Claude Skills
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.
聚焦FBM、发货与入库、图片与视频的 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。
聚焦差异化、类目与节点、市场机会的 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。
Diagnose high Amazon Ads ACoS by decomposing CPC, conversion rate, price, query mix, placement mix, and sample sufficiency. Use when the user asks why ACoS is high, whether a keyword has enough clicks, how to estimate CPA or break-even CPC, or whether to move, pause, or continue a target. Return evidence-ranked actions and keep live changes behind approval.
Apply a simple Amazon Ads allocation model that separates discovery from exploitation, tests keyword and placement effects, and reallocates budget toward evidence-backed conversion pockets. Use when the user asks for a clear mental model for Amazon ads, how to find good traffic, how to compare placements, or how to reduce poor traffic. Draft only unless live changes are explicitly approved.
Rebuild an unprofitable Amazon ad account by replacing head-term dependence with a verified keyword universe, root-based broad tests, pre-emptive negatives, exact harvesting, and portfolio-level profit controls. Use when ACoS is extreme, lowering ads kills sales, or a product needs a structured turnaround. Do not promise a fixed turnaround period.
Build an Amazon growth strategy that treats tax, product safety, account, IP, and logistics compliance as non-negotiable constraints, then compares niches, price bands, operating models, and marketplaces using weighted economics. Use when the user asks how to find opportunities as compliance costs rise or whether to shift product, model, or marketplace. Reject evasion and infringement strategies.
Plan Amazon ASIN product-targeting campaigns by scoring product similarity, demand, truthful conversion advantages, placement hypotheses, budget isolation, and downstream search-term harvesting. Use when the user asks whether a new product can start with ASIN targeting, how to choose competitor ASINs, or when to move discovered queries into exact campaigns. Avoid review manipulation and ranking guarantees.
Triage Amazon FBA inventory that unexpectedly becomes defective or unfulfillable by separating labeling, shipment, Transparency, listing-change, compliance, and system-state causes, then building a factual support case and deadline plan. Use when sellable stock changes to defective, a compliance review clears but stock remains blocked, or auto-removal is approaching. Do not rely on UI loopholes.
Design a compliant precision-first Amazon launch that starts with high-intent long-tail demand, validates conversion, and expands toward broader terms without fake orders or review manipulation. Use when the user asks for 白帽 0-1 推新品, a universal launch sequence, keyword-root grouping, or a limited-risk launch framework. Produce a staged plan and require approval before ad changes.
Improve an Amazon listing's discoverability for conversational shopping assistants through complete structured attributes, factual use cases, evidence-backed content, localization, and compliant customer support signals. Use when the user asks how Rufus, Alexa, or AI shopping recommendations may find a product. Never seed reviews or Q&A, fabricate scenarios, or guarantee recommendation placement.
Triage loss of the Amazon Featured Offer by checking account health, order defect signals, price competitiveness, offer and fulfillment state, listing classification, unauthorized sellers, and external price evidence before escalating. Use when the Buy Box or purchase button disappears or repeatedly returns. Do not assume sabotage, manipulate feedback, or edit other sellers' data.
Sequence Amazon keyword promotion from high-intent long-tail terms to mid-volume and head terms using stage gates, mixed ad formats, profitability checks, and exact harvesting. Use when the user asks which keywords to launch first, why competitor head terms do not convert for a new ASIN, or how to expand traffic without losing relevance. No ranking promises or artificial orders.
Create a disciplined Amazon keyword-position monitoring system that prioritizes revenue-contributing terms, separates organic and sponsored observations, controls measurement noise, and triggers evidence-based diagnostics. Use when the user asks which keyword ranks to track, how often to track them, or what to do when a core term drops. Do not automate bid changes from a single noisy snapshot.
Diagnose and design low-bid Amazon Ads discovery experiments that probe residual traffic, minimum viable bids, placements, and harvestable search terms under a portfolio cap. Use when the user asks about 捡漏广告, low-CPC discovery, bid floors, incremental keyword testing, or turning cheap traffic into a durable campaign. Default to analysis and draft changes; never mutate live ads without explicit approval.
Design a scalable Amazon long-tail keyword portfolio with evidence-based query generation, clustering versus single-keyword isolation, portfolio budget caps, automation drafts, sample safeguards, and human approvals. Use when the user asks about hundreds of campaigns, single-keyword structures, low-bid long-tail coverage, bulk sheets, or automated bid rules. Do not create live rules or campaigns without approval.
Design Amazon keyword-ranking experiments that identify promising terms from relevance, conversion, current organic visibility, and placement performance, then sequence long-tail, mid-tail, and head-term tests. Use when the user asks which keywords to push, what an ad position may reveal about order potential, or why organic rank stalls despite paid orders. Do not equate sponsored placement with organic rank or guarantee movement.
Turn an Amazon keyword universe into a clean taxonomy and campaign map using relevance, intent, roots, negatives, and evidence from authorized reports. Use when the user asks how to collect keywords, perform word-root analysis, choose auto versus broad versus exact targeting, or prevent broad campaigns from drifting. Produce a draft architecture and never apply ad changes without explicit approval.
Evaluate and improve low-price, high-CPC Amazon products using break-even economics, legitimate bundles or multipacks, long-tail traffic, low-bid discovery, creator channels, and original video ads. Use when a product has thin margin, expensive clicks, or cannot profitably scale Sponsored Products. Respect variation, IP, and creator-program rules and keep execution behind approval.
Triage negative Amazon reviews into policy violations, suspected abuse, and genuine product feedback, then prepare factual official reports and product-remediation actions. Use when the user asks whether a review can be removed, how to report abusive content, or how to respond to a rating decline. Never fabricate evidence, contact reviewers off-platform, or incentivize review changes.
Recover an underperforming Amazon new-product advertising program by diagnosing traffic concentration, sample sufficiency, placement mix, retail readiness, and unit economics in a fixed order. Use when a new ASIN has run for days or weeks with few orders, scattered clicks, or unclear next steps. Build controlled tests and do not increase budget or change live ads without approval.
Build an evidence-based Amazon new-product traffic plan that moves from controlled discovery to stable converting terms and measures organic-rank and organic-order changes without claiming causality. Use when the user asks how a new ASIN can gain organic traffic, how to sequence auto, product targeting, broad, and exact campaigns, or when to taper launch ads. Default to read-only planning and require approval for live changes.
Assess whether an Amazon operator is ready to become an independent seller by modeling cash runway, working-capital cycles, fixed costs, portfolio success probability, transferable capabilities, and ethical boundaries. Use when the user considers leaving a job to start an Amazon business or is struggling after going independent. Provide scenario-based decisions, not motivational guarantees.
Create a quantified Amazon new-product launch plan by translating a sales target into comparable-product benchmarks, keyword economics, budget scenarios, milestones, and stop-loss rules. Use when the user asks for a 新品推广计划, target-order reverse planning, competitor-based launch budget, or GO/NO-GO assessment before launch. Keep competitor estimates labeled and do not execute campaigns without approval.
Diagnose why an Amazon new product cannot gain traction by separating retail-readiness, traffic relevance, click-through, conversion, economics, and feedback quality. Use when a new ASIN is not launching, ads are not converting, or the team is tempted to use fake reviews, inflated reference prices, or artificial orders. Replace unsafe tactics with compliant conversion and advertising work.
Coordinate a careful response to an Amazon patent complaint by preserving notices, verifying jurisdiction and patent status, obtaining qualified counsel, comparing non-infringement, design-around, license, settlement, and validity options, and preparing factual platform submissions. Use when a listing is removed for alleged patent infringement. This is operational triage, not legal advice.
Diagnose why an Amazon keyword converts poorly at top of search but better elsewhere by analyzing placement reports, effective bids, competitor context, and controlled experiments. Use when an exact keyword gains premium placement yet underperforms, when raising bids shifts spend to the wrong placement, or when the user wants a placement test. Never claim exact page-position control.
Audit suspicious Amazon review patterns and proposed review-growth tactics for policy risk, then replace unsafe ideas with official reporting and compliant review programs. Use when the user encounters sudden review spikes, asks about 直评突破, synchronized submissions, paid reviews, review services, or how to investigate competitor review anomalies. Do not reverse-engineer or enable manipulation.
Reduce avoidable Amazon returns through root-cause analysis, accurate listing content, packaging and quality fixes, official Product Support features, manuals, support videos, spare-parts workflows, and privacy-safe service operations. Use when customers return products due to setup, usage, missing parts, or delayed support. Never request reviews during support or build an unauthorized customer list.
Design a scalable Amazon seller operating system using category specialization, portfolio capacity, operator skill tiers, SOP floors, experiment governance, incentives, and resource allocation. Use when the user asks how a small team can manage more products, improve operator productivity, allocate launches, or balance expert autonomy with standardized processes. Do not repeat anecdotal revenue claims as benchmarks.
Assess whether a team should enter or expand on Amazon using unit economics, cash runway, product-market fit, operational capability, compliance, and staged validation. Use when the user asks whether Amazon is still worth doing, whether a new seller or factory should enter, what product-price band to choose, or how to make a GO/NO-GO decision. Do not promise returns or treat anecdotes as benchmarks.
Prepare an evidence-based tax-compliance triage pack for Amazon cross-border sellers by mapping entities, marketplaces, goods flow, customs declarations, invoices, settlements, returns, and inventory reconciliation, then framing questions for qualified tax and customs advisers. Use when users ask about 0110, 1039, 9810, offshore entities, historical gaps, or future compliance. This is not tax or legal advice and must not enable evasion.
Respond safely to suspicious Amazon buyer-seller messages, extortion, phishing, coercive orders, and review threats by preserving evidence, avoiding off-platform engagement, securing accounts, and reporting through official channels. Use when a seller receives threatening messages, false service claims, unusual bulk orders, or requests for money or credentials. Do not conceal the seller's own policy violations.
Design Amazon Ads for legitimate parent-child variations by selecting a hero child, allocating queries by variant attributes, isolating budgets, and monitoring halo effects and inventory. Use when the user asks how to advertise many variants, prevent child ASINs from competing, choose a hero variation, or split keywords by color, size, pack count, or style. Never create invalid variations or execute without approval.
Plan an ad-intensive but policy-compliant Amazon launch that expands indexed and converting keyword coverage while preserving profitability and inventory guardrails. Use when the user asks for a pure white-hat launch, broad keyword coverage, when to move terms into exact campaigns, or how to combine auto, broad, product targeting, and eligible promotions. No review manipulation or ranking guarantees.
Design a policy-compliant Amazon review acquisition plan for high-ticket or low-volume products using eligible official programs, neutral Request a Review workflows, product quality, support, and legitimate variations. Use when the user asks how to gain initial reviews without giving away excessive inventory or proposes paid reviews, seed ASINs, cross-market manipulation, or zombie listings. Refuse prohibited tactics.
聚焦评价与口碑、政策变化、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。
Assess a proposed Woot deal or onboarding path using current official eligibility, account ownership, deal economics, inventory, brand rights, operational responsibilities, and compliance risks. Use when the user asks whether to apply for Woot, use a service provider, submit a deal, or treat Woot as a launch channel. Never support account trading, fake reviews, artificial orders, or risk shielding.
聚焦高客单价、利润模型、成本结构的 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。
聚焦否定投放、搜索词分析、手动广告的 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。
聚焦竞价策略、卖家精灵、关键词排名的 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ROAS、政策变化、ACOS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。
聚焦类目与节点、标题、转化率的 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。
聚焦成本结构、客服与工单、汇率风险的 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。
聚焦图片与视频、运营工具、A+ 页面的 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。
聚焦运营工具、尺寸重量、点击表现的 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。
聚焦季节性、现金流、竞品验证的 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。
聚焦经营经验的 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FBA、发货与入库、成本结构的 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。
聚焦尺寸重量、变体关系、品牌与备案的 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。
聚焦评价与口碑、五点描述、转化率的 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。
聚焦搜索词分析、差异化、关键词排名的 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。
聚焦卖家精灵、新品启动、市场机会的 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FBA、Listing 诊断、匹配方式的 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。
聚焦经营经验、FBA、AI 工作流的 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Listing 诊断、品牌与备案、税务与出口的 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。
聚焦市场机会、运营工具、关键词体系的 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。
Benchmark Amazon niche ad efficiency by comparing visible advertising breadth, estimated sales, review cohorts, CPC, and conversion economics. Use when deciding whether a product has a simple enough paid-traffic structure for a new entrant.
Create a guarded Amazon Ads launch plan that prioritizes query relevance, listing alignment, conversion evidence, and capped learning spend. Use when a new product has little history and the team wants to improve auction eligibility without assuming a hidden fixed weight score.
Discover Amazon product opportunities by starting with a clearly defined audience and mapping recurring work, life, event, and gifting needs. Use when product-first searches produce generic red-ocean ideas.
Build a compact Amazon Ads launch keyword set that combines controlled broad discovery with exact intent capture. Use when a new niche product has many candidate terms but limited inventory and cannot afford to test a huge keyword list.
Claude Skills — questions
Answers built from the skills we actually parsed.