mafengwo-original-images
Download original-size images from Mafengwo photo and travel-note pages. 用于从马蜂窝图片页或游记页提取原图链接、下载原图、导出链接和文件大小清单,并支持断点续下与校验。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Download original-size images from Mafengwo photo and travel-note pages. 用于从马蜂窝图片页或游记页提取原图链接、下载原图、导出链接和文件大小清单,并支持断点续下与校验。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Initialize a Java Maven Spring Boot project scaffold into an empty directory (or add a new child module to an existing one). Generates parent/child POM, logback, layered application config, README, docs/ skeleton, test skeleton, Dockerfile/build.sh/run.sh/rollback.sh, Jenkinsfile, build-readiness checklist, and a .dev-flow.yml seed (with scaffold block + build-credentials) plus project-level state .dev-flow/project.json wired into dev-lifecycle as the project-level cascade-0 node. Template + mixin architecture: each project type (java-web / java-mcp) is a self-contained independent template with zero inheritance, eliminating javax/jakarta version residue. Triggered when the current project folder is empty OR the user explicitly asks to create a child module; when uncertain, ask first.
Orchestrate dev-spec, git-flow, ci-trigger into a resumable development lifecycle with evidence-backed specs, step-by-step implementation, Review Loop, and Auto Cascade. 编排证据化 spec、步骤化开发、分支生命周期和 Jenkins 测试部署。
Trigger Jenkins builds, monitor long-running packaging flows, fetch failure logs, analyze errors, and optionally notify DingTalk. 触发 Jenkins 构建、监控长流程、拉取失败日志、分析原因并可选通知钉钉。
Turn conversations, requirement documents, API docs, local PDF/DOCX files, and prototype images into evidence-backed development specs with implementation steps. 将需求对话、对接文档、API 文档、本地 PDF/DOCX 和原型图整理为可开发、可测试、可追踪的 spec。
Manage single feature branch lifecycle: init, step-aware commit, push, and integrate into test branch with smart conflict handling. 管理单 feature 分支创建、按实施步骤提交、推送、合并测试分支的生命周期。
A domain-agnostic thinking-partner method for turning any immature idea into a complete, implementable manuscript through deliberate divergence then convergence. NOT a software skill — software is merely one example domain; it applies equally to research design, business strategy, product, writing, policy, planning, and any open-ended problem you can't yet see whole. Invoke when the user brings a half-formed idea, says 先扩散后收敛 / 扩散收敛 / diverge-converge, wants the full picture before committing, or wants a multi-turn exploration distilled into a handoff document. 一套领域无关的通用思维方法:把任何不成熟的想法通过先扩散后收敛,逐步逼近成一份可实施的手稿,不限于软件构建。
| name | mafengwo-original-images |
| description | Download original-size images from Mafengwo photo and travel-note pages. 用于从马蜂窝图片页或游记页提取原图链接、下载原图、导出链接和文件大小清单,并支持断点续下与校验。 |
当用户提供马蜂窝图片页、游记页或类似页面,并要求下载网页图片时,使用本 skill 提取原始图片链接、去掉缩略图参数、下载原图,并导出:
original_image_links.txt
images/
summary.json
original_image_links.txt 必须使用以下格式,每行一个原图链接和文件大小,逗号拼接:
https://note.mafengwo.net/img/xx/yy/example.jpeg,1.5M
当用户说出类似需求时触发:
? 及其后面的压缩、裁剪、质量参数,例如去掉 imageView2%2F2%2Fw%2F600%2Fq%2F50。YYYYMMDD图片下载-地点或网页标题-原图。意大利;没有可靠地点时使用网页标题。original_image_links.txt。original_image_links.txt 每行格式为 原始链接,文件大小M,例如 https://note.mafengwo.net/img/xx/yy/example.jpeg,1.5M。data-original, data-src, data-url, data-rt-src, src.note.mafengwo.net/img/...。? 及其后面的所有内容。raw_image_links.txt,再调用下载脚本。scripts/download_original_images.py 完成下载、断点续下、大小统计和清单生成。? 或 imageView2。优先使用宿主 agent 提供的浏览器自动化能力提取渲染后的图片链接。如果没有可用自动化能力,先在普通浏览器完成页面验证,再把以下代码粘贴到 DevTools Console:
copy([...new Set([...document.images]
.map(img => img.dataset.original || img.dataset.src || img.dataset.url || img.dataset.rtSrc || img.src)
.filter(Boolean)
.map(url => url.startsWith("//") ? `https:${url}` : url)
.filter(url => /^https?:\/\//.test(url))
.filter(url => /\.(jpe?g|png|webp|gif)(\?|$)/i.test(url))
.filter(url => /note\.mafengwo\.net\/img\//.test(url))
)].join("\n"))
将复制出来的内容保存为 raw_image_links.txt。
python3 scripts/download_original_images.py \
--url "https://www.mafengwo.cn/photo/10051/scenery_24796451_1.html" \
--raw-links raw_image_links.txt \
--place "意大利" \
--page-title "从佛罗伦萨到多洛米蒂,繁花盛开的序曲" \
--out-root .
脚本会执行以下工作:
original_001.jpeg、original_002.png 等。M 为单位写入文件大小,例如 0.2M、1.5M。summary.json 和 download_check.json。下载完成后运行:
wc -l original_image_links.txt
find images -type f | wc -l
grep -nE 'imageView2|\?' original_image_links.txt
du -sh .
预期结果:
grep 检查 imageView2 或 ? 时没有任何输出。download_check.json 中 missing 和 invalid 都为 0。本 skill 的 SKILL.md 保持 agent-neutral:只描述任务流程、输入输出和校验标准,不绑定某个 agent 的私有工具。需要适配具体 agent 时,只读取对应 adapter:
adapters/claude-code.mdadapters/openclaw.mdadapters/codex.mdadapters/generic-browser.md