenced with a verification checkpoint (Step 5: grep the markdown and confirm all links are https://), plus a pre-flight checklist and explicit error fallback (ImgBB failure → original URL), satisfying the validation-loop requirement for batch operations.	5 / 5
Progressive Disclosure	Content is organized into clear sections and lists four reference resources, but no references/, scripts/, or assets/ bundle files exist and the referenced /tools/* and /公众号写作/* paths are external/absolute rather than one-level-deep bundle links, so structure is present but signaling is weak.	3 / 5
	Total	15 / 20 Passed

Description

83%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 concise, third-person, and clearly answers both what and when with natural trigger terms. It is well above the midpoint but stops just short of fully comprehensive coverage of synonyms and edge-case triggers.

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete actions (一键生成, 上传图床, 自动插入Markdown链接), but the actions are framed at a moderate level rather than a comprehensive list of distinct capabilities.	4 / 5
Completeness	It explicitly answers both what the skill 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), matching the top anchor's requirement for concrete trigger phrases.	5 / 5
Trigger Term Quality	It lists natural trigger phrases a user would say ("配图", "插图", "上传图片", "文章配图") with good coverage, though a few synonyms (e.g. "图片") and file/extension terms are absent.	4 / 5
Distinctiveness Conflict Risk	The image-generation-and-upload-to-imgbed niche is fairly distinct with specific triggers, but it could marginally overlap with a generic image/asset skill.	4 / 5
	Total	17 / 20 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: 49a55ba

Reviewed: 9 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.