[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-Whatsonyourmind-oraclaw-solver-zh-CN":3,"guides-for-Whatsonyourmind-oraclaw-solver":426,"similar-k1760hxt0cnnrqhq23p0yead4586nmqs-zh-CN":427},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":242,"isFallback":237,"parentExtension":247,"providers":248,"relations":254,"repo":257,"tags":422,"workflow":423},1778699177208.4888,"k1760hxt0cnnrqhq23p0yead4586nmqs",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"为 AI 代理提供工业级的调度和资源优化。在几毫秒内通过能源匹配、预算分配和任何 LP/MIP 约束问题来解决任务调度。",{"claudeCode":12},"Whatsonyourmind/oraclaw","oraclaw-solver","https://github.com/Whatsonyourmind/oraclaw",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":240},1778699177208.489,"kn79m16afrv4y50cyrckpy5fm986mgvc","zh-CN",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"tier":217,"useCases":218},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","描述清楚地说明了 AI 代理调度和资源优化的挑战，明确了任务和约束。",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","该技能通过提供复杂问题的确定性、数学上正确的优化解决方案，超越了简单的提示，解决了 LLM 启发式问题。",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","该技能为优化任务提供了完整的生命周期覆盖，具有清晰的工具和定价，适合立即集成到工作流程中。",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","该技能专注于优化和数学问题解决，遵循单一领域原则。",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","显示的描述准确地反映了该技能在优化和调度方面的能力。",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","工具被指定名称（例如 `solve_schedule`、`solve_constraints`）并专注于不同的优化任务。",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","SKILL.md 提供了 `solve_schedule` 和 `solve_constraints` 参数的清晰示例，默认行为由示例暗示。",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","像 `solve_schedule` 和 `solve_constraints` 这样的工具名称具有描述性，并与领域保持一致。",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","工具的输入参数是结构化的且具体的，输出专注于优化结果，而不是无关数据。",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","该项目在 MIT 许可下发布，这是一个允许的开源许可，并有一个专门的 LICENSE 文件。",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","最后一次提交是在 2026 年 5 月 2 日，表明最近有维护。",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","该项目使用 npm 和 lockfiles，表明具有良好的依赖管理实践。",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","该技能需要 `ORACLAW_API_KEY`，它通过环境变量处理，而不是硬编码。",{"category":65,"check":69,"severity":24,"summary":70},"Injection","该技能的工具定义明确，并且似乎不执行任意代码或加载不受信任的外部指令。",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","该技能在运行时不获取外部代码或内容；所有依赖项似乎都已通过标准包管理器捆绑或安装。",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","该技能在定义的范围内（MCP 服务器、API）运行，并且没有试图修改其指定项目文件夹之外文件的迹象。",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","未发现拒绝工具调用的分离进程或重试循环的证据。",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","该技能不指示代理读取或提交机密数据给第三方。出站调用似乎已记录在案。",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","捆绑的内容和文档似乎没有隐藏的操纵技巧、控制字符或不可见的 Unicode 标签。",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","MCP 服务器和 SDK 包是用标准的 TypeScript/JavaScript 实现的，并且没有混淆。",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","该技能不对用户项目结构做任何假设，独立运行。",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","在过去 90 天内有 0 个打开的问题和 44 个已关闭的问题，维护者参与度非常出色。",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","SKILL.md 前端部分的 `version` 字段设置为 '1.0.0'，表明版本控制清晰。",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","工具输入是结构化的 JSON，这意味着 MCP 服务器或 API 会通过模式符合性进行验证。",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","该技能执行优化计算，不涉及破坏性操作。",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","该工具旨在返回结构化的结果，这暗示了对不可行问题或其他问题的稳健错误处理。",{"category":110,"check":114,"severity":115,"summary":116},"Logging","not_applicable","该技能主要是一个提供结构化输出的 API/MCP 服务器，而不是需要本地审计日志的破坏性或复杂过程。",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","该技能处理抽象的数学问题，不处理个人数据。",{"category":118,"check":122,"severity":24,"summary":123},"Target market","该技能的优化能力具有普遍适用性，未检测到区域限制。",{"category":91,"check":125,"severity":24,"summary":126},"Runtime stability","该技能作为 API 或 MCP 服务器运行，并依赖于标准的 Web 技术和 Node.js，确保了广泛的兼容性。",{"category":44,"check":128,"severity":24,"summary":129},"README","README 内容全面、结构清晰，并清楚地解释了该技能的目的和功能。",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","MCP 工具目录列出了 17 个工具，这在可接受的范围内并且有充分的文档记录。",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","列出的工具名称和功能各不相同，避免了冗余。",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","所有宣传的功能，包括特定的工具和 API 端点，都已实现并有文档记录。",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","提供了 MCP 服务器、REST API 和 npm SDK 的清晰安装说明，并附有可复制代码示例。",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","API 和工具文档暗示了结构化的响应，其中将包含可操作的错误消息，用于不可行问题或其他问题。",{"category":103,"check":148,"severity":24,"summary":149},"Pinned dependencies","该项目表明使用了 npm 并且有一个 lockfile，这表明依赖项已固定。",{"category":33,"check":151,"severity":115,"summary":152},"Dry-run preview","该技能执行确定性计算，不涉及需要干运行功能的更改状态操作或出站数据传输。",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","该工具是无状态计算，因此是天然幂等的。API 文档暗示了及时的响应。",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","未提及遥测，且该技能的设计表明它不收集用户数据。",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","`SKILL.md` 精确定义了调度和优化的目的，包括工件和用户意图，如规划和分配。",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","`SKILL.md` 的前端部分简洁明了，清楚地说明了核心能力并提供了触发短语。",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","`SKILL.md` 内容简洁，详细说明了核心功能并有效使用了示例。",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","`SKILL.md` 内容简洁，提供详细的示例和工具说明，符合渐进披露原则。",{"category":170,"check":174,"severity":115,"summary":175},"Forked exploration","该技能执行直接计算，不涉及需要 `context: fork` 的深度探索或代码审查。",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","`SKILL.md` 和 README 提供了清晰、可直接使用的 JSON 示例，用于调度和自定义约束优化。",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","`SKILL.md` 提到了不可行问题以及如何通过放宽约束来处理它们，涵盖了一个关键的边缘情况。",{"category":110,"check":183,"severity":115,"summary":184},"Tool Fallback","该技能不依赖于需要回退机制的外部 MCP 服务器或工具。",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","求解器的确定性性质以及对不可行问题的明确处理表明，意外状态会适当地中止工作流。",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","该技能是自包含的，专注于优化任务，并且似乎不隐式依赖于其他技能。",1778699052626,"该技能为 AI 代理提供确定性的优化解决方案，能够通过 `solve_schedule` 和 `solve_constraints` 等特定工具处理任务调度、预算分配和通用的 LP/MIP 约束问题。它包括一个 REST API 和 SDK。",[195,196,197,198,199],"具有能源匹配功能的工业级调度","具有自定义约束的预算分配","用于优化问题的 LP/MIP 求解器","确定性且毫秒级的快速结果","用于广泛集成的 REST API 和 SDK",[201,202,203],"执行基于启发式或近似的解决方案","替代 LLM 在非数学任务上的推理能力","处理无法进行数学优化的任务","3.0.0","4.4.0","为 AI 代理提供数学上精确且确定性的优化能力，使它们能够高效、准确地解决复杂的调度和资源分配问题。","该扩展经过精心打磨，拥有出色的文档、清晰的目标和强大的实现，涵盖了复杂的优化任务。所有检查均以高质量通过。",100,"一个强大且文档齐全的技能，用于工业级的 AI 代理调度和资源优化。",[211,212,213,214,215,216],"optimization","scheduling","linear-programming","resource-allocation","operations-research","planning","verified",[219,220,221,222],"规划将任务与能源水平匹配的每日/每周计划","在具有硬性约束的竞争优先级之间分配预算","解决容量有限的资源分配问题","优化人员配置、路线规划或容量规划",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"security":236,"testCoverage":239},{"hasLockfile":225},true,1778699040327,{"descriptionLength":228,"readmeSize":229},182,9472,{"closedIssues90d":231,"forks":232,"hasChangelog":225,"manifestVersion":233,"openIssues90d":8,"pushedAt":234,"stars":235},44,2,"1.0.0",1777714123000,8,{"hasNpmPackage":237,"license":238,"smitheryVerified":237},false,"MIT",{"hasCi":225,"hasTests":225},{"updatedAt":241},1778699177208,{"basePath":243,"githubOwner":244,"githubRepo":245,"locale":18,"slug":13,"type":246},"mission-control/packages/clawhub-skills/oraclaw-solver","Whatsonyourmind","oraclaw","skill",null,{"evaluate":249,"extract":252},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":250,"targetMarket":251,"tier":217},[211,212,213,214,215,216],"global",{"commitSha":253},"HEAD",{"repoId":255,"translatedFrom":256},"kd76fmxm1ng903s4fmj0p7hxxs86ndkg","k179wx4phqshs3khsdvgw86k4d86mjag",{"_creationTime":258,"_id":255,"identity":259,"providers":260,"workflow":418},1778698831609.0093,{"githubOwner":244,"githubRepo":245,"sourceUrl":14},{"classify":261,"discover":394,"github":397},{"commitSha":253,"extensions":262},[263,275,283,291,299,307,315,323,331,339,347,355,363,371,377],{"basePath":264,"description":265,"displayName":266,"installMethods":267,"rationale":268,"selectedPaths":269,"source":273,"sourceLanguage":274,"type":246},"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",[270],{"path":271,"priority":272},"SKILL.md","mandatory","rule","en",{"basePath":276,"description":277,"displayName":278,"installMethods":279,"rationale":280,"selectedPaths":281,"source":273,"sourceLanguage":274,"type":246},"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",[282],{"path":271,"priority":272},{"basePath":284,"description":285,"displayName":286,"installMethods":287,"rationale":288,"selectedPaths":289,"source":273,"sourceLanguage":274,"type":246},"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",[290],{"path":271,"priority":272},{"basePath":292,"description":293,"displayName":294,"installMethods":295,"rationale":296,"selectedPaths":297,"source":273,"sourceLanguage":274,"type":246},"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",[298],{"path":271,"priority":272},{"basePath":300,"description":301,"displayName":302,"installMethods":303,"rationale":304,"selectedPaths":305,"source":273,"sourceLanguage":274,"type":246},"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",[306],{"path":271,"priority":272},{"basePath":308,"description":309,"displayName":310,"installMethods":311,"rationale":312,"selectedPaths":313,"source":273,"sourceLanguage":274,"type":246},"mission-control/packages/clawhub-skills/oraclaw-decide","Decision intelligence for AI agents. Analyze options, map decision dependencies with PageRank, detect when information sources conflict, and find the choices that matter most.","oraclaw-decide",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-decide/SKILL.md",[314],{"path":271,"priority":272},{"basePath":316,"description":317,"displayName":318,"installMethods":319,"rationale":320,"selectedPaths":321,"source":273,"sourceLanguage":274,"type":246},"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":271,"priority":272},{"basePath":324,"description":325,"displayName":326,"installMethods":327,"rationale":328,"selectedPaths":329,"source":273,"sourceLanguage":274,"type":246},"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":271,"priority":272},{"basePath":332,"description":333,"displayName":334,"installMethods":335,"rationale":336,"selectedPaths":337,"source":273,"sourceLanguage":274,"type":246},"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":271,"priority":272},{"basePath":340,"description":341,"displayName":342,"installMethods":343,"rationale":344,"selectedPaths":345,"source":273,"sourceLanguage":274,"type":246},"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":271,"priority":272},{"basePath":348,"description":349,"displayName":350,"installMethods":351,"rationale":352,"selectedPaths":353,"source":273,"sourceLanguage":274,"type":246},"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":271,"priority":272},{"basePath":356,"description":357,"displayName":358,"installMethods":359,"rationale":360,"selectedPaths":361,"source":273,"sourceLanguage":274,"type":246},"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":271,"priority":272},{"basePath":364,"description":365,"displayName":366,"installMethods":367,"rationale":368,"selectedPaths":369,"source":273,"sourceLanguage":274,"type":246},"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":271,"priority":272},{"basePath":243,"description":372,"displayName":13,"installMethods":373,"rationale":374,"selectedPaths":375,"source":273,"sourceLanguage":274,"type":246},"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.",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-solver/SKILL.md",[376],{"path":271,"priority":272},{"basePath":378,"description":379,"displayName":380,"installMethods":381,"license":238,"rationale":382,"selectedPaths":383,"source":273,"sourceLanguage":274,"type":393},"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":380},"server.json with namespace/server name at mission-control/packages/mcp-server/server.json",[384,386,388,390],{"path":385,"priority":272},"server.json",{"path":387,"priority":272},"package.json",{"path":389,"priority":272},"README.md",{"path":391,"priority":392},"src/index.ts","low","mcp",{"sources":395},[396],"manual",{"closedIssues90d":231,"description":398,"forks":232,"homepage":399,"license":238,"openIssues90d":8,"pushedAt":234,"readmeSize":229,"stars":235,"topics":400},"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",[401,402,403,404,405,406,407,393,211,408,409,410,411,412,413,213,414,415,416,417],"ai-agents","algorithms","api","bandits","decision-intelligence","fastify","machine-learning","typescript","agent-tools","anthropic","claude-mcp","contextual-bandit","deterministic-tools","llm-tools","model-context-protocol","monte-carlo","pagerank",{"classifiedAt":419,"discoverAt":420,"extractAt":421,"githubAt":421,"updatedAt":419},1778698837409,1778698831609,1778698835357,[213,215,211,216,214,212],{"evaluatedAt":424,"extractAt":425,"updatedAt":241},1778699052902,1778698837670,[],[428,458,479,511,539,568],{"_creationTime":429,"_id":430,"community":431,"display":432,"identity":438,"providers":443,"relations":452,"tags":454,"workflow":455},1778696691708.3035,"k17br1j5s86ae90zqeyd7zcg2586mkwr",{"reviewCount":8},{"description":433,"installMethods":434,"name":436,"sourceUrl":437},"Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms\n",{"claudeCode":435},"ruvnet/ruflo","Performance Analysis","https://github.com/ruvnet/ruflo",{"basePath":439,"githubOwner":440,"githubRepo":441,"locale":274,"slug":442,"type":246},".claude/skills/performance-analysis","ruvnet","ruflo","performance-analysis",{"evaluate":444,"extract":451},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":445,"targetMarket":251,"tier":217},[446,447,211,448,449,450],"performance","analysis","claude-flow","bottleneck-detection","reporting",{"commitSha":253,"license":238},{"repoId":453},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[447,449,448,211,446,450],{"evaluatedAt":456,"extractAt":457,"updatedAt":456},1778699217174,1778696691708,{"_creationTime":459,"_id":460,"community":461,"display":462,"identity":465,"providers":466,"relations":473,"tags":475,"workflow":476},1778699119124.668,"k174xef0y7h5dr9f932g3ax6d986n2dd",{"reviewCount":8},{"description":463,"installMethods":464,"name":310,"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},{"basePath":308,"githubOwner":244,"githubRepo":245,"locale":18,"slug":310,"type":246},{"evaluate":467,"extract":472},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":468,"targetMarket":251,"tier":217},[469,447,211,470,471],"decision-making","graph-theory","ai-agent-tools",{"commitSha":253},{"repoId":255,"translatedFrom":474},"k17fe7ybjme5s1n10mmg3emmns86nr26",[471,447,469,470,211],{"evaluatedAt":477,"extractAt":425,"updatedAt":478},1778698934136,1778699119124,{"_creationTime":480,"_id":481,"community":482,"display":483,"identity":489,"providers":494,"relations":502,"tags":506,"workflow":507},1778694375752.5935,"k176q0fcrs34d0qgcw5zcfr7e186mppv",{"reviewCount":8},{"description":484,"installMethods":485,"name":487,"sourceUrl":488},"为任何支持的驱动程序语言优化 MongoDB 客户端连接配置（池、超时、模式）。在处理/更新/审查实例化或配置 MongoDB 客户端（例如，调用 `connect()` 时）、配置连接池、对连接错误（ECONNREFUSED、超时、池耗尽）进行故障排除、优化与连接相关的性能问题时，请使用此技能。这包括构建具有 MongoDB 的无服务器函数、创建使用 MongoDB 的 API 端点、优化高流量 MongoDB 应用程序、创建长期运行任务和并发性，或调试与连接相关的失败等场景。",{"claudeCode":486},"mongodb/agent-skills","MongoDB Connection Optimizer","https://github.com/mongodb/agent-skills",{"basePath":490,"githubOwner":491,"githubRepo":492,"locale":18,"slug":493,"type":246},"skills/mongodb-connection","mongodb","agent-skills","mongodb-connection",{"evaluate":495,"extract":500},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":496,"targetMarket":251,"tier":217},[491,497,498,446,211,499],"database","connection","configuration",{"commitSha":253,"license":501},"Apache-2.0",{"parentExtensionId":503,"repoId":504,"translatedFrom":505},"k170hje3xzpy2mbkn00agzm38x86mkbz","kd74vahs1zbjqzqbert490xyrd86nfv5","k175wmq2n17n23xzphj2zzt3qs86n3xd",[499,498,497,491,211,446],{"evaluatedAt":508,"extractAt":509,"updatedAt":510},1778694243014,1778694149049,1778694375752,{"_creationTime":512,"_id":513,"community":514,"display":515,"identity":521,"providers":526,"relations":532,"tags":535,"workflow":536},1778692488329.0164,"k17d7dgccv6vnj9tcw0cehwnph86nryb",{"reviewCount":8},{"description":516,"installMethods":517,"name":519,"sourceUrl":520},"Analyze which rules are actively used vs inert. Detect coverage gaps. Recommend pruning to reduce token consumption.",{"claudeCode":518},"luiseiman/claude-kit","Rule Effectiveness Analysis","https://github.com/luiseiman/claude-kit",{"basePath":522,"githubOwner":523,"githubRepo":524,"locale":274,"slug":525,"type":246},"skills/rule-effectiveness","luiseiman","claude-kit","rule-effectiveness",{"evaluate":527,"extract":531},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":528,"targetMarket":251,"tier":217},[529,499,447,211,530],"claude-code","git",{"commitSha":253,"license":238},{"parentExtensionId":533,"repoId":534},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[447,529,499,530,211],{"evaluatedAt":537,"extractAt":538,"updatedAt":537},1778693275143,1778692488329,{"_creationTime":540,"_id":541,"community":542,"display":543,"identity":549,"providers":553,"relations":560,"tags":563,"workflow":564},1778692978469.281,"k17fvrbr8zcyr4j5pmdazwefps86mk8e",{"reviewCount":8},{"description":544,"installMethods":545,"name":547,"sourceUrl":548},"自动化分析、评估、设计和优化目标项目。将 VibeGuard 集成作为基线扫描，修复过程遵循 VibeGuard 规范，并在最后运行合规性检查。支持 auto-run-agent 自主执行。",{"claudeCode":546},"majiayu000/vibeguard","auto-optimize","https://github.com/majiayu000/vibeguard",{"basePath":550,"githubOwner":551,"githubRepo":552,"locale":18,"slug":547,"type":246},"workflows/auto-optimize","majiayu000","vibeguard",{"evaluate":554,"extract":559},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":555,"targetMarket":251,"tier":217},[556,211,552,557,558],"code-analysis","automation","developer-tools",{"commitSha":253},{"repoId":561,"translatedFrom":562},"kd7b0vh258xpbyerk68bk3e1ks86mk58","k170rpk64k5rypx65jra7hetvx86nt23",[557,556,558,211,552],{"evaluatedAt":565,"extractAt":566,"updatedAt":567},1778692790049,1778692607327,1778692978469,{"_creationTime":569,"_id":570,"community":571,"display":572,"identity":578,"providers":582,"relations":590,"tags":593,"workflow":594},1778691497595.9666,"k170aa7za6n5wvxtwx7xj8dc9d86mx9e",{"reviewCount":8},{"description":573,"installMethods":574,"name":576,"sourceUrl":577},"Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to \"compress image\", \"optimize image\", \"convert to webp\", or reduce image file size.",{"claudeCode":575},"jimliu/baoyu-skills","baoyu-compress-image","https://github.com/jimliu/baoyu-skills",{"basePath":579,"githubOwner":580,"githubRepo":581,"locale":274,"slug":576,"type":246},"skills/baoyu-compress-image","jimliu","baoyu-skills",{"evaluate":583,"extract":589},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":584,"targetMarket":251,"tier":217},[585,586,587,588,211],"image","compression","webp","png",{"commitSha":253},{"parentExtensionId":591,"repoId":592},"k172q4hxm2acmg5ree5aeemx1x86m6hx","kd718jn448p61w289hzf15tecd86n3a4",[586,585,211,588,587],{"evaluatedAt":595,"extractAt":596,"updatedAt":595},1778691619519,1778691497596]