claude-seo 图像生成提示词工程实战基于 Claude Banana 的六组件推理简报与领域模式提示词体系【免费下载链接】claude-seoUniversal SEO skill for Claude Code. 26 sub-skills 19 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, agent readiness (Lighthouse Agentic Browsing, WebMCP, llms.txt), backlinks, local SEO, e-commerce, international SEO, Google APIs, and PDF/Excel reporting. 9 optional extensions for live SEO data.项目地址: https://gitcode.com/GitHub_Trending/cl/claude-seo本文面向在 claude-seo 项目中使用seo-image-gen技能基于 Gemini 图像生成模型、经 nanobanana MCP 驱动的 Claude Banana 流水线的开发者与 SEO 从业者。全文围绕 prompt-engineering.md 这套提示词工程参考展开系统讲解六组件推理简报6-Component Reasoning Brief、九大领域模式修饰库、高级技巧、跨模型提示词迁移规则、经 2500 条提示词验证的成熟模板以及安全过滤器改写策略读完你能够为 OG 图、博客头图、产品图、信息图等 SEO 资产编写出可稳定复现的高质量生成提示词并理解这些提示词在仓库中的真实执行链路。文档在技能体系中的定位在 claude-seo 仓库中SKILL.md 将这套提示词方法定义为生成流水线的核心步骤之一构造 Reasoning Brief 时加载references/prompt-engineering.md使用六组件系统并按领域模式分配权重Subject 30%、Style 25%、Context 15% 等。因此这份参考文档不是孤立的写作技巧而是seo-image-gen每次调用gemini_generate_image之前的必经环节。本文按原文档骨架逐节展开并在关键处补充 generate.py、presets.py、batch.py 等源码证据帮助你理解提示词→API 请求→图片产出的完整链路。六组件推理简报6-Component Reasoning Brief文档明确了一条硬性规则每个图像提示词都应包含以下六个组件并以自然叙事段落书写绝不使用逗号分隔的关键词列表。关键词列表丢掉了组件之间的逻辑关系模型只能堆砌元素而非理解场景。1. Subject主体主体的核心是物理细节的具体性——年龄、肤质、皱纹、手部状态等可被看见的特征而不是类别标签。GoodA weathered Japanese ceramicist in his 70s, deep sun-etched wrinkles mapping decades of kiln work, calloused hands cradling a freshly thrown tea bowl with an irregular, organic rimBadold man, ceramic, bowl2. Action动作描述正在发生的事情运动、姿态、手势、存在状态。用动词让画面活起来。Goodleaning forward with intense concentration, gently smoothing the rim with a wet thumb, a thin trail of slip running down his wristBadmaking pottery3. Context环境环境、场所、时间与空间细节负责建立可信的世界观。Goodinside a traditional wood-fired anagama kiln workshop, stacked shelves of drying pots visible in the soft background, late afternoon light filtering through rice paper screensBadworkshop, afternoon4. Composition构图镜头角度、景别、取景方式、空间关系。没有构图指令的默认结果是居中构图。Goodintimate close-up shot from slightly below eye level, shallow depth of field isolating the hands and bowl against the soft bokeh of the workshop behindBadclose up5. Lighting灯光光源、光线质量、方向、色温、阴影。这是文档反复强调的最大质量分水岭见常见错误第 3 条。Goodwarm directional light from a single high window camera-left, creating gentle Rembrandt lighting on the face with a soft triangle of light on the shadow-side cheek, deep warm shadows in the workshopBadnatural lighting6. Style风格艺术媒介、美学参照、摄影技术细节。命名真实设备与经典美学参照比空洞的写实、8K、杰作有效得多。Goodcaptured with a Sony A7R IV, 85mm f/1.4 GM lens, Kodak Portra 400 color grading with lifted shadows and muted earth tones, reminiscent of Dorothea Langes documentary portraitureBadphotorealistic, 8K, masterpiece与源码的印证在 generate.py 中提示词作为contents[0].parts[0].text原样传给 Gemini 的generateContent接口模型只拿到一段纯文本。这解释了为什么叙事段落而非标签堆砌如此重要——API 层没有任何额外的关键词解析或权重修饰全部语义负担都落在自然语言本身。领域模式修饰库Domain Mode Modifier Libraries针对不同图像类型文档提供九套可直接引用的修饰词库。它们的作用是把六组件中的 Style/Composition/Lighting 等组件填充到该领域可被模型识别的行话粒度。Cinema Mode电影模式相机规格RED V-Raptor、ARRI Alexa 65、Sony Venice 2、Blackmagic URSA镜头Cooke S7/i、Zeiss Supreme Prime、Atlas Orion anamorphic胶片Kodak Vision3 500T钨丝灯、Kodak Vision3 250D日光、Fuji Eterna Vivid布光方案三点布光、明暗对照chiaroscuro、伦勃朗光、分割光、蝴蝶光、轮廓/逆光景别建立性远景、中近景、极限特写、荷兰角、俯拍摇臂、斯坦尼康跟拍调色青橙、去饱和冷调、温暖复古、高对比黑色电影Product Mode产品模式表面抛光大理石、拉丝混凝土、原色亚麻、亚克力台座、渐变背景灯光柔光箱漫射、硬光主光补光板、轮廓分离、帐篷光tent lighting、光绘角度45 度主视觉、俯拍平铺、四分之三、正对、虫眼视角风格参照Apple 产品摄影、Aesop 极简、Bang Olufsen 简洁、奢侈美妆Portrait Mode人像模式焦段85mm经典、105mm压缩感、135mm长焦、50mm环境人像光圈f/1.4梦幻虚化、f/2.8主体锐利、f/5.6环境交代姿态语言抓拍中途手势、直面镜头的对抗性、剪影侧面、过肩回望肤质/纹理可见雀斑、微距下的毛孔、眼中的眼神光、次表面散射Editorial/Fashion Mode编辑/时尚模式出版物参照Vogue Italia、Harpers Bazaar、GQ、National Geographic、Kinfolk造型要点层次质感、标志性配饰、单色配色、对比图案场景大理石楼梯、金色时刻天台、工业 loft、沙漠沙丘、霓虹小巷姿态力量站姿、放松编辑式斜倚、运动模糊、风中织物UI/Web Mode界面/网页模式风格扁平矢量、等距 3D、线条艺术、玻璃拟态、新拟态、Material Design颜色指定精确 hex 或描述性色板如 cool blues #2563EB to #1E40AF尺寸按 2x 为 retina 设计指明需要的精确像素尺寸背景透明先要纯白背景再后期处理、渐变、纯色Logo Mode标志模式构造几何原语、黄金比例、网格制图、负空间字体粗体无衬线、优雅衬线、定制字标、字母组合颜色最多 2-3 色、可单色化、高对比输出要求纯白背景生成后期处理为透明Landscape Mode风景模式景深分层前景兴趣点、中景主体、背景氛围大气效果雾、薄雾、霾、体积光柱、尘埃粒子时段蓝调时刻黎明前、金色时刻、魔法时刻日落后、午夜蓝天气戏剧性暴风云、雨后转晴、积雪、阳光斑驳Infographic Mode信息图模式布局模块化分区、清晰视觉层级、bento 网格、自上而下流向文字用引号包裹精确文本、描述性字体风格、指明字号层级数据可视化柱状图、饼图、流程图、时间线、对比表格颜色高对比、无障碍配色、一致的品牌色Abstract Mode抽象模式几何分形、沃罗诺伊镶嵌、螺旋、斐波那契、有机流动、晶体纹理大理石纹路、流体动力学、烟雾卷须、墨水扩散、水彩晕染色板类比和谐、互补冲突、单色渐变、霓虹衬黑风格生成艺术、数据可视化艺术、故障艺术、程序化、材料微距摄影实战建议结合 SEO 用例表原文档在 SKILL.md 的用例映射中为每种 SEO 资产指定了领域模式——OG/Social 预览用 Product 或 UI/Web博客头图用 Cinema 或 Editorial产品图用 Product信息图用 InfographicFavicon 用 Logo。选择领域模式时应先查用例表确定模式再用上方修饰库填充细节。高级技巧Advanced Techniques多轮角色一致性Character Consistency使用gemini_chat保持会话上下文并通过描述锚点维持角色稳定第一轮用详尽的物理描述生成角色后续轮引用同一个角色 重复 2-3 个关键标识关键标识发色/发型、标志性服装、面部特征多图参考技术3.1 Flash在对话中提供最多 4-5 张角色参考图为每个角色分配名字Character A: the red-haired knight模型在不同角度、动作、环境中保持角色特征参考图若覆盖多个角度效果最佳源码支撑gemini_chat是 nanobanana MCP 提供的能力见 mcp-tools.md其核心卖点正是会话一致性——跨轮次保持风格、角色与上下文。这也解释了文档错误清单第 10 条不要试图一次生成就做到完美的原因迭代式精修依赖的就是会话上下文。无参考图的风格迁移Style Transfer Without Reference Images详尽描述目标风格替代引用图片Render this scene in the style of a 1950s travel poster: flat areas of color in a limited palette of teal, coral, and cream. Bold geometric shapes with visible paper texture. Hand-lettered title text with a mid-century modern typeface feel.文本渲染技巧Text Rendering Tips精确引用文本with the text OPEN DAILY in bold condensed sans-serif25 个字符以内是可靠渲染的实际上限最多 2-3 个独立短语更多文本片段会显著降低质量描述字体特征而非字体名称指明位置centered at the top third、along the bottom edge高对比深底浅字或反之文本优先 hack先在对话中以对话方式确立文本概念I need a sign that says FRESH BREAD再生成——模型会锚定早期提到的文本预期字体会被创造性诠释而非精确复刻与模型文档的交叉印证文本渲染上限在 gemini-models.md 中被再次确认Text rendering supported - best under 25 characters并在常见错误第 8 条中作为独立失分项列出。正面表述Positive Framing不使用否定提示词Gemini 不支持 negative prompt。将排除性表述改写为正面表述不要写改写为no blursharp, in-focus, tack-sharp detailno peopleempty, deserted, uninhabitedno textclean, uncluttered, text-freenot darkbrightly lit, high-key lighting搜索增强生成Search-Grounded Generation基于真实世界数据天气、事件、统计的图像可借助 Google Search grounding 引入实时信息特别适合含当前数据的信息图。三段式公式[Search/source request]要查什么[Analytical task]要分析/提取什么[Visual translation]如何渲染成图像示例Search for the current top 5 programming languages by GitHub usage in 2026, analyze their relative popularity percentages, then generate a clean infographic bar chart with the language logos and percentages in a modern dark theme.该能力在 API 层由tools: [{googleSearch: {}}]启用见 gemini-models.md是否可用取决于 MCP 包版本对 search grounding 的支持见 mcp-tools.md 的功能可用性表。从 Midjourney/DALL-E 到 Gemini 的提示词迁移规则当从 claude-prompts 数据库Midjourney/DALL-E 等迁移提示词到 Gemini 自然语言格式时按下表逐项映射源语法Gemini 等价写法--ar 16:9单独调用set_aspect_ratio(16:9)--v 6、--style raw移除——Gemini 没有版本/风格参数--chaos 50描述多样性unexpected, surreal composition--no trees正面表述open clearing with no vegetation(word:1.5)权重描述性强调prominently featuring [word]8K, masterpiece, ultra-detailed只保留 ultra-realistic, high resolution其余删除逗号分隔标签扩展为描述性叙事段落shot on Hasselblad保留——相机规格在 Gemini 中有效关键洞察这张表背后是两种完全不同的提示词哲学——Midjourney 用参数化标志flag控制生成Gemini 用自然语言承载全部语义。第 5 行权重语法→描述性强调的映射说明(word:1.5)这类权重控制没有直接等价物只能通过位置和措辞prominently featuring来传递重要性。十大常见提示词错误关键词堆砌堆叠通用质量词8K, masterpiece, best quality毫无增益只在结尾使用 ultra-realistic, high resolution标签列表Gemini 要散文不要 red car, sunset, mountain, cinematic缺少灯光描述这是最大的质量分水岭没有构图指令结果就是千篇一律的居中构图风格含糊make it look cool 对比具体的艺术方向忽略宽高比始终在生成前设置提示词过长超过约 200 词后收益递减要精准而非冗长文本超过约 25 字符超出后渲染质量急剧下降关键细节埋在末尾长提示词中靠后的细节可能被降权把关键信息精确文本、关键约束放在提示词前三分之一不通过后续提示词迭代用gemini_chat渐进精修而不是试图一次生成搞定一切源码验证第 6 条generate.py 定义了 14 种合法宽高比集合VALID_RATIOS1:1、16:9、9:16、4:3、3:4、2:3、3:2、4:5、5:4、1:4、4:1、1:8、8:1、21:9并在 L148-L154 做运行时校验——传入非法比值会直接报错退出。在 MCP 路径下则通过set_aspect_ratio在生成前设置mcp-tools.md 列出全部 14 种。因此忽略宽高比不仅损失构图质量还可能触发参数校验失败。经过验证的提示词模板库Proven Prompt Templates以下模式从 2500 条测试过的提示词中提取持续产出高质量结果。以它们为起点按需求调整。获胜公式Winning Formula权重分配组件权重包含内容Subject主体40%年龄、肤色、发色/发型、瞳色、体型、表情Styling造型25%品牌名、纹理、版型、配饰、颜色Environment环境15%地点 时段 情境细节Camera相机10%相机型号 镜头 焦段 景别Lighting灯光10%质量、方向、色温、阴影注意此权重表是提示词内的组件分布建议seo-image-gen流水线在 SKILL.md 中另有领域模式强调权重Subject 30%、Style 25%、Context 15% 等二者角度不同——前者教怎么写后者教按领域怎么侧重使用时互为补充。Instagram 广告 / 社交媒体模式[带年龄/外貌的主体] [带品牌/质感的服装] [动作动词] [场景] [相机规格] [灯光] [平台美学]示例产品植入Hyper-realistic gym selfie of athletic 24yo influencer with glowing olive skin, wearing crinkle-textured athleisure set in mauve. iPhone 16 Pro Max front-facing portrait mode capturing sweat droplets on collarbones, hazel eyes enhanced by gym LED lighting. Mirror reflection shows perfect form, golden morning light through floor-to-ceiling windows. Frayed chestnut ponytail with baby hairs, ultra-detailed skin texture, trending aesthetic.示例生活方式广告A 24-year-old blonde fitness model in a high-energy sports drink advertisement. Mid-run on a beach, wearing a vibrant orange sports bra and black shorts, playful smile and sparkling blue eyes exuding vitality. Bottle of the drink held in hand, waves crashing in background. Shot on Nikon D850 with 70-200mm f/2.8 lens, natural light, fast shutter speed capturing motion. Ultra-realistic skin texture, water droplets, product label clearly visible.示例奢华生活方式Gorgeous Instagram model wearing a designer silk gown, luxury rooftop restaurant, golden hour lighting, champagne in hand, luxurious aspirational lifestyle. Captured with Sony A7R IV, 85mm f/1.4 lens, shallow depth of field, warm color grading.产品 / 商业摄影模式[带品牌/细节的产品] [动态元素] [表面/场景] commercial photography for advertising campaign [灯光] high resolution示例饮品Gatorade bottle with condensation dripping down the sides, surrounded by lightning bolts and a burst of vibrant blue and orange light rays. The Gatorade logo is prominently displayed on the bottle, with splashes of water frozen in mid-air. Commercial food photography for an advertising campaign, high resolution, high level of detail, vibrant complementary colors.示例食品In and Out burger with layers of fresh lettuce, melted cheese, and pretzel bun, placed on a white surface with the In and Out logo subtly glowing in the background. Falling french fries and golden light, warm scene. Commercial food photography for an advertising campaign, high resolution, high level of detail, vibrant complementary colors.时尚 / 编辑模式[带族裔/年龄/特征的模特] [带质感/品牌/剪裁的服装] [地点] [姿态/动作] [相机 镜头] [灯光质量]示例街拍A 24-year-old female AI influencer posing confidently in an urban cityscape during golden hour. Flawless sun-kissed skin, long wavy brown hair, deep green eyes. Wearing a chic streetwear outfit: oversized beige blazer, white top, high-waisted jeans. Captured with Sony A7R IV at 85mm f/1.4, shallow depth of field with warm golden bokeh.示例高级时装Stunning 24-year-old woman, long platinum blonde hair, radiant skin, piercing blue eyes, dressed in a chic pastel blazer with a modern minimalist aesthetic, soft sunlight glow, high-end fashion appeal. Shot on Canon EOS R5, 85mm f/1.2 lens.示例先锋A blonde fitness model transformed into a runway-ready fashion icon, wearing a bold avant-garde outfit: cropped leather jacket with neon pink accents, paired with high-waisted athletic shorts and knee-high boots. Captured mid-stride on a minimalist white runway, playful twinkle in her eye, dramatic studio lighting from above.SaaS / 科技营销模式[UI 稿或抽象视觉] on [深/浅] background [带 hex 的具体颜色] [字体描述] clean, premium SaaS aesthetic [玻璃拟态/渐变/辉光效果]示例仪表盘主视觉A floating glassmorphism UI card on a deep charcoal background showing a content analytics dashboard with a rising line graph in teal (#14B8A6), bar charts in coral (#F97316), and a circular progress indicator at 94%. Subtle grid lines, frosted glass effect with 20% opacity, teal glow bleeding from the card edges. Clean premium SaaS aesthetic, no text smaller than headline size.示例功能亮点An isometric 3D illustration of interconnected data nodes on a dark navy background. Each node is a glowing teal sphere connected by thin luminous lines, forming a constellation pattern. One central node pulses brighter with radiating rings. Modern tech illustration style with subtle depth of field, volumetric lighting from below.示例对比/前后对照Split-screen image: left side shows a cluttered, dim workspace with scattered papers, red error indicators, and a frustrated expression conveyed through a cracked coffee mug and tangled cables. Right side shows a clean, organized dashboard interface glowing in teal and white on a dark background, with smooth flowing lines and checkmarks. A sharp vertical dividing line separates chaos from clarity.Logo / 品牌模式[产品/瓶装/物品] with [品牌元素] prominently displayed [动态视觉元素] commercial photography [灯光风格] high resolution, vibrant complementary colors示例A sleek matte black bottle with a minimal white logo mark centered on the label, surrounded by swirling gradient ribbons of teal and coral light. The bottle sits on a reflective dark surface, sharp studio rim lighting separating it from the background. Product photography for luxury branding, high resolution, dramatic contrast.让提示词真正起效的关键战术Key Tactics点名真实相机Sony A7R IV、Canon EOS R5、iPhone 16 Pro Max 锚定真实感指定精确镜头85mm f/1.4 给模型精确的景深信息使用年龄 族裔 特征24yo with olive skin, hazel eyes 远胜 a person品牌锚定造型Lululemon mat、Tom Ford suit 触发特定视觉联想包含微细节sweat droplets on collarbones、baby hairs stuck to neck添加平台语境Instagram aesthetic、commercial photography for advertising描述质感crinkle-textured、metallic silver、frosted glass使用动作动词mid-run、posing confidently、captured mid-stride结尾用 ultra-realistic, high resolution这两个锚点在 Gemini 上有效避免 8K, masterpiece, best quality 这类无价值的通用堆叠产品图要写 prominently displayed确保产品/logo 不被隐藏反模式不要这样做A dark-themed Instagram ad showing...过于元层面描述的是概念而非画面A sleek SaaS dashboard visualization...抽象没有视觉锚点Modern, clean, professional...对模型毫无意义的模糊形容词A bold call to action with...描述营销意图而非视觉内容描述观者应该有什么感受改为描述什么创造了那种感受安全过滤器改写策略Safety Filter Rephrase StrategiesGemini 的安全过滤器Layer 2服务端输出过滤器无法关闭。提示词被拦截时唯一出路是改写。常见触发类别类别触发内容改写思路暴力/武器战斗、血腥、受伤、枪械使用隐喻或后果描述battle-worn → weathered veteran医疗/血腥手术、伤口、解剖细节抽象化或临床化open wound → medical illustration真实公众人物指名道姓的名人、政客使用原型Elon Musk → a tech entrepreneur in a minimalist office儿童风险未成年人处于任何模糊情境添加安全语境说明教育、家庭或玩乐式框架色情/暗示暴露服装、亲密姿态艺术化框架fashion editorial, fully clothed, editorial pose五种改写模式抽象化Abstraction把具体危险元素替换为抽象概念艺术框架Artistic framing把内容框定为艺术、编辑或纪录片隐喻Metaphor用象征性语言替代字面描述正面强调Positive emphasis描述存在什么而非危险的是什么语境转移Context shift从威胁性语境转移到教育/专业语境改写示例对照被拦截的提示词成功改写a soldier in combat firing a riflea determined soldier standing guard at dawn, rifle slung over shoulder, morning mist over the outposta scary horror monstera fantastical creature from a dark fairy tale, intricate organic textures, bioluminescent accents, concept art styledog in a fighta friendly golden retriever playing energetically in a sunny park, action shot, joyful expressionmedical surgery scenea clean modern operating room viewed from the observation gallery, soft blue surgical lights, professional documentary stylecelebrity portrait of [name]a distinguished middle-aged man in a tailored navy suit, warm studio lighting, editorial portrait style关键原则Layer 2输出过滤器分析的是生成的图像本身而非仅提示词。即使提示词措辞完美模型解读方式若触发输出过滤器仍会被拦截。此时应把视觉概念整体向远离触发点的方向移动而不是只换措辞。在流水线中的表现拦截在 generate.py 中体现为promptFeedback.blockReason或候选为空直接以错误退出SKILL.md 的 错误处理表 明确IMAGE_SAFETY的解决方式是改写提示词——见 prompt-engineering 的安全章节。同时 gemini-models.md 记录了一个已知问题过滤器过度谨慎良性提示词也可能被拦截需要改写措辞迭代。建议在改写前先用 SKILL.md 的成本意识流程记录一次失败尝试避免反复试错产生无效费用。提示词如何进入生成流水线源码级串联把上述技巧落到实际执行完整链路如下依据 SKILL.md 的 Generation Pipeline识别用例由命令或上下文判断og、hero、product、infographic、custom、batch映射到预配置参数应用 SEO 默认值用例表决定宽高比、分辨率与领域模式如 OG 图 16:9/1K/Product信息图 2:3/4K/Infographic检查预设python3 scripts/presets.py list查看品牌预设presets.py 将预设存储为~/.banana/presets/NAME.jsoncreate子命令支持--colors/--style/--typography/--lighting/--mood/--ratio/--resolution参数品牌预设覆盖 SEO 默认值的颜色/情绪/字体但宽高比与分辨率始终由 SEO 预设兜底见 seo-image-presets.md 的选择逻辑设置宽高比MCP 路径调set_aspect_ratio直连 API 路径由--aspect-ratio传入并在 generate.py 校验 14 种合法值构造 Reasoning Brief加载本提示词工程参考按六组件叙事段落编写应用领域模式权重侧重生成MCP 调gemini_generate_imageMCP 不可用时回退python3 scripts/generate.py --prompt ... --aspect-ratio 16:9 --resolution 1K --model gemini-3.1-flash-image-previewgenerate.py 的请求体会把responseModalities设为[TEXT,IMAGE]可选thinkingConfig.thinkingLevel并自动在错误输出中脱敏 Google API Key批量场景batch.py 解析 CSV必需prompt列可选ratio/resolution/model/preset输出结构化计划 JSON 并附带estimated_cost总估算——这正是文档成本透明原则的实现成本记账python3 scripts/cost_tracker.py log --model MODEL --resolution RES --prompt brief记录每次生成cost_tracker.py 按模型分辨率查价如 3.1 Flash 1K 约 $0.039、4K 约 $0.156写入~/.banana/costs.json生成后 SEO 清单alt text、SEO 文件名keyword-description-widthxheight.webp、WebP 转换magick output.png -quality 85 output.webp、文件体积目标头图 200KB、缩略图 100KB、ImageObject结构化数据与og:image标签——后处理的具体 ImageMagick/FFmpeg 配方见 post-processing.md其中 4K 输出建议直接以原生 4K 生成而非 1K 后放大总结一套可落地的提示词方法论回到本文起点prompt-engineering.md 的核心贡献可以归纳为三层结构层六组件推理简报保证提示词信息完整、表达层叙事段落、真实相机/品牌锚点、正面表述替代否定、具体灯光与构图指令保证模型可解析、策略层领域模式库与模板库降低从零编写的成本安全改写策略处理被拦截的边界情况。在 claude-seo 中这套方法论通过seo-image-gen技能与 Banana 扩展落地为可重复执行的生成流水线——编写提示词时记住开头那条贯穿全文的规则让模型看见你描述的场景而不是读到一组标签。【免费下载链接】claude-seoUniversal SEO skill for Claude Code. 26 sub-skills 19 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, agent readiness (Lighthouse Agentic Browsing, WebMCP, llms.txt), backlinks, local SEO, e-commerce, international SEO, Google APIs, and PDF/Excel reporting. 9 optional extensions for live SEO data.项目地址: https://gitcode.com/GitHub_Trending/cl/claude-seo创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考