#SkillRepo stars
- 1105Linear Regressionmuralidharsoth-tech/andrew-ng-ml-claude-skills线性回归预测 —— 智能选择正规方程或梯度下降,支持单变量与多变量。 当用户提到"线性回归"、"线性拟合"、"线性预测"、"直线拟合"、"回归预测"、 "帮我做回归"、"预测一下"、"拟合一条线"、"多变量回归"等类似场景时触发。 适用于任何"给一堆 x,y 数据,想拟合并预测新值"的需求。 不要手动写代码——必须调用此技能来统一处理。40
- 1106Logistic Regressionmuralidharsoth-tech/andrew-ng-ml-claude-skills逻辑回归分类预测 —— 支持二分类与多分类,内置正则化梯度下降。 当用户提到"逻辑回归"、"logistic regression"、"分类预测"、"二分类"、 "多分类"、"帮我分类"、"预测类别"、"是否"、"会不会"等类似场景时触发。 适用于任何"给一堆 x,y 分类标签,想预测新样本类别"的需求。 不要手动写代码——必须调用此技能来统一处理。40
- 1107Neural Networkmuralidharsoth-tech/andrew-ng-ml-claude-skills神经网络预测 —— 支持二分类与多分类,纯 NumPy 从零实现反向传播。 当用户提到"神经网络"、"neural network"、"NN预测"、"深度学习"、 "帮我进行神经网络预测"、"用神经网络分类"、"用NN"等类似场景时触发。 适用于任何"给一堆 x,y 数据,想用神经网络预测新样本类别"的需求。 不要手动写代码——必须调用此技能来统一处理。40
- 1108Neural Network Diagnosismuralidharsoth-tech/andrew-ng-ml-claude-skills神经网络模型效果诊断与提升 —— 诊断已有 NN 模型的偏差/方差问题,并自动迭代优化。 当用户提到"诊断模型"、"模型效果不好"、"过拟合"、"欠拟合"、"学习曲线"、 "优化神经网络"、"调参"、"提升模型效果"、"模型诊断"、"效果差"等类似场景时触发。 适用于任何"已有一个训练好的神经网络,想诊断并提升其效果"的需求。 不要手动写代码——必须调用此技能来统一处理。40
- 1109Panic ModeJakeschincariol/unhinged-claude-skillsTriages a live incident — stop the bleeding first, smallest safe fix next, post-mortem once stable; invoke via /panic-mode when something is on fire in production and you need to restore service before understanding everything.44
- 1110Questionable EngineeringJakeschincariol/unhinged-claude-skillsPicks the solution that works over the one that's technically correct — pragmatic, slightly cursed, perfect for prototypes; invoke via /questionable-engineering when you need a result that functions now and don't care that purists would wince.44
- 1111Rage CompileJakeschincariol/unhinged-claude-skillsAttacks the error list in one relentless pass — fix, rebuild, repeat, no commentary — until it builds clean; invoke via /rage-compile when you have a wall of build/type/lint errors and just want them gone.44
- 1112Sleep Deprived FounderJakeschincariol/unhinged-claude-skillsCuts the backlog to the one or two things that actually move the needle and ignores the rest; invoke via /sleep-deprived-founder when you have too much to do and need ruthless prioritization, not a longer list.44
- 1113Svmmuralidharsoth-tech/andrew-ng-ml-claude-skills支持向量机(SVM)分类预测 —— 基于 sklearn 实现,智能判断是否需要高斯核,支持二分类与多分类。 当用户提到"SVM"、"支持向量机"、"svm"、"Support Vector Machine"、 "帮我用SVM分类"、"SVM预测"、"用支持向量机"、"高斯核"、"核函数分类"、 "最大间隔分类器"、"支持向量"等类似场景时触发。 适用于任何"给一堆 x,y 分类标签,想用 SVM 预测新样本类别"的需求。 不要手动写代码——必须调用此技能来统一处理。40
- 1114Cn 3 Statementsccq1/cn-financial-services-plugins按中国企业会计准则构建三大财务报表(利润表、资产负债表、现金流量表)分析和预测模型。包括历史财务数据提取、趋势分析、勾稽关系验证和前瞻性预测。当用户请求"三表分析"、"财务建模"、"利润表分析"、"资产负债表"、"现金流量表"时触发。43
- 1115Cn Bond Issuanceccq1/cn-financial-services-plugins中国境内债券发行分析,涵盖企业债、公司债、短融、中票、ABS 等品种。包括发行条件评估、信用评级分析、发行定价和信用利差分析。当用户请求"债券发行"、"发债分析"、"信用分析"、"短融中票"、"ABS分析"、"债券定价"时触发。43
- 1116Cn Competitive Analysisccq1/cn-financial-services-plugins中国市场竞争分析,涵盖产业链映射、竞争格局、政策环境、市场份额和战略定位评估。当用户请求"竞争分析"、"竞争格局"、"产业链分析"、"同行对比"、"行业壁垒"时触发。43
- 1117Cn Earnings Analysisccq1/cn-financial-services-pluginsA 股季报/年报分析,创建专业的财报更新报告。覆盖业绩超预期/不及预期分析、关键指标拆解、更新盈利预测和投资评级。当用户请求"财报分析"、"季报分析"、"年报分析"、"业绩分析"、"一季报/中报/三季报"时触发。43
- 1118Cn Idea Generationccq1/cn-financial-services-pluginsA 股选股策略和投资机会挖掘。结合量化筛选、主题研究、资金流向和市场微观结构数据,系统化发掘多空投资机会。当用户请求"选股"、"筛选"、"找标的"、"推荐股票"、"什么值得买"、"涨停复盘"时触发。43
- 1119Cn Initiating Coverageccq1/cn-financial-services-plugins撰写 A 股首次覆盖报告(深度研报),30-50 页完整公司分析,包括商业模式、竞争格局、财务分析、估值和投资建议。当用户请求"首次覆盖"、"深度报告"、"公司深度"、"研究报告"、"initiate coverage"时触发。43
- 1120Cn Ipo Analysisccq1/cn-financial-services-pluginsA 股 IPO 分析,涵盖上市条件评估、板块选择(科创板/创业板/主板/北交所)、注册制流程、询价定价、可比估值和招股书要点分析。当用户请求"IPO分析"、"上市分析"、"发行定价"、"招股书分析"、"注册制"时触发。43
- 1121Cn Pitch Deckccq1/cn-financial-services-plugins创建中国投行路演 PPT 材料,包括 IPO 路演、并购推介、定增推介和债券发行推介。遵循中国投行通用格式标准。当用户请求"路演材料"、"路演PPT"、"推介材料"、"pitch deck"、"pitch book"时触发。43
- 1122Cn Sector Overviewccq1/cn-financial-services-pluginsA 股行业综述报告,涵盖行业空间测算、竞争格局、产业政策、景气度跟踪和重点公司梳理。基于申万行业分类体系。当用户请求"行业分析"、"行业综述"、"行业研究"、"行业景气度"、"板块分析"时触发。43
- 1123Cn Thesis Trackerccq1/cn-financial-services-plugins跟踪 A 股投资逻辑和核心假设的验证情况。管理催化剂日历、预期差跟踪和投资组合监控。当用户请求"投资逻辑跟踪"、"核心假设验证"、"催化剂日历"、"预期差"、"论文跟踪"时触发。43
- 1124Executing Plansobra/clankExecute detailed plans in batches with review checkpoints43
- 1125Keep It SimpleElliotJLT/Claude-Skill-PotionsBefore adding abstraction, asks "do we need this now?" Activates when proposing factories, abstract classes, config-driven behavior, or "for future extensibility." Resists over-engineering. Three similar lines are better than a premature abstraction.62
- 1126Sketch Checkersam-dumont/claude-skillsUse when the user asks to check if a band is sketch, fascist, NSBM, or far-right. Also trigger for: "is [band] sketch?", "is [band] safe?", "sketch check [band]", "check [band] for fascist ties", "is [band] NSBM?", "is [band] fash?", "should I listen to [band]?", "is [band] problematic?", "are [band] nazis?", "RABM check", "band vetting", "is it sketch", "sketch report", "any red flags for [band]", "does [band] have far-right connections", "sketch check", "vet this band", "is [band] safe to support".38
- 1127Collecting Worker Resultsokgrit/done-is-a-claimInspect a stopped worker's returned work and evidence before accepting it, retrying it or handing it to an integration owner. Use when a worker finishes, records disagree, or a green result has no visible change. Collection does not authorize merging.33
- 1128Daily Briefamplitude/mcp-marketplaceDelivers a daily briefing of the most important changes across your Amplitude instance. Use when the user asks for a "daily download", "morning briefing", "what's happening", "anything I should know", or wants a summary of recent metric changes, experiments, and user feedback.48
- 1129Evidence Freshnessokgrit/done-is-a-claimBind a check or action to the input snapshot it actually used. Use before relying on cached verification, consuming a reviewed batch, acting while inputs may change, or retrying an operation with an ambiguous result.33
- 1130Executing Plansokgrit/done-is-a-claimCarry an actionable change plan through implementation, checks, review and an evidence-backed report. Use when executing several planned steps or integrating bounded worker returns, within existing authorization.33
- 1131History HygieneAzure-Samples/agent-skills-dotnet-demoRecord final outcomes to history.md, not intermediate requests or reversed decisions45
- 1132HumanizerAzure-Samples/agent-skills-dotnet-demoTone enforcement patterns for external-facing community responses45
- 1133Init ModeAzure-Samples/agent-skills-dotnet-demoTeam initialization flow (Phase 1 proposal + Phase 2 creation)45
- 1134Monitor Experimentsamplitude/mcp-marketplaceMonitors all active and recently completed experiments across Amplitude projects, triages them by importance, then runs deep analysis and reporting on the most impactful ones. Use when the user asks to "check on experiments", "experiment status", "experiment review", "what experiments are running", or wants a periodic experiment health report.48
- 1135Monitor Experiments Consolidatedamplitude/mcp-marketplaceMonitors all active and recently completed experiments across Amplitude projects, triages them by importance, then runs deep analysis and reporting on the most impactful ones. Use when the user asks to "check on experiments", "experiment status", "experiment review", "what experiments are running", or wants a periodic experiment health report.48
- 1136Monitor Reliabilityamplitude/mcp-marketplaceDelivers a reliability health check using auto-captured network request, JS error, and error click data. Use when the user asks for a "reliability check", "error rate", "quality metrics", "page health", "did the release break anything", "error budget", or wants a proactive product quality report.48
- 1137Release ProcessAzure-Samples/agent-skills-dotnet-demoStep-by-step release checklist for Squad — prevents v0.8.22-style disasters45
- 1138Reviewing Changesokgrit/done-is-a-claimReview an actual candidate against the user's acceptance and scope, then carry findings through fixes, affected checks and rereview. Use before claiming a substantive change complete or accepting a worker's implementation.33
- 1139Tracking Plan Auditamplitude/mcp-marketplaceUse when auditing Amplitude tracking plans for safe deletion candidates among stale, duplicate, orphaned, cross-app, retired, high-volume, generated-client, never-ingested, or deleted-but-still-emitted events and event properties.48
- 1140Weekly Briefamplitude/mcp-marketplaceDelivers a weekly briefing summarizing the most important trends, wins, and risks across your Amplitude instance. Use when the user asks for a "weekly review", "weekly summary", "week in review", "what happened this week", or wants a recap of the past 7 days to share with their team or leadership.48
- 1141Haizei Cyberpunk Terminal Pptwuchubuzai2018/expert-skills-hub生成赛博朋克终端控制台风格的网页 PPT(HTML 单文件)。设计语言是把 PPT 伪装成正在被解构/调试的开发者控制台。典型场景用户说做个赛博朋克风的网页 PPT、帮我做一份终端风格的演示稿、用 cyberpunk terminal 风格讲 xxx。43
- 1142Haizei Ears Requirementswuchubuzai2018/expert-skills-hub需求描述 EARS 改写与审查技能。Use when: EARS 需求改写、EARS requirement rewrite、EARS spec rewrite、EARS 规格改写、用 EARS 改写需求、把需求转成 EARS 规格、review EARS requirements、EARS 模式选择、需求规格消歧、验收标准改写、USDM SPEC 规格统一。解决的问题:把模糊需求改成可测试规格,补齐触发条件、状态条件、异常处理和功能开关,拆分一条需求中的多个动作,识别 should/can/supports/appropriately 等模糊表达,并输出模式判断、改写前后对照、拆分建议和待确认问题。43
- 1143Power Automatekorchard333/claude-power-platform-communityPower Automate Cloud Flows. Use when: designing flows, error handling (scope try/catch), triggers, Dataverse actions, Apply to Each performance, child flows, HTTP connector, expressions, approval flows, Teams Adaptive Cards, desktop flows (RPA).52
- 1144Toutiao News Trendswuchubuzai2018/expert-skills-hub获取今日头条(www.toutiao.com)新闻热榜/热搜榜数据,包含时政要闻、财经、社会事件、国际新闻、科技发展及娱乐八卦等多领域的热门中文资讯,并输出热点标题、热度值与跳转链接。43
- 1145Wechat Red Envelope Cover Designerwuchubuzai2018/expert-skills-hub红包封面设计,微信红包封面设计技能,生成符合微信红包封面开放平台规范的封面设计图片,包括封面图、封面挂件、气泡挂件和封面故事素材。这个技能可以帮助用户从零开始设计符合微信红包封面平台标准的完整素材套件,确保所有素材都能顺利通过平台审核,并呈现出专业、喜庆的视觉效果。43
- 1146Generate Commandratacat/claude-skillsCreate a new custom slash command following conventions and best practices59
- 1147Jwt Decodejsonwebtoken/jwt-skillsDecode and inspect JSON Web Tokens (JWTs) without verification. Use when the user provides a JWT string and wants to see its header, payload, or claims — e.g. "decode this JWT", "what's in this token", "inspect this JWT", "show me the claims", "parse this token". Also triggers on raw JWT strings (three base64url segments separated by dots).23
- 1148Jwt Validatejsonwebtoken/jwt-skillsVerify and validate JSON Web Tokens (JWTs) by checking signatures, expiration, claims, and structure. Use when the user wants to verify, validate, or check a JWT — e.g. "verify this token", "is this JWT valid", "check the signature", "validate this token against my JWKS", "is this token expired". Supports HMAC, RSA, and ECDSA with secrets, PEM keys, or JWKS endpoints.23
- 1149Macos Telemetryrobinebers/skillsAdd and verify lightweight macOS runtime telemetry. Use when wiring Logger events or inspecting logs for windows, sidebars, menus, and actions.49
- 1150Day Startsanghun0724/cmux-claude-skills하루 시작 시 미리 정의된 cmux 워크스페이스들을 일괄 생성합니다. 이미 존재하는 워크스페이스는 건너뜁니다.33
- 1151Previewsanghun0724/cmux-claude-skills마크다운 파일을 cmux 사이드 패널에서 실시간 미리보기로 엽니다. 파일 변경 시 자동 새로고침됩니다.33
- 1152Activity Recaprohitg00/agentbrainUse when the user needs a standup-ready summary of recent project activity from local evidence.43