image-upload
Skill46 starsChanged 3 months agoMITView on GitHub
scan a document's local image references and upload to ImgBB / Freeimage / UploadMe / ImgLink, replacing links in-place. Use when the user says "上传图片", "replace local image links", "全量转存", "mirror images", "scan and upload images", "图床化".
- Reads credentials
3 other projects use a version of this.
Adopted by
Most recently taken up by
- iamzifei/image-upload-skilltheir own version, first seen Aug 12, 2026
- Isaac-Flath/agent-starter-skillstheir own version, first seen Apr 12, 2026
- jjenkins/agent-image-skillstheir own version, first seen Mar 1, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- Isaac-Flath/agent-starter-skills★ 8same name
- iamzifei/image-upload-skill★ 6same name
- jjenkins/agent-image-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- dify-deploySkill
- dify-workflowSkill
- frontend-reviewSkill
- github-star-managerSkill
- ideological-self-reportSkill
- mkdocs-shadcnSkill
The file
Files
图床化 Skill
扫描文档(Markdown / HTML)中的本地图片引用,上传至图床,将本地路径替换为远程 URL。
执行步骤
Step 1 — 确定模式
根据用户意图选择模式:
- document 模式:用户指定一篇文档 → 扫描其中的本地图片引用(
/<img src="...">) - single 模式:用户指定单张图片文件 → 直接上传,返回 URL
- mirror 模式:用户要求"全量转存"/"把文档里所有图片(含网络图片)搬到我的图床" → 扫描本地 + 文档内已有的远程 URL 图片,一并转存
完成标准:模式已确定,目标文件路径 / 图片路径已明确。
Step 2 — 加载配置
运行 node scripts/upload.mjs --help 确认脚本可用,然后查找 .env 文件(搜索顺序:当前目录 → Skill 目录 → ~/.claude/ → ~/)。
读取 IMAGE_UPLOAD_PROVIDER(默认 imglink)和对应的 API Key 环境变量。
如果 API Key 缺失(出现 Missing *_API_KEY 错误):
- 展示对应图床的 API Key 获取链接(见
references/providers.md) - 询问用户粘贴 Key
- 将 Key 写入
.env文件(优先写到项目目录;如不存在则写到~/.claude/.env) - 静默重试上传
完成标准:API Key 已就绪,provider 已确认;或用户明确放弃。
Step 3 — 上传
根据模式调用脚本:
# document 模式(仅打印映射表)
node scripts/upload.mjs /path/to/document.md
# document 模式(原地替换链接)
node scripts/upload.mjs /path/to/document.md --replace
# mirror 模式(含网络图片,原地替换)
node scripts/upload.mjs /path/to/document.md --mirror --replace
# single 模式
node scripts/upload.mjs /path/to/image.pngSVG / AVIF / 大文件:SVG、ICO 仅 ImgLink 支持,AVIF 仅 ImgLink 与 UploadMe 支持;超过当前 provider 单文件上限(ImgLink 50MB / ImgBB 32MB / Freeimage 64MB / UploadMe 64MB)时切换到支持的 provider(详见 references/providers.md)。四家都不支持时跳过该图并保留原链接。
mirror 幂等:若远程图片的 host 已是目标图床域名,跳过再次转存。
完成标准:所有扫描到的图片都有上传结果(成功 URL 或明确的跳过理由),无遗漏。
Step 4 — 输出结果
- document 模式(无
--replace):输出映射表本地路径 → 远程直链 → Markdown 引用 - document 模式(有
--replace):确认文档已写回,报告替换数量 - single 模式:返回 URL、
、<img src="url">、[IMG]url[/IMG]
完成标准:结果已展示给用户;替换模式下文档已实际写回磁盘。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

