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.
聚焦供应链、发货与入库、税务与出口的 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FBM、供应链、发货与入库的 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。
聚焦汇率风险、市场机会、成本结构的 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。
聚焦品牌与备案、手动广告、自动广告的 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AI 工作流、图片与视频、站外流量的 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。
聚焦预算分配、竞价策略、匹配方式的 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。
聚焦竞品验证、商品投放、关键词体系的 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。
聚焦关键词排名、利润模型、政策变化的 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。
聚焦账号关联、自动广告、类目与节点的 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。
聚焦政策变化、SB 广告、SD 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。
聚焦发货与入库、TACOS、库存管理的 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SP 广告、新品启动、广告位的 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。
聚焦客服与工单、变体关系、评价与口碑的 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。
聚焦图片与视频、运营工具、AI 工作流的 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、新品启动、点击表现的 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TACOS、利润模型、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。
聚焦现金流、FBA、发货与入库的 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。
聚焦库存管理、发货与入库、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。
聚焦供应链、利润模型、发货与入库的 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。
聚焦广告位、评价与口碑、关键词体系的 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。
聚焦关键词体系、卖家精灵、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。
聚焦竞品验证、成本结构、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。
聚焦利润模型、新品启动、供应链的 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。
Map Amazon product targets by substitute, complement, own-brand defense, and category discovery using current relevance, price, rating, and performance evidence. Use to structure Sponsored Products, Sponsored Brands, or display product targeting.
聚焦ROAS、季节性、竞价策略的 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。
Build a privacy-safe Amazon Marketing Cloud audience hypothesis, measurement query plan, and activation experiment. Use when standard audiences are insufficient and the advertiser needs a custom multi-touch or engagement-based segment.
Build an Amazon competitor value map from comparable product facts, review and Q&A themes, price, offer, creative, and observable advertising. Use for product, listing, and ad strategy without copying claims or inventing competitor backend data.
Design a goal-led Amazon display advertising plan using contextual, remarketing, in-market, lifestyle, or custom audience tactics. Use when extending beyond search ads while keeping targeting, measurement, and budget expansion controlled.
Build localized, evidence-backed Amazon keyword plans for seasonal peaks across multiple marketplaces. Use when preparing listings and ads for an event while preventing literal translation, shared-budget assumptions, and cross-market data leakage.
Transfer proven Amazon launch knowledge into a new marketplace while revalidating compliance, localization, demand, fees, inventory, and ad eligibility. Use when expanding from a mature marketplace without assuming past success will repeat.
Build and test a seasonal Amazon keyword cluster from local shopper intent, event timing, product relevance, and landing-page evidence. Use for holiday, occasion, gifting, or weather-led search opportunities without keyword stuffing.
Turn a verified high-intent Amazon search query into an evidence-backed video storyboard, mobile-first captions, and controlled creative variants. Use for Sponsored Brands video or other eligible video ads.
Prepare Amazon ads for a major shopping event with a backward calendar, product tiers, inventory and deal checks, proven keywords, budget guardrails, and post-event recovery. Use before Prime Day, Black Friday, or a regional peak.
Turn a verified buyer concern into a factual, mobile-readable Amazon secondary-image brief. Use when a product needs to explain compatibility, setup, safety, dimensions, or expected results without simulating a review or social-media endorsement.
Build a fair Amazon creative-team scorecard that separates controllable craft and process quality from shared CTR, conversion, and business outcomes. Use to brief, review, and coach designers without assigning them sole ownership of sales metrics.
Turn Amazon customer evidence into a human-centered product brief covering the job, context, functional and emotional outcomes, alternatives, constraints, and validation. Use before product development or major differentiation decisions.
Diagnose Amazon ads with impressions and clicks but low conversion by tracing traffic relevance, placement, offer, reviews, listing expectation match, product fit, inventory, and market change. Use before changing bids or creative.
Design an Amazon image-composition test around one buyer question, truthful product scale, visual hierarchy, mobile readability, and current image rules. Use when an image feels busy or fails to communicate value clearly.
Design a category-compliant Amazon main-image distinctiveness experiment based on shopper recognition and click-through evidence. Use when competing listings look interchangeable or a visual-similarity feature creates an unverified optimization hypothesis.
Create and quality-control AI-assisted apparel ad concepts from verified product assets, fit and material facts, usage scenarios, rights, and current ad policies. Use before generating or testing fashion creative variants.
Gate an Amazon new-product launch across product-market evidence, compliance, offer, listing, inventory, unit economics, ads, and measurement. Use before treating campaign creation as the launch plan.
Run a controlled Amazon ad-taper experiment after a query reaches stable organic visibility, measuring paid incrementality, total query performance, profit, and rank durability. Use instead of abruptly cutting ads.
Translate verified Amazon product facts into feature-advantage-benefit-proof copy and carefully bounded sensory or emotional language. Use for titles, bullets, images, A+ modules, and ads without unsupported superlatives.
Translate familiar content patterns into compliant Amazon secondary-image or A+ experiments without copying social interfaces, fabricating testimonials, or changing the main-image rules. Use when listing creative feels generic and needs a controlled engagement test.
AI 投研工作台——在 deepseek-harness 里编排 virattt/ai-hedge-fund（美股多策略 AI 基金，支持回测）、iFinD 权威数据源（经 plugins/ifind 访问，财报/公告/股东/预测/选股，A股港股美股）与本地 A股/港股技术分析技能，配合 risk-gate 风控钩子、定时盯盘与投资记忆，完成"分析→回测→解读→复盘"的完整投研闭环。当用户要求分析美股、运行 AI 基金、回测策略、比较投资大师观点、生成投研报告、定时盯盘、复盘投资假设，或查询财报/财务报表/公告/股东户数/业绩预测/智能选股/iFinD/同花顺数据时使用。触发词：AI 基金、对冲基金、回测、巴菲特、格雷厄姆、投研、美股分析、盯盘、复盘、iFinD、同花顺、股东户数、财务报表、公告、业绩预测。
考公AI导师 — a tutor for the Chinese civil service exam (公务员考试), covering 行测 (aptitude), 申论 (essay), and 面试 (structured interview). Use when the user mentions 考公, 公务员, 国考, 省考, 事业编, 选调生, 公考, 行测, 申论, 面试模拟, 结构化面试, 常识判断, 言语理解, 数量关系, 判断推理, 资料分析, 时政热点, or asks to practise exam questions, get an essay graded against the official rubric, run a mock structured interview, analyse current affairs for the exam, or build a study plan. Also matches kaogong, gongwuyuan, guokao, shengkao, xingce, shenlun, mianshi, and "Chinese civil service exam prep".
Build or resume mathematical-modeling competition work, including CUMCM, MCM/ICM, graduate and regional contests, data challenges, and open-topic statistical modeling. Guide problem framing, modeling, computation, validation, Chinese or English LaTeX writing, and reviewed PDF/source delivery using current official requirements. Not for ordinary paper polishing.
Build or resume mathematical-modeling competition work, including CUMCM, MCM/ICM, graduate and regional contests, data challenges, and open-topic statistical modeling. Guide problem framing, modeling, computation, validation, Chinese or English LaTeX writing, and reviewed PDF/source delivery using current official requirements. Not for ordinary paper polishing.
Independently review a CUMCM computation package before its claims enter validation or paper writing. Use only inside a generated independent-review package.
Expert documentation generator for coding projects. Analyzes codebases to create thorough, comprehensive documentation for developers and users. Supports incremental updates, multi-audience documentation, architecture decision records, and documentation health tracking. Works with any project type (APIs, CLIs, web apps, libraries). Use when you need to document a new project, update docs after adding features, or create comprehensive documentation for open source releases.
This skill should be used when writing technical content in the style of Hunt/Thomas (The Pragmatic Programmer) and Joel Spolsky (Joel on Software). It applies when creating technical essays, documentation, tutorials, or explanatory content that needs to be clear, engaging, and actionable.
This skill should be used when orchestrating complex writing workflows with multiple phases. It provides two-agent orchestration patterns, the two-gate content readiness assessment, 10 baseline writing strategies, 20+ situational strategies, and quality checkpoints. Inspired by the Spiral Writing System.
Collaborative brainstorming partner for multi-session ideation projects. Use when the user wants to brainstorm, ideate, explore ideas, or think through problems—whether for SaaS products, software tools, book ideas, newsletter content, business strategies, or any creative/analytical challenge. Handles session continuity across days/weeks via versioned markdown documents. Includes brainstorming methods catalog and supports both connected (cross-project awareness) and clean-slate modes.
This skill should be used when writing in the distinctive style of David Heinemeier Hansson (DHH). It applies when creating blog posts, technical articles, business content, manifestos, or any prose requiring a clear, punchy, opinionated style.
This skill should be used when extracting voice profiles from sample text, creating voice documentation, or matching a specific writing style. It applies when users provide sample text and want to capture the voice for future use.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Develop ebook ideas into structured concepts ready for architecture. Use when the user has an ebook idea (from a brainstorm document, existing content to repurpose, a book section to extract, or a fresh concept) and wants to develop it into a clear, validated concept. Produces an Ebook Concept Document with reader, transformation, promise, content source, scope/format, and key topics. Handles multi-session development with living documents.
Create a structured session handoff document for continuity across sessions. Use when ending a work session, switching contexts, or before a break. Captures decisions, progress, code changes, and next steps so a future session can pick up where you left off without losing context.
Optimize iOS App Store and Google Play Store listings for maximum discoverability and conversion. Perform competitive keyword research, craft keyword-optimized titles/subtitles/descriptions, design screenshot sequences, and generate A/B test variants. Use when the user has a built app and needs to write or improve their store listing, do ASO keyword research, optimize app metadata, plan screenshot strategy, or create listing variants for testing. Triggers on "optimize my app listing", "ASO", "app store optimization", "keyword research for my app", "improve my store listing", "screenshot strategy", "app store keywords", "play store listing".
Claude Skills — questions
Answers built from the skills we actually parsed.