The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 600 files from 1 763 authors, of which 61 947 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Turn verified product facts and third-party keyword exports into an auditable AI workflow for filtering queries, selecting ad candidates, drafting listing fields, and preserving evidence for every claim. Use for AI写Listing、关键词表清洗、竞品词过滤、广告词选择、标题五点和后台词草拟. Not for invented claims or direct publishing.
Plan an Amazon new-product traffic mix that limits early audience noise across manual keywords, product targeting, display audiences, and video while testing whether weak conversion is traffic- or product-led. Use for 新品人群标签、用户画像、相同关键词转化不同、展示或视频广告受众、前期控流量.
Assess an Amazon boutique business model through differentiated demand, pricing room, saturation, tail conversion, market health, capital turnover, and downside controls. Use for 什么是精品、精品选品框架、资金周转、市场健康度、精品是否成立. Do not reduce boutique strategy to premium creative.
Create evidence-backed Amazon image and A+ briefs with AI while preserving the real product's shape, color, scale, included components, and policy compliance. Use for AI做亚马逊商品图、主图差异化、副图和A+规划、评论洞察转视觉、图片测款. Not for fabricating the product.
Validate whether an apparent Amazon blue-ocean opportunity is driven by durable differentiated demand or by price, promotion, review, variation, or off-platform distortions. Use for 蓝海选品、低评论高销量、新品异军突起、差异化机会、真假蓝海. This is a pre-screen, not a sourcing decision.
Plan a profit-oriented Amazon boutique-product operating rhythm from selection gates through precise traffic tests, conversion validation, bid control, and cautious scaling. Use for 精品怎么投广告、低评论新品、追求高投产、什么时候减少或扩大广告. Do not use review manipulation.
Reverse-engineer an Amazon breakout case by testing competing explanations across product innovation, brand, keyword breadth, organic visibility, timing, variants, promotions, returns, and compliance. Use for 爆款案例复盘、为什么突然增长、是不是站外、能不能复制、成功因素拆解.
Control Amazon ad budget and placement as separate levers, diagnosing when click acceleration dilutes conversion and when additional budget can extend profitable traffic. Use for 加预算后转化下降、点击太快、怎么调顶部和商品页、预算不足还是竞价过高.
Infer competitor keyword coverage from observable organic and sponsored positions, shared attributes, query patterns, and product relevance without claiming access to a competitor account. Use for 竞品广告词分析、反查竞品关键词、判断精准词与探索词、找防守或捡漏词. Do not claim unseen campaign settings as facts.
Build a first-pass Amazon competitor traffic network from high-relevance organic and sponsored query observations plus attribute-root exploration. Use for 抢竞品流量、竞品关键词分层、精准和广泛互补、旧版流量网络复盘. Prefer the v2 Skill when full evidence is available.
Scale Amazon ad traffic only after conversion quality, click velocity, budget continuity, inventory, and contribution economics show that broader reach can be absorbed. Use for 点击突然变多转化下降、要不要加预算、自然排名与广告扩量、维护新品转化.
Diagnose weak Amazon conversion product-first by benchmarking comparable listings, market difficulty, price-value fit, visual differentiation, keyword precision, and placement mix. Use for 产品转化差、广告不出单、价格还是图片问题、词不准还是商品页问题、商品页位置差.
Build an evidence-gated Amazon competitor traffic network with separate opportunistic exact, contested exact, attribute exploration, automatic discovery, and defense layers. Use for 系统化抢竞品流量、自然强但广告弱的词、竞品核心词、防守词、自动捡漏. Use v1 only for a simpler audit.
Set Amazon per-SKU inventory and advertising boundaries from realistic sales capacity, cash turnover, conversion, break-even acquisition cost, and portfolio risk. Use for 首批发多少、库存临界点、精铺盈利逻辑、广告花费怎么控、多产品组合风险.
Build testable hypotheses for Amazon keyword relevance and ranking from conversion, clicks, orders, add-to-cart signals, listing semantics, and related-query behavior without claiming a proprietary ranking formula. Use for 关键词权重、精准小词和大词关系、为什么出单后曝光增加、自然排名机制假设.
Estimate Amazon operating difficulty from comparable-product sales distribution, low-review performance, ad dependence, store constraints, returns, and inventory break-even rather than headline demand alone. Use for 产品好不好运营、评论少能卖多少、该发多少货、头部销量高但新品难做. Do not treat heuristic ratios as guarantees.
Turn competitor keyword observations and verified product attributes into separate exact, exploratory, listing, and backend keyword maps with explicit inclusion and exclusion reasons. Use for 写Listing前选词、广告精准词和广泛词、竞品词表过滤、关键词去向映射.
Design a compliant Amazon organic-rank experiment around relevant high-converting queries, variant fit, controlled ad support, and incremental-profit checks. Use for 推关键词自然排名、选择推词变体、自然第一后是否停广告、精准词放量. Do not use artificial orders.
Assess paid-versus-organic Amazon order contribution with whole-ASIN economics, cannibalization tests, query relevance, and time-window controls instead of subtracting attributed ad orders mechanically. Use for 广告单挤占自然单、关广告会不会掉单、哪些词可停、自然订单怎么算、整体广告盈利.
Find defensible Amazon niches inside competitive categories by combining differentiated product slices, low-review performance, ad-efficiency proxies, and evidence-quality checks. Use for 红海里找蓝海、化妆包等细分类目、低评论销量、广告效率、运营难度. Not for copying or review merging.
Improve Amazon conversion by mining verified customer language, repositioning a product around a defensible benefit, and aligning images, title, bullets, and precise traffic in a controlled test. Use for 主图差异化、评论洞察、标题五点优化、同质化产品重新定位、提升转化.
Screen an Amazon niche whose demand window, differentiated slice, low-review competition, conservative stocking, and operational follow-through must all align before launch. Use for 季节性蓝海、未来月份选品、趋势下滑、低评论切片、首批库存和后续开发.
Design an evidence-gated Amazon new-product ad launch with precise keyword selection, small coherent groups, controlled traffic acquisition, placement learning, and profit-aware scaling. Use for 新品广告怎么开、冷启动词怎么选、预算和竞价怎么设、何时降价扩量. Execution remains approval-gated.
Design an Amazon spread-model portfolio that limits per-SKU inventory and ad exposure while aggregating profit across validated non-standardized product opportunities. Use for 精铺选品和运营、多SKU小批量、单品盈利平衡、组合备货. Not for indiscriminate catalog flooding.
Control Amazon spread-model advertising around per-SKU break-even, conservative inventory, precise keyword tests, uniform group logic, and low-touch exception management. Use for 精铺广告打法、广告花费占比、少量备货、多个SKU怎么管、何时淘汰.
Plan a compliant Amazon post-stockout recovery by rebuilding precise traffic, reassessing lost organic and related-product exposure, and scaling only after conversion stabilizes. Use for 补货后转化变差、断货后自然流量掉了、广告重启、受众重新校准. Do not use for review or order manipulation.
Pre-screen Amazon spread-model product ideas by demand timing, market depth, differentiated slices, operating difficulty, conservative sales capacity, and inventory exposure. Use for 精铺选品、低库存多产品模式、首批备货、运营难度快筛. Formal investment decisions require broader research.
聚焦品牌与备案、知识产权、客服与工单的 Amazon 账户、合规与风险。在需要识别受影响账户与义务,核对通知、证据和期限,形成风险分级、纠正计划与可审核材料时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦点击表现、关键词体系、新品启动的 Amazon 广告诊断与实验。在需要区分流量、零售承接和经济性问题,形成有样本依据的调整建议及受控实验时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦品牌与备案、图片与视频、类目与节点的 Amazon 品牌、内容与增长。在需要将购买任务和品牌事实映射到内容与渠道,形成可验证的创意简报和增长计划时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦评价与口碑、用户画像、新品启动的 Amazon 客户反馈与转化改进。在需要从评论、退货和客服证据定位购买障碍,形成产品或页面改进的优先级和验证计划时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦评价与口碑、FBA、发货与入库的 Amazon FBA、物流与库存。在需要核对可售、在途、交期和费用,量化断货与积压风险,形成可执行的库存处理方案时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦平台费用、季节性、库存管理的 Amazon FBA、物流与库存。在需要核对可售、在途、交期和费用,量化断货与积压风险,形成可执行的库存处理方案时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦供应链、发货与入库、现金流的 Amazon 费用、利润与现金流。在需要统一费用、订单和币种口径,复算贡献利润、资金缺口及压力情景时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦税务与出口、平台费用、季节性的 Amazon 费用、利润与现金流。在需要统一费用、订单和币种口径,复算贡献利润、资金缺口及压力情景时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦五点描述、标题、AI 工作流的 Amazon Listing 与页面操作。在需要定位页面与字段问题,形成有产品事实支撑的修改草案、只读预检和结果核验计划时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦新品启动、市场机会、季节性的 Amazon Listing 与页面操作。在需要定位页面与字段问题,形成有产品事实支撑的修改草案、只读预检和结果核验计划时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦AI 工作流、五点描述、卖家精灵的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦Apify、归因分析、转化率的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦现金流、新品启动、库存管理的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦类目与节点、五点描述、变体关系的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦经营经验的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦站外流量、品牌与备案的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦平台费用、税务与出口、FBA的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦政策变化、客服与工单、手动广告的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦新品启动、竞价策略、手动广告的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦库存管理、Featured Offer、站外流量的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦市场机会、卖家精灵、自动广告的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦利润模型、汇率风险、手动广告的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦季节性、ACOS、转化率的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦季节性、库存管理、发货与入库的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦评价与口碑、成本结构、账户验证的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦税务与出口、成本结构、现金流的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦税务与出口、供应链、发货与入库的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦发货与入库、账户健康、客服与工单的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦供应链、广告曝光、差异化的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦运营工具、卖家精灵、CPC的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦账户验证、用户画像、A+ 页面的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题,识别适用前提、替代解释和可迁移的经营动作时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦政策变化、利润模型、季节性的 Amazon 平台政策与异常监控。在需要核对官方规则、时间和适用范围,形成影响清单、应对动作与复核节点时使用;根据当前业务问题选择证据卡,避免加载无关主题。
聚焦现金流、利润模型、供应链的 Amazon 选品与产品开发。在需要验证购买需求、直接竞争、差异化和单位经济,形成进入、有限验证或暂缓的有据判断时使用;根据当前业务问题选择证据卡,避免加载无关主题。
Answers built from the skills we actually parsed.