') + ')', 'gi'); if (regex.test(text)) { found = true; var frag = document.createDocumentFragment(); var parts = text.split(regex); parts.forEach(function(part, i) { if (i % 2 === 0) { frag.appendChild(document.createTextNode(part)); } else { var span = document.createElement('span'); span.className = 'userscript-highlight'; span.textContent = part; frag.appendChild(span); } }); node.parentNode.replaceChild(frag, node); } }); } else if (node.nodeType === 1 && node.childNodes) { // element var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT']; if (!skipTags.includes(node.tagName)) { Array.from(node.childNodes).forEach(highlight); } } } highlight(document.body); // Re-highlight on dynamic content var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1 || node.nodeType === 3) highlight(node); }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Strip utm_, fbclid, gclid, etc. from all links on page (function() { var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content', 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid', 'ref', 'ref_src', 'source', 'medium', 'campaign']; function cleanUrl(url) { try { var u = new URL(url, window.location.origin); var changed = false; trackingParams.forEach(function(p) { if (u.searchParams.has(p)) { u.searchParams.delete(p); changed = true; } }); return changed ? u.toString() : url; } catch (e) { return url; } } function cleanLinks() { document.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } cleanLinks(); var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1) { if (node.tagName === 'A') cleanLinks(); node.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Auto-enable theater mode on YouTube (function() { function tryTheater() { var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]'); if (btn && !btn.classList.contains('activated')) { btn.click(); } } // Try immediately tryTheater(); // Try after navigation (SPA) var lastUrl = location.href; setInterval(function() { if (location.href !== lastUrl) { lastUrl = location.href; setTimeout(tryTheater, 500); } }, 1000); // Also try on player load var observer = new MutationObserver(tryTheater); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Remove or un-stick sticky/fixed headers that block content (function() { function unstick() { document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) { if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') { el.style.position = 'static'; el.style.top = 'auto'; el.style.zIndex = 'auto'; } }); } unstick(); var observer = new MutationObserver(unstick); observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] }); })(); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); })(); 【案例】电商产品出图Skill · Issue #19 · modelstudioai/modelstudioai.github.io · GitHub
Skip to content

【案例】电商产品出图Skill #19

Description

我做了什么

用 Clacky AI Agent 自动创建了一个「电商产品出图」Skill,实现从需求追问→素材分析→Prompt工程→调用百炼CLI生图→迭代优化的全流程自动化。

Skill 的核心能力:

  • 智能判断信息是否充分,最少追问、最快出图
  • 有素材图时自动调用 vision 理解产品,再构造精准 prompt
  • 内置 7 层质量基底词(8K/写实/光影/色彩/完整性/细节一致/输出控制),每次自动注入
  • 支持 8 大品类风格词库 + 6 大平台规则适配
  • 支持单图迭代和套图模式(5图标准电商套图)
  • 用户说"太假""太亮""不够高级"等模糊反馈时,能精准映射到 prompt 调整

使用的工具

  • OpenWork / 百炼 CLI
  • Skill 名称:ecommerce-image
  • 其他:Clacky AI Agent(skill-creator 自动生成 + 多轮迭代优化)

效果展示

Skill 已部署在 ~/.clacky/skills/ecommerce-image/,可通过对话触发或 WebUI /ecommerce-image 调用。

工作流示意:

用户:"帮我做几张蓝牙耳机白底主图,高级感"
↓
Agent 自动:
1. 判断信息充分 → 不追问
2. 选择 image generate 路线 + 1:1 尺寸
3. 构造英文 prompt(产品描述 + 白底词 + 高级感词 + 质量基底)
4. 注入完整 negative prompt
5. 调用 `bailian image generate --n 3 --watermark false --prompt-extend false`
6. 交付3张图 + 逐张点评 + 迭代引导

支持的 prompt 质量层级:

  • 质量基底层(8K/professional/sharp)
  • 真实性层(photorealistic/PBR/natural light)
  • 完整性层(no cropping/correct perspective)
  • 光影层(HDR/cinematic/soft shadows)
  • 色彩层(balanced exposure/natural white balance)
  • Negative 层(40+ 常见翻车词全覆盖)

踩坑记录(可选)

  1. npm 包名:百炼 CLI 的 npm 包名是 bailian-cli,但安装后的命令是 bailian(不是 bailian-cli),一开始找不到命令
  2. prompt-extend 必须关闭:不加 --prompt-extend false 时,模型会自行扩写 prompt,导致生成结果偏离用户意图
  3. 质量词不是越多越好:最初堆了 7 层分开注入(每层一段),后来发现合并为一段效果更好,避免 prompt 过长被截断
  4. Negative prompt 很关键:电商图最常见问题是出现文字/水印/变形,需要在 negative 中全面覆盖

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions