[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-Whatsonyourmind-oraclaw-decide-zh-CN":3,"guides-for-Whatsonyourmind-oraclaw-decide":429,"similar-k174xef0y7h5dr9f932g3ax6d986n2dd-zh-CN":430},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":244,"isFallback":239,"parentExtension":249,"providers":250,"relations":256,"repo":259,"tags":425,"workflow":426},1778699119124.668,"k174xef0y7h5dr9f932g3ax6d986n2dd",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"为 AI 代理提供决策智能。分析选项、使用 PageRank 映射决策依赖关系、检测信息源冲突，并找出最重要的选择。",{"claudeCode":12},"Whatsonyourmind/oraclaw","oraclaw-decide","https://github.com/Whatsonyourmind/oraclaw",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":225,"workflow":242},1778699119124.6682,"kn7brgzmtpdc1cff8t3qgpg9m986ncay","zh-CN",{"checks":20,"evaluatedAt":195,"extensionSummary":196,"features":197,"nonGoals":203,"promptVersionExtension":207,"promptVersionScoring":208,"purpose":209,"rationale":210,"score":211,"summary":212,"tags":213,"tier":219,"useCases":220},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,188,192],{"category":22,"check":23,"severity":24,"summary":25},"实用性","问题相关性","pass","描述清晰地阐述了 AI 代理的决策智能问题，包括分析选项、映射依赖关系和检测冲突等具体任务。",{"category":22,"check":27,"severity":24,"summary":28},"独特性","该技能提供确定性的优化、模拟和分析工具（强盗算法、PageRank、收敛评分），超越了 LLM 在数学任务上的标准能力。",{"category":22,"check":30,"severity":24,"summary":31},"生产就绪性","该技能提供了一套全面的决策分析工具，文档和示例清晰，表明已准备好用于实际工作流程。",{"category":33,"check":34,"severity":24,"summary":35},"范围","单一职责原则","该技能专注于决策智能及相关的分析工具，保持了连贯的领域，不包含无关的功能。",{"category":33,"check":37,"severity":24,"summary":38},"描述质量","显示的描述准确地反映了该技能在决策智能、分析和查找有影响力的选择方面的能力。",{"category":40,"check":41,"severity":24,"summary":42},"调用","作用域工具","工具是作用域狭窄的动宾组合（例如，optimize_bandit、analyze_decision_graph），而不是通用的执行命令。",{"category":44,"check":45,"severity":24,"summary":46},"文档","配置和参数参考","SKILL.md 提供了清晰的工具文档，包括图分析的参数以及 ORACLAW_API_KEY 等先决条件。",{"category":33,"check":48,"severity":24,"summary":49},"工具命名","像 `optimize_bandit` 和 `analyze_decision_graph` 这样的工具名称具有描述性，并遵循动宾命名约定。",{"category":33,"check":51,"severity":24,"summary":52},"最小 I/O 表面","`analyze_decision_graph` 等工具的输入模式定义明确，只请求必要的数据，并具有结构化输出。",{"category":54,"check":55,"severity":24,"summary":56},"许可证","许可证可用性","该扩展根据 MIT 许可证分发，在 README 和 LICENSE 文件中清晰标明。",{"category":58,"check":59,"severity":24,"summary":60},"维护","提交近期性","最近一次提交是在 2026 年 5 月 2 日，在过去 90 天内，表明维护活跃。",{"category":58,"check":62,"severity":24,"summary":63},"依赖管理","该项目使用 npm 并列出了其 SDK 包，暗示了标准的依赖管理实践，并有一个锁文件。",{"category":65,"check":66,"severity":24,"summary":67},"安全","密钥管理","该技能需要 ORACLAW_API_KEY，其记录为环境变量，并且没有迹象表明密钥被回显。",{"category":65,"check":69,"severity":24,"summary":70},"注入","该扩展似乎将数据作为算法的输入，没有迹象表明执行不受信任的代码或指令来自外部数据。",{"category":65,"check":72,"severity":24,"summary":73},"传递性供应链炸弹","所有代码和依赖项似乎都已提交到存储库，没有运行时获取外部代码或指令。",{"category":65,"check":75,"severity":24,"summary":76},"沙箱隔离","工具操作数据输入并返回结构化输出，没有迹象表明修改了预期范围之外的文件。",{"category":65,"check":78,"severity":24,"summary":79},"沙箱逃逸原语","在提供的源代码中，没有迹象表明存在分离进程或围绕被拒绝的工具调用的重试循环。",{"category":65,"check":81,"severity":24,"summary":82},"数据泄露","该扩展处理分析数据，并且不向第三方提交机密用户数据。出站调用指向已记录的服务，如 Render。",{"category":65,"check":84,"severity":24,"summary":85},"隐藏文本技巧","捆绑的内容和描述没有隐藏的操纵技巧、控制字符或异常 Unicode。",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","不透明代码执行","代码似乎是纯 JavaScript/TypeScript，没有混淆、base64 负载或运行时脚本获取。",{"category":91,"check":92,"severity":24,"summary":93},"可移植性","结构假设","该技能定义了自己的工具，并依赖于标准环境变量，而不是特定的项目目录结构。",{"category":95,"check":96,"severity":24,"summary":97},"信任","问题关注度","在过去 90 天内，打开了 0 个问题，关闭了 44 个问题，维护者具有高关闭率并积极管理问题。",{"category":99,"check":100,"severity":24,"summary":101},"版本控制","发布管理","在 SKILL.md 前端 matéria 中声明了一个有意义的版本 `version: 1.0.0`，并且存在 CHANGELOG.md。",{"category":103,"check":104,"severity":24,"summary":105},"执行","验证","工具期望结构化输入（JSON）并返回结构化输出，这暗示了内部验证和清理。",{"category":65,"check":107,"severity":24,"summary":108},"无保护的破坏性操作","该技能是分析性的且只读的，不执行任何破坏性操作。",{"category":110,"check":111,"severity":24,"summary":112},"代码执行","错误处理","这些工具被设计为返回结构化 JSON，这暗示了带有清晰代码和消息的强大错误处理能力。",{"category":110,"check":114,"severity":115,"summary":116},"日志记录","not_applicable","该技能作为一个 API 和 MCP 服务器运行，日志记录由调用代理或服务器基础结构处理，而不是在技能包本身内部处理。",{"category":118,"check":119,"severity":24,"summary":120},"合规性","GDPR","该技能对提供的数据执行数学分析，并且不固有地操作或提交个人数据。",{"category":118,"check":122,"severity":24,"summary":123},"目标市场","该扩展使用标准的算法和数据格式，未检测到区域限制；targetMarket 为 global。",{"category":91,"check":125,"severity":24,"summary":126},"运行时稳定性","该技能依赖于标准的 Web API 和环境变量，使其可以跨不同运行时环境移植。",{"category":44,"check":128,"severity":24,"summary":129},"README","README 内容全面，详细介绍了项目的目的、实现以及如何开始。",{"category":33,"check":131,"severity":24,"summary":132},"工具表面积","该技能在 SKILL.md 中公开了 3 个核心工具，以及 17 个 MCP 工具的目录，这是一个合理的数量。",{"category":40,"check":134,"severity":24,"summary":135},"重叠近同义工具","公开的工具涵盖了不同的功能（optimize_bandit、analyze_decision_graph、score_convergence），没有显著重叠。",{"category":44,"check":137,"severity":24,"summary":138},"虚假特性","所有宣传的特性，包括 MCP 工具和 API 访问，都有相应的实现和文档。",{"category":140,"check":141,"severity":24,"summary":142},"安装","安装说明","提供了设置 MCP 服务器、REST API 和 npm SDK 的清晰说明，包括示例调用。",{"category":144,"check":145,"severity":24,"summary":146},"错误","可操作的错误消息","这些工具返回结构化 JSON，这意味着错误将被分类并带有代码和可能的修复提示。",{"category":103,"check":148,"severity":24,"summary":149},"固定的依赖项","该项目有一个锁文件 (`hasLockfile: true`) 并列出了特定的 SDK 包，表明依赖项已固定。",{"category":33,"check":151,"severity":115,"summary":152},"干运行预览","该技能是分析性的，不执行状态更改操作或出站数据发送，这些都需要干运行模式。",{"category":154,"check":155,"severity":24,"summary":156},"协议","幂等重试和超时","这些工具是为无状态 API 调用设计的，意味着它们是幂等的，并且应该在 API 层面实现超时。",{"category":118,"check":158,"severity":24,"summary":159},"遥测选择加入","该扩展似乎不发送遥测数据；如果发送，由于没有提及选择退出遥测，因此其选择加入性质是隐含的。",{"category":40,"check":161,"severity":24,"summary":162},"精确目的","SKILL.md 清楚地定义了其作为 AI 代理决策智能的目的，列出了具体用例和工具。",{"category":40,"check":164,"severity":24,"summary":165},"简洁的前端 matéria","前端 matéria 简洁且自成一体，提供了核心功能和触发短语的清晰摘要。",{"category":44,"check":167,"severity":24,"summary":168},"简洁的正文","SKILL.md 相当简洁，将大量材料留给 README 和其他链接资源。",{"category":170,"check":171,"severity":24,"summary":172},"上下文","渐进式披露","SKILL.md 概述了过程并链接到 README 等外部资源以获取更详细的信息，而不是嵌入所有内容。",{"category":170,"check":174,"severity":115,"summary":175},"分叉探索","此技能不适用于需要分叉上下文的深度探索或代码审查；它处理特定输入以进行分析。",{"category":22,"check":177,"severity":24,"summary":178},"使用示例","SKILL.md 和 README 提供了清晰、可直接使用的图分析和 API 调用示例，展示了可观察到的结果。",{"category":22,"check":180,"severity":24,"summary":181},"边缘情况","SKILL.md 概述了图分析输入的规则，并提供了收敛评分数据质量的指导，解决了潜在的故障模式。",{"category":110,"check":183,"severity":115,"summary":184},"工具回退","该技能主要公开其自己的工具和 MCP 服务器，没有隐含地依赖需要回退的其他特定技能。",{"category":91,"check":186,"severity":24,"summary":187},"堆栈假设","该技能依赖于标准的 Web 技术（REST API、npm SDK）和环境变量，没有任何特定的操作系统或语言运行时假设。",{"category":189,"check":190,"severity":24,"summary":191},"安全性","意外状态下的停止","该技能需要其分析工具的特定输入格式，这意味着它将在意外或格式错误的 상태 下以错误停止。",{"category":91,"check":193,"severity":24,"summary":194},"跨技能耦合","该技能的功能是自包含的，不依赖于同时加载的其他特定技能。",1778698934020,"该技能提供确定性的数学和分析工具，适用于 AI 代理，包括优化算法（强盗算法、遗传算法）、图分析（PageRank、瓶颈）、收敛评分和预测。可以通过 MCP 服务器、REST API 或 npm SDK 访问。",[198,199,200,201,202],"使用强盗算法和遗传算法分析选项","映射决策依赖关系并查找瓶颈","检测信息源的一致性和冲突","使用 PageRank 计算决策影响","提供 API 和 SDK 访问高级算法",[204,205,206],"执行通用 LLM 推理或文本生成","取代核心 AI 代理对话能力","提供主观或基于启发式的决策支持","3.0.0","4.4.0","为 AI 代理提供确定性的、数学上可靠的决策制定和分析能力，超越 LLM 的启发式方法。","所有检查均以高严重性通过，表明该技能文档齐全、安全且健壮。",100,"一个高质量的技能，为 AI 代理提供高级决策智能工具。",[214,215,216,217,218],"decision-making","analysis","optimization","graph-theory","ai-agent-tools","verified",[221,222,223,224],"从相互竞争的选项中选择最佳选项","映射决策之间的依赖关系并查找瓶颈","检查多个信息源是否一致或冲突","识别哪个决策具有最高涟漪效应",{"codeQuality":226,"collectedAt":228,"documentation":229,"maintenance":232,"security":238,"testCoverage":241},{"hasLockfile":227},true,1778698921380,{"descriptionLength":230,"readmeSize":231},175,9472,{"closedIssues90d":233,"forks":234,"hasChangelog":227,"manifestVersion":235,"openIssues90d":8,"pushedAt":236,"stars":237},44,2,"1.0.0",1777714123000,8,{"hasNpmPackage":239,"license":240,"smitheryVerified":239},false,"MIT",{"hasCi":227,"hasTests":227},{"updatedAt":243},1778699119124,{"basePath":245,"githubOwner":246,"githubRepo":247,"locale":18,"slug":13,"type":248},"mission-control/packages/clawhub-skills/oraclaw-decide","Whatsonyourmind","oraclaw","skill",null,{"evaluate":251,"extract":254},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":252,"targetMarket":253,"tier":219},[214,215,216,217,218],"global",{"commitSha":255},"HEAD",{"repoId":257,"translatedFrom":258},"kd76fmxm1ng903s4fmj0p7hxxs86ndkg","k17fe7ybjme5s1n10mmg3emmns86nr26",{"_creationTime":260,"_id":257,"identity":261,"providers":262,"workflow":421},1778698831609.0093,{"githubOwner":246,"githubRepo":247,"sourceUrl":14},{"classify":263,"discover":396,"github":399},{"commitSha":255,"extensions":264},[265,277,285,293,301,309,315,323,331,339,347,355,363,371,379],{"basePath":266,"description":267,"displayName":268,"installMethods":269,"rationale":270,"selectedPaths":271,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-anomaly","Anomaly detection for AI agents. Z-score, IQR, and streaming detection. Find outliers in data instantly. Sub-millisecond response. Works on single values or full datasets.","oraclaw-anomaly",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-anomaly/SKILL.md",[272],{"path":273,"priority":274},"SKILL.md","mandatory","rule","en",{"basePath":278,"description":279,"displayName":280,"installMethods":281,"rationale":282,"selectedPaths":283,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-bandit","A/B testing and feature optimization for AI agents. Pick the best option automatically using Multi-Armed Bandits and Contextual Bandits (LinUCB). No data warehouse needed — works from request","oraclaw-bandit",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-bandit/SKILL.md",[284],{"path":273,"priority":274},{"basePath":286,"description":287,"displayName":288,"installMethods":289,"rationale":290,"selectedPaths":291,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-bayesian","Bayesian inference engine for AI agents. Update beliefs with new evidence. Prior + evidence = posterior. Multi-factor prediction with calibration tracking.","oraclaw-bayesian",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-bayesian/SKILL.md",[292],{"path":273,"priority":274},{"basePath":294,"description":295,"displayName":296,"installMethods":297,"rationale":298,"selectedPaths":299,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-calibrate","Prediction quality scoring for AI agents. Brier score, log score, and multi-source convergence analysis. Know if your forecasts are accurate and if your data sources agree.","oraclaw-calibrate",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-calibrate/SKILL.md",[300],{"path":273,"priority":274},{"basePath":302,"description":303,"displayName":304,"installMethods":305,"rationale":306,"selectedPaths":307,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-cmaes","CMA-ES continuous optimization for AI agents. State-of-the-art derivative-free optimizer. 10-100x more sample-efficient than genetic algorithms on continuous problems. Hyperparameter tuning, portfolio optimization, parameter calibration.","oraclaw-cmaes",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-cmaes/SKILL.md",[308],{"path":273,"priority":274},{"basePath":245,"description":310,"displayName":13,"installMethods":311,"rationale":312,"selectedPaths":313,"source":275,"sourceLanguage":276,"type":248},"Decision intelligence for AI agents. Analyze options, map decision dependencies with PageRank, detect when information sources conflict, and find the choices that matter most.",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-decide/SKILL.md",[314],{"path":273,"priority":274},{"basePath":316,"description":317,"displayName":318,"installMethods":319,"rationale":320,"selectedPaths":321,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-ensemble","Multi-model consensus for AI agents. Combine predictions from multiple LLMs, models, or sources into a mathematically optimal consensus. Auto-weights by historical accuracy.","oraclaw-ensemble",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-ensemble/SKILL.md",[322],{"path":273,"priority":274},{"basePath":324,"description":325,"displayName":326,"installMethods":327,"rationale":328,"selectedPaths":329,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-evolve","Genetic Algorithm optimizer for AI agents. Multi-objective Pareto optimization for portfolio weights, pricing, hyperparameters, marketing mix — any problem with multiple competing goals. Handles nonlinear search spaces that LP solvers cannot.","oraclaw-evolve",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-evolve/SKILL.md",[330],{"path":273,"priority":274},{"basePath":332,"description":333,"displayName":334,"installMethods":335,"rationale":336,"selectedPaths":337,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-forecast","Time series forecasting for AI agents. ARIMA and Holt-Winters predictions with confidence intervals. Predict revenue, traffic, prices, or any sequential data. Sub-5ms inference.","oraclaw-forecast",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-forecast/SKILL.md",[338],{"path":273,"priority":274},{"basePath":340,"description":341,"displayName":342,"installMethods":343,"rationale":344,"selectedPaths":345,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-graph","Network intelligence for AI agents. PageRank, community detection (Louvain), critical path, and bottleneck analysis for any graph of connected things.","oraclaw-graph",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-graph/SKILL.md",[346],{"path":273,"priority":274},{"basePath":348,"description":349,"displayName":350,"installMethods":351,"rationale":352,"selectedPaths":353,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-pathfind","A* pathfinding and task sequencing for AI agents. Find the optimal path through workflows, dependencies, and decision trees. K-shortest paths via Yen's algorithm. Cost/time/risk breakdown.","oraclaw-pathfind",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-pathfind/SKILL.md",[354],{"path":273,"priority":274},{"basePath":356,"description":357,"displayName":358,"installMethods":359,"rationale":360,"selectedPaths":361,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-risk","Risk assessment engine for AI agents. Value at Risk (VaR), CVaR, stress testing, and multi-factor risk scoring. Monte Carlo powered. Built for trading agents, lending agents, and portfolio managers.","oraclaw-risk",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-risk/SKILL.md",[362],{"path":273,"priority":274},{"basePath":364,"description":365,"displayName":366,"installMethods":367,"rationale":368,"selectedPaths":369,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-simulate","Monte Carlo simulation for AI agents. Run thousands of probabilistic scenarios to model risk, forecast revenue, estimate project timelines, and quantify uncertainty. Supports 6 distribution types.","oraclaw-simulate",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-simulate/SKILL.md",[370],{"path":273,"priority":274},{"basePath":372,"description":373,"displayName":374,"installMethods":375,"rationale":376,"selectedPaths":377,"source":275,"sourceLanguage":276,"type":248},"mission-control/packages/clawhub-skills/oraclaw-solver","Industrial-grade scheduling and resource optimization for AI agents. Solve task scheduling with energy matching, budget allocation, and any LP/MIP constraint problem in milliseconds.","oraclaw-solver",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-solver/SKILL.md",[378],{"path":273,"priority":274},{"basePath":380,"description":381,"displayName":382,"installMethods":383,"license":240,"rationale":384,"selectedPaths":385,"source":275,"sourceLanguage":276,"type":395},"mission-control/packages/mcp-server","OraClaw Decision Intelligence — 17 MCP tools for AI agents (6 premium API-key tools + 11 free). Full input/output schemas + MCP behavior annotations on every tool. Optimization (bandit/CMA-ES/genetic/LP-MIP), simulation (Monte Carlo/scenarios), prediction (ARIMA/Holt-Winters/Bayesian/ensemble), scoring (convergence/calibration), graph analytics, anomaly detection, pathfinding, scheduling.","@oraclaw/mcp-server",{"npm":382},"server.json with namespace/server name at mission-control/packages/mcp-server/server.json",[386,388,390,392],{"path":387,"priority":274},"server.json",{"path":389,"priority":274},"package.json",{"path":391,"priority":274},"README.md",{"path":393,"priority":394},"src/index.ts","low","mcp",{"sources":397},[398],"manual",{"closedIssues90d":233,"description":400,"forks":234,"homepage":401,"license":240,"openIssues90d":8,"pushedAt":236,"readmeSize":231,"stars":237,"topics":402},"Deterministic decision-intelligence MCP server for AI agents — 17 tools, 21 algorithms (LinUCB, HiGHS LP/MIP, PageRank, Monte Carlo, CMA-ES, conformal). Sub-25ms. Zero LLM cost. AAA on Glama. Field-validated in 12+ OSS projects.","https://web-olive-one-89.vercel.app",[403,404,405,406,407,408,409,395,216,410,411,412,413,414,415,416,417,418,419,420],"ai-agents","algorithms","api","bandits","decision-intelligence","fastify","machine-learning","typescript","agent-tools","anthropic","claude-mcp","contextual-bandit","deterministic-tools","linear-programming","llm-tools","model-context-protocol","monte-carlo","pagerank",{"classifiedAt":422,"discoverAt":423,"extractAt":424,"githubAt":424,"updatedAt":422},1778698837409,1778698831609,1778698835357,[218,215,214,217,216],{"evaluatedAt":427,"extractAt":428,"updatedAt":243},1778698934136,1778698837670,[],[431,460,489,517,547,578],{"_creationTime":432,"_id":433,"community":434,"display":435,"identity":441,"providers":446,"relations":454,"tags":456,"workflow":457},1778696691708.3035,"k17br1j5s86ae90zqeyd7zcg2586mkwr",{"reviewCount":8},{"description":436,"installMethods":437,"name":439,"sourceUrl":440},"Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms\n",{"claudeCode":438},"ruvnet/ruflo","Performance Analysis","https://github.com/ruvnet/ruflo",{"basePath":442,"githubOwner":443,"githubRepo":444,"locale":276,"slug":445,"type":248},".claude/skills/performance-analysis","ruvnet","ruflo","performance-analysis",{"evaluate":447,"extract":453},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":448,"targetMarket":253,"tier":219},[449,215,216,450,451,452],"performance","claude-flow","bottleneck-detection","reporting",{"commitSha":255,"license":240},{"repoId":455},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[215,451,450,216,449,452],{"evaluatedAt":458,"extractAt":459,"updatedAt":458},1778699217174,1778696691708,{"_creationTime":461,"_id":462,"community":463,"display":464,"identity":470,"providers":475,"relations":482,"tags":485,"workflow":486},1778692488329.0164,"k17d7dgccv6vnj9tcw0cehwnph86nryb",{"reviewCount":8},{"description":465,"installMethods":466,"name":468,"sourceUrl":469},"Analyze which rules are actively used vs inert. Detect coverage gaps. Recommend pruning to reduce token consumption.",{"claudeCode":467},"luiseiman/claude-kit","Rule Effectiveness Analysis","https://github.com/luiseiman/claude-kit",{"basePath":471,"githubOwner":472,"githubRepo":473,"locale":276,"slug":474,"type":248},"skills/rule-effectiveness","luiseiman","claude-kit","rule-effectiveness",{"evaluate":476,"extract":481},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":477,"targetMarket":253,"tier":219},[478,479,215,216,480],"claude-code","configuration","git",{"commitSha":255,"license":240},{"parentExtensionId":483,"repoId":484},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[215,478,479,480,216],{"evaluatedAt":487,"extractAt":488,"updatedAt":487},1778693275143,1778692488329,{"_creationTime":490,"_id":491,"community":492,"display":493,"identity":499,"providers":503,"relations":511,"tags":513,"workflow":514},1778697652123.8975,"k17egwaz31kmprzw1q8m38fv4586mqah",{"reviewCount":8},{"description":494,"installMethods":495,"name":497,"sourceUrl":498},"Search and analyze your own session logs (older/parent conversations) using jq.",{"claudeCode":496},"steipete/clawdis","session-logs","https://github.com/steipete/clawdis",{"basePath":500,"githubOwner":501,"githubRepo":502,"locale":276,"slug":497,"type":248},"skills/session-logs","steipete","clawdis",{"evaluate":504,"extract":510},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":505,"targetMarket":253,"tier":219},[506,507,508,215,509],"logs","session","jq","cli",{"commitSha":255},{"repoId":512},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[215,509,508,506,507],{"evaluatedAt":515,"extractAt":516,"updatedAt":515},1778698902636,1778697652123,{"_creationTime":518,"_id":519,"community":520,"display":521,"identity":527,"providers":532,"relations":539,"tags":542,"workflow":543},1778697369386.3174,"k17bxj50v6wxff2qe5a5a4d4bn86mvk3",{"reviewCount":8},{"description":522,"installMethods":523,"name":525,"sourceUrl":526},"关于演示文稿幻灯片格式、权重系统、导航和章节结构的知识",{"claudeCode":524},"shanraisshan/claude-code-best-practice","Presentation Structure","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":528,"githubOwner":529,"githubRepo":530,"locale":18,"slug":531,"type":248},".claude/skills/presentation/presentation-structure","shanraisshan","claude-code-best-practice","presentation-structure",{"evaluate":533,"extract":538},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":534,"targetMarket":253,"tier":219},[535,536,537,215],"presentation","html","documentation",{"commitSha":255,"license":240},{"repoId":540,"translatedFrom":541},"kd74710g49kxgwbfjxeb7s132d86myxr","k175cp8c6m1kknsf9yhd75swn586m4hj",[215,537,536,535],{"evaluatedAt":544,"extractAt":545,"updatedAt":546},1778697246983,1778697205743,1778697369386,{"_creationTime":548,"_id":549,"community":550,"display":551,"identity":557,"providers":561,"relations":571,"tags":574,"workflow":575},1778695548458.3403,"k17874jrpzpfq3ftmmahe017n586nmy2",{"reviewCount":8},{"description":552,"installMethods":553,"name":555,"sourceUrl":556},"Compose or analyze sacred music in Hildegard von Bingen's distinctive modal style. Covers modal selection, melodic contour (wide-range melodies), text-setting (syllabic and melismatic), neumatic notation, and liturgical context for antiphons, sequences, and responsories. Use when composing a new piece in Hildegardian style, analyzing an existing chant for structure and mode, researching medieval modal music, preparing to perform or teach Hildegard's music, or setting Latin sacred texts.\n",{"claudeCode":554},"pjt222/agent-almanac","compose-sacred-music","https://github.com/pjt222/agent-almanac",{"basePath":558,"githubOwner":559,"githubRepo":560,"locale":276,"slug":555,"type":248},"skills/compose-sacred-music","pjt222","agent-almanac",{"evaluate":562,"extract":570},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":563,"targetMarket":253,"tier":219},[564,565,566,567,568,569,215],"hildegard","sacred-music","chant","modal","musicology","composition",{"commitSha":255},{"parentExtensionId":572,"repoId":573},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[215,566,569,564,567,568,565],{"evaluatedAt":576,"extractAt":577,"updatedAt":576},1778696688896,1778695548458,{"_creationTime":579,"_id":580,"community":581,"display":582,"identity":588,"providers":592,"relations":599,"tags":601,"workflow":602},1778684091954.6682,"k1724x2k19t06bmxsstfq8t7xs86ntjn",{"reviewCount":8},{"description":583,"installMethods":584,"name":586,"sourceUrl":587},"Run Cogny marketing analysis tasks — fetch scheduled tasks, analyze ad accounts via MCP, report findings",{"claudeCode":585},"cognyai/claude-code-marketing-skills","cogny","https://github.com/cognyai/claude-code-marketing-skills",{"basePath":589,"githubOwner":590,"githubRepo":591,"locale":276,"slug":586,"type":248},"skills/cogny","cognyai","claude-code-marketing-skills",{"evaluate":593,"extract":598},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":594,"targetMarket":253,"tier":219},[595,215,586,596,597,452],"marketing","ads","automation",{"commitSha":255},{"repoId":600},"kd7371gwzbdr07nc839hsmagw986nje6",[596,215,597,586,595,452],{"evaluatedAt":603,"extractAt":604,"updatedAt":603},1778684198526,1778684091954]