lark-apps妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用协作者与协作权限设置、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要开发/新建一个系统·工具·平台·应用，或要本地开发 / 云端开发 / 修改 / 部署 /…lark-base飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权由 MCP server 自动处理。lark-calendar飞书日历：管理日历日程和会议室。查看/搜索日程、创建/更新日程、管理参会人、查询忙闲和推荐时段、预定会议室。当用户需要查看日程安排、创建/修改会议、查询/预定会议室时使用。不负责：查询过去的视频会议记录（走 lark-meeting）、待办任务（走 lark-task）。lark-doc飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 lark_docs_fetch。表格或 Base 内部数据操作不在本 skill。lark-drive飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token…lark-im飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。lark-meeting飞书视频会议：查询会议记录与会议产物(纪要/逐字稿/妙记)、妙记搜索/上传/下载/编辑、机器人参与会议(⚠️ 应用身份写操作，MCP server 不可用)；查询进行中的会议、实时会议内容(发言/聊天/共享文档)问答(会上/会里)、发送会中聊天/表情；基于 meeting_id、meeting_no、event_id、note_id、minute_token、vc-node-id 或妙记 URL 查询相关信息。预约会议、忙闲和会议室管理走 lark-calendar。lark-slides飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 lark-doc）、云文档里的独立画板对象（走 lark-whiteboard）、上传或下载普通文件（走…
explorador de repositorios
aws-samples · Repositorios y skills representativas - Página 2
Vista por repositorio de 1166 skills recopiladas en 176 repositorios de GitHub.
gpu-instance-selectionSelect optimal EC2 GPU instance types for Physical AI RL training based on VRAM, interconnect, and cost requirementskubernetes-native-featuresLeverage Kubernetes-native features for GPU training including GPU Operator, topology scheduling, and priority classesdeployment-methodDeploy and manage Physical AI RL training jobs on EKS including CodeBuild CI, GitOps, and experiment managementeks-cluster-provisioningProvision an Amazon EKS cluster with GPU node groups, EFA networking, and OIDC for Physical AI RL training workloadsrlinf-dataset-preparationRLinf: Download, preprocess, and stage datasets and model weights for RLinf training on EKSfunctional-testingValidate the Physical AI RL training stack end-to-end from infrastructure smoke tests to training step verificationkubernetes-manifestsConstruct Kubernetes Jobs, StatefulSets, and Services for GPU-accelerated RL training workloads on EKSrlinf-functional-testingRLinf: Validate RLinf training examples end-to-end from container tests to single-step training
skill-evalEvaluate AI Agent Skills across safety, quality, reliability, and cost efficiency. Audit for security issues (secrets, injection, unsafe installs), test functional correctness with-skill vs without-skill, measure trigger precision, classify cost-efficiency…pr-namingchecks PR namespr-naming-conventionValidates PR titles and branch names against the company naming convention. Use when the user mentions PR titles, branch naming, pull request naming conventions, or asks to check whether a PR title or branch name follows the standard format.pr-naming-conventionValidates PR titles and branch names against the company naming convention. Use when the user mentions PR titles, branch naming, pull request naming conventions, or asks to check whether a PR title or branch name follows the standard format.data-analysisAnalyze CSV and JSON data files to produce summary statistics, detect anomalies, and generate formatted reports. Use when the user asks to summarize data, compute statistics (mean, median, percentiles), find outliers, or produce tabular reports from…sloppy-weatherGets weathergood-skillA well-structured test skill that follows the agentskills.io spec. Use when testing skill evaluation tools.good-skillA well-structured test skill that follows the agentskills.io spec. Use when testing skill evaluation tools.
api-gateway-authorizer-securitySecure Amazon API Gateway routes when a scanner reports missing authorization, choose Cognito/OIDC JWT or other business authorizers first, and use an always-allow Lambda authorizer only as an explicitly documented fallback for public routes.agentic-responsible-ai-assessmentWalk a client through a Responsible AI assessment questionnaire and score their answers 0-5 across eight RAI dimensions (Governance, Privacy & Security, Safety, Veracity & Robustness, Controllability, Fairness, Explainability, Transparency). Use when a user…gitlab-docs-publishingPublish HTML/Markdown design documents on GitLab Pages with selection-driven discussion. Reviewers select any text in the published doc; a floating 💬 bubble opens a prefilled GitLab Issue (title + anchor link + selection quote + label) in a new tab. GitLab…security-scanComprehensive security and compliance scanning for AWS CDK projects. Use when running security audits, checking license compliance, scanning container vulnerabilities, or running aggregated SAST/IaC/secret analysis before deployment.agentcore-browser-web-scrapingBuild production web scraping on Bedrock AgentCore Browser — connect Playwright over signed CDP WebSocket, drive extraction with an LLM agent over fixed tool primitives (navigate, scroll, extract-by-selector, screenshot), reuse login state via Browser…agentcore-mcp-oauth-facadeBuild an OAuth + MCP protocol facade in front of Bedrock AgentCore Gateway or Runtime so strict MCP clients (Claude Code, Cursor, Amazon Quick, mcp-remote) can connect. Use when an MCP client fails OAuth discovery ("Fix highlighted fields", DCR errors), when…aws-agentic-aiAWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore service including Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, or Evaluations.…end-to-end-testingSystematic E2E testing workflow with evidence capture and reporting. Use when running integration tests, validating complete user flows, capturing test evidence, or generating test reports.
aidlc-prototypeBuild a throwaway spike to validate requirements. Demonstrates core user flows with minimal code — no architecture, no tests, no production concerns.aidlc-deployCI/CD pipeline generation and deployment configuration. Produces pipeline configs, environment definitions, and deployment scripts for the target platform.aidlc-buildFinal integration build and test verification. Validates that implemented code compiles, passes all test suites, and meets quality gates before deployment.aidlc-implementCode generation and testing. Execute implementation tasks from design specs using standard, parallel, or autonomous modes.aidlc-code-reviewReview implemented code against design specs, coding standards, and best practices. Produces severity-classified findings with suggested fixes.aidlc-decompositionDecompose requirements into units of work with DDD concepts. Define system boundaries, dependencies, and development sequence.aidlc-designTechnology decisions and architecture design. Generates D3 decision gate, validates choices, produces modular or compact design documents with components, data model, API spec, integration, implementation, correctness, and NFR specifications.aidlc-requirementsTranslate business needs into user stories with EARS acceptance criteria. Generates decision gate, personas, and requirements. Includes routing recommendation for next phase.
agentcore-patternsVerified Amazon Bedrock AgentCore patterns for Runtime handlers, Gateway MCP clients with SigV4/IAM auth, Memory session management with Strands, and Bedrock cross-region inference-profile IAM policies. Use when building or debugging AgentCore-based agents.aws-technical-docsAWS technical documentation patterns covering procedures, lists, tables, titles, error messages, and content patterns. Use when writing AWS service documentation, procedures, troubleshooting guides, tutorials, or getting started content.cli-executionCLI execution best practices covering RTK token compression, AWS discover-then-execute patterns, output control, and bash/zsh scripting with logging. Use when running CLI commands, querying AWS resources, writing automation scripts, or working with shell…cloudwatch-dashboardsAWS CloudWatch dashboard observability patterns including dashboard hierarchy, widget selection, CDK implementation, metric math, alarms, and cross-account monitoring. Use when creating dashboards, setting up observability, or instrumenting workloads with…designStart a new plan interactively — clarify the problem, research, then write plan.md and tasks.md. Use when asked to design, scope, plan, or start a new plan or feature.diagnoseInvestigate and fix open issues in the .kiro/issues/ folder using test-first debugging. Use when asked to diagnose, triage, or work through unresolved bug reports, or when the user mentions open issues that need fixing.executeExecute the active plan's task groups in order, delegating to coder/ops/reviewer/docs subagents. Use when asked to execute, run, or build out the current plan or its tasks.flywheelAnalyze recent session transcripts for user-correction patterns and propose agent/steering/skill configuration improvements. Use when asked to run the flywheel, improve agent configuration, or learn from past sessions.
aws-vpc-dns-investigationUse this skill when a name is not resolving as expected inside a VPC, or before applying a DNS control-plane change. Activate on symptoms such as NXDOMAIN or SERVFAIL from an EC2 instance, a hostname resolving to a public address when a private endpoint was…storage-s3-resiliency-expertiseS3 resiliency, security, and data protection review. Assesses one or many S3 buckets across nine dimensions — versioning, replication, object lock, encryption, block public access, bucket policy, ownership controls, server access logging, and static website…database-rds-devopsDatabase-level data-plane diagnostics for Aurora MySQL and Aurora PostgreSQL. Executes predefined read-only health check queries via RDS Data API to analyze buffer pool, connections, locks, replication, storage, performance, and index efficiency. Requires the…investigation-cost-guardrailCost guardrail for AWS DevOps Agent that covers ALL AWS services and native agent tools. Before the agent makes any paid API call, this skill estimates cost, enforces budgets per investigation, detects expensive operations across all services (Athena queries,…msk-operationsAmazon MSK Provisioned operations, troubleshooting, and health assessment for Standard and Express brokers. Use whenever the user mentions Amazon MSK, MSK Provisioned, MSK Standard/Express brokers, Apache Kafka on AWS, `kafka.*` / `express.*` instance types,…database-migration-service-expertiseAWS Database Migration Service (DMS) operational review and troubleshooting skill. Conducts best practices validation, health assessments, performance diagnostics, cost optimization reviews, and migration cutover guidance. Triggers on requests like "DMS…wiz-security-contextAutomatically load this skill when investigating an operational anomaly on a cloud resource - CPU or memory spikes, latency, elevated error rates, unexpected network traffic, crashes, or cost spikes - to determine whether it is a purely operational issue or a…service-quota-checkUse this skill during any incident investigation, capacity planning, or operational troubleshooting when the issue may be caused by hitting AWS service limits. Activate when you observe throttling errors (ThrottlingException, TooManyRequestsException,…
inspection-cost-idleInterpret pre-computed low-utilisation and structural inspection findings for RDS, Aurora, and ElastiCache (Redis, Valkey, Memcached) as a cost-optimisation review. Use when a task description contains the marker NOTIOPS_INSPECTION together with hit_reason…inspection-high-loadInterpret pre-computed high-load and chronic-high inspection findings for RDS, Aurora, and ElastiCache (Redis, Valkey, Memcached). Use when a task description contains the marker NOTIOPS_INSPECTION together with hit_reason threshold_high or chronic_high. The…aws-health-eventsCheck AWS Health for service events, scheduled changes, and account notifications that may explain or correlate with an operational issue — filtered by service, time window, region, and status. Use when investigating service degradation, elevated error rates,…aws-well-architected-review-devopsConduct an automated AWS Well-Architected Framework review across all six pillars (Security, Reliability, Operational Excellence, Performance Efficiency, Cost Optimization, Sustainability). Use when the operator asks for an architecture review, security…cost-spike-triageTriage a sudden AWS cost increase or bill spike to find the root cause — which service, usage type, region, and (where available) which account or resource drove the change between two periods. Use when the user says their AWS bill went up, costs spiked,…eks-operation-reviewComprehensive best-practice review of an Amazon EKS cluster across reliability, security, cost, networking, and scalability — control-plane and node-group configuration, add-on and Kubernetes version currency, workload health (pods/deployments/events),…idle-resource-scanScan an AWS account for idle, unused, or oversized resources that are wasting money — stopped-but-still-billing EBS volumes, unattached Elastic IPs, idle EC2 instances, idle RDS databases, old snapshots, and low-utilization instances. Use when the user asks…rds-health-reviewReview the operational health and best-practice posture of Amazon RDS databases — Multi-AZ and backup configuration, storage headroom and autoscaling, instance right-sizing from CPU and connection metrics, recent failovers or maintenance events, and pending…
app-modernization-constructionCONSTRUCTION phase of the optional application-modernization module: apply the APPROVED application changes from the change plan — embedded SQL, datasource/ORM configuration, entity mappings, stored-routine call sites, error handling and result-set typing —…app-modernization-inceptionINCEPTION phase (assessment) of the optional application-modernization module: scan an application and classify every site impacted by a database migration — embedded SQL, datasource/ORM configuration, entity mappings, stored-routine call sites, error-code…app-modernization-operationsOPERATIONS & CUTOVER phase of the optional application-modernization module: plan how the converted application deploys together with the database cutover — artifact + configuration, ordering against the DB cutover runbook, rollback, and post-cutover checks.…app-modernization-orchestratorOPTIONAL module — entry point for modernizing APPLICATION CODE to match a completed database migration. Use ONLY when the user explicitly asks to migrate, convert or update an application (its embedded SQL, datasource config, ORM mappings, stored-routine call…app-modernization-validationVALIDATION & TESTING phase of the optional application-modernization module: compile the converted application, diagnose and fix the compile/test failures the database migration caused (result-set types, error codes, driver APIs, ORM mappings), run the test…oracle-to-mysql-playbookKnowledge base for converting Oracle to MySQL (Aurora MySQL compatible), distilled from the AWS Oracle-to-Aurora-MySQL Migration Playbook into granular per-topic references. Use when converting or assessing a specific Oracle construct for a MySQL target —…oracle-to-postgresql-playbookKnowledge base for converting Oracle to PostgreSQL (Aurora PostgreSQL compatible), distilled from the AWS Oracle-to-Aurora-PostgreSQL Migration Playbook into granular per-topic references. Use when converting or assessing a specific Oracle construct —…sqlserver-to-mysql-playbookKnowledge base for converting Microsoft SQL Server to MySQL (Aurora MySQL compatible), distilled from the AWS SQL-Server-to-Aurora-MySQL Migration Playbook into granular per-topic references. Use when converting or assessing a SQL Server construct for a MySQL…
backend-engineeringBuild a well-structured backend service for ANY task: an API, a tool server, a data endpoint, or an MCP server that exposes a module's capabilities over the wire. Use when implementing the server side of a build. Principles the agent applies to whatever it is…configure-claude-code-validatorConfigure a second Claude Code agent as the VALIDATOR in our AgentCore harness: it reads the task and the builders' work, authors a self-contained executable check, the engine runs that check, and its real exit code is the gate. Use when the user says "set up…configure-kiro-validatorConfigure the Kiro agent as the VALIDATOR in our AgentCore harness: Kiro reads the task and the builders' work, AUTHORS a self-contained executable check, the engine runs that check, and its real exit code is the gate. Use when the user says "set up Kiro",…configure-claude-code-backendConfigure the Claude Code agent as the BACKEND builder in the 3-agent AgentCore coding harness: the agent that implements whatever backend the task's contract names and exposes it through the AgentCore Gateway. Use this when the user says "set up Claude…extend-the-harnessDecision guide for adding a 4th+ role to OUR 3-agent AgentCore coding-agent harness (Claude Code = BACKEND / implements the backend deliverable, Kiro = VALIDATOR / authors the acceptance check whose exit code decides, opencode = FRONTEND BUILDER). Use when…vercel-deployShip the opencode-built chatbot UI (the FRONTEND BUILDER's artifact in our 3-agent harness) to Vercel and wire it to the AgentCore Gateway MCP endpoint. Use when the user says "deploy the frontend", "deploy to Vercel", "ship the chatbot UI", "publish the UI",…configure-opencode-frontendConfigure opencode as the frontend builder in the three-agent AgentCore harness. Use for deploying the opencode Runtime, staging AGENTS.md and .config/opencode/opencode.json, or verifying that the generated interface resolves its service address at runtime…harness-setupUmbrella entrypoint for standing up the 3-agent AgentCore coding-agent harness end to end. Use when the user says "set up the harness", "configure the agents", "first time setup", "deploy the coding agents", "bootstrap the harness", "get the agents running",…
research-biomedical-databasesUse when querying biomedical databases (UniProt, ClinVar, gnomAD, PDB, Reactome, Open Targets, etc.) via the Biomni AgentCore Gateway MCP server. Covers protein lookup, variant interpretation, pathway analysis, drug-target associations, and genomic annotation…clinical-protocol-draftingUse when drafting clinical trial protocol sections (objectives, background, study design) grounded in ICH guidelines (E6, E8, E9) and FDA regulations (21 CFR Part 312). Generates IRB-ready protocol documents from grant documents or study synopses.biomarker-database-analysisUse when a researcher needs to query biomedical databases for biomarker discovery, build target profiles from UniProt/Open Targets/STRING, rank biomarker candidates by evidence strength, or generate SQL queries against clinical genomic databases.biomarker-multi-agent-discoveryUse when orchestrating a multi-agent biomarker discovery workflow that requires coordinating database queries, pathway analysis, literature review, statistical modeling, and clinical evidence synthesis to produce ranked biomarker panels.biomarker-pathway-analysisUse when a researcher needs to analyze biological pathways for biomarker discovery, map disease mechanisms to druggable targets using Reactome/KEGG, identify pathway enrichment from gene sets, or understand mechanism-of-action for candidate biomarkers.genomics-variant-interpretationUse when interpreting genomic variants from VCF files, performing clinical variant classification using ClinVar/VEP annotations, analyzing allele frequencies against population data (1000 Genomes), or generating clinical reports for genetic counseling.hcls-build-agentUse when a developer wants to build a new healthcare or life sciences agent, structure tools and system prompts for an HCLS workflow, or create a Strands agent with domain-specific capabilities. Also use when someone asks about agent architecture, tool…hcls-deploy-agentUse when a developer wants to deploy an HCLS agent to Amazon Bedrock AgentCore, configure Gateway tools as MCP endpoints, set up authentication with Cognito, configure memory, or register an agent in the AgentCore Registry. Also use for deployment…
fact-check-loopIterative fact-checking loop for any document (PPT, Word, PDF, Markdown, etc.) against its original source. Spawns independent subagents in fresh contexts to eliminate confirmation bias. Each round checks all claims, the main agent fixes issues found, then a…finding-your-unknownsUse at the start of a non-trivial agentic coding task, or when a long-horizon task keeps coming back wrong. Surfaces the gaps between what you told the agent (the "map") and where the work actually happens (the "territory") — your unknowns — before, during,…animated-aws-archDraw an animated, light-theme, LEFT-TO-RIGHT AWS architecture diagram as one self-contained SVG — official AWS service icons, marching-ants connectors, and traveling request dots that show data moving through the system. Use this whenever the user asks for an…health-checkUse when performing routine environment checks, validating service health before or after deployments, checking SLO compliance, or generating a health status report. Also use when the user asks "环境健康么", "服务状态怎样", "部署前检查", or "SLO 达标了么". Queries CloudWatch…log-diagnosisUse when searching CloudWatch logs for errors, investigating application issues, correlating events across services, or when a user reports a problem and you need to find relevant log entries. Also use when the user asks "what errors happened recently",…hello-cliReference example agent-friendly CLI for managing todos. Demonstrates all 10 agent-friendly principles end-to-end. Use this as a structural template for your own CLI. Common workflows: list pending todos, create new todos, mark complete and archive (single…api-to-agent-cliUse when the user has a set of internal APIs / REST endpoints / SDK and wants to expose them as an agent-friendly CLI. Also use when retrofitting an existing CLI for AI agent use, or when auditing how agent-ready an existing CLI is. Prevents the common 1:1…aws-troubleshootingUniversal AWS troubleshooting framework. Activate when: any AWS resource is unhealthy, unreachable, or degraded; status checks fail; deployments fail; connectivity issues; performance degradation; unexpected errors or state transitions; the user says…