Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating/porting/converting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching, quota health checks and throttling diagnosis, cost attribution, migrating between Claude model generations, chunking strategies, API selection (Converse vs InvokeModel), and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Coinbase CDP, Stripe Privy, 402 Payment Required, paid endpoint). NOT for custom model training, Rekognition, or Comprehend.

Deploys and operates containerized workloads on ECS, Fargate, and ECR. Covers task definitions, Fargate services, ECR repository setup and lifecycle policies, ECS Exec debugging, service scaling, deployment strategies, load balancer integration, and logging configuration. Use when deploying, debugging, or optimizing containers on AWS. ALSO USE for container deployment options (ECS vs ECS Express Mode), networking modes, health check troubleshooting, OOM errors, secrets injection, blue/green deployments, ECR image management, and App Runner sunset guidance and migration. NOT for Kubernetes, EKS, or CI/CD pipelines.

Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating/porting/converting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching, quota health checks and throttling diagnosis, cost attribution, migrating between Claude model generations, chunking strategies, API selection (Converse vs InvokeModel), and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Coinbase CDP, Stripe Privy, 402 Payment Required, paid endpoint). NOT for custom model training, Rekognition, or Comprehend.

Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal. Triggers: "add memory", "remember across sessions", "call agent from app", "invoke agent from code", "agent auth", "streaming", "VPC", "VPC connectivity", "can't reach from VPC", "multi-agent", "A2A", "A2A auth", "orchestrator not delegating", "specialist not called", "migrate Bedrock Agent", "migration issue", "change model", "browser tool", "code interpreter", "delete agent", "tear down", "agentcore remove", "cross-account memory", "add payments capability to my agent", "wire payments plugin", "payments middleware for my agent", "integrate x402 payments with the agent I'm building", "enable my agent project with x402 payments". External APIs via Gateway: use agents-connect. New project: use agents-get-started. CLI/dev-server errors: use agents-debug. Runtime x402 payments: use agents-pay. Migration-specific Strands vs LangGraph routes here.

Dealing with delayed DOM generation, lazy loading, and optimistic state synchronization in vanilla JavaScript without a reactive framework.

Project N.E.K.O. 胶囊化 UI、品牌蓝视觉系统规范

**重要提醒**: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。

Use to list Liferay worktrees with their assigned ports, running status, offset, and database, or to print the port and database summary for a single worktree.

Generate a targeted local test plan for branch changes. Use when the user wants to know which tests to run before merging, asks for a test plan, wants to validate changes locally, or mentions running tests for their branch. This skill analyzes commits on top of master and produces a runnable shell script covering Unit, Integration, Playwright, and Poshi tests within a 20-minute local budget.

Resolve a single Liferay test failure end-to-end.

Create a GitHub PR for the current branch. Use when the user asks to create a PR, send a PR, or invokes /pr.

Comment a pr-check run on an existing GitHub PR with a marker the webhook parses to apply the commit status and label. Use after rerunning pr-check on an open PR.

Format a Markdown file to match Liferay conventions — frontmatter order, Title Case headings, braced shell variables, long-form CLI flags, and professional prose. Use when the user asks to format, clean up, polish, or copy-edit a Markdown file destined for the Liferay repository.

Handle rsyslog post-.0 v8-stable updates, including patch-release ChangeLog sections, PRs targeting v8-stable, preserving stable merge commit hashes, and merging v8-stable back into main cleanly.

Standardizes testing and validation for rsyslog using the diag.sh framework.

Monitor rsyslog pull requests after push or rerun, including GitHub Actions checks, unresolved review threads, bot comments, reruns for known flakes, and concise status reporting.

Encodes technical requirements for rsyslog modules, including concurrency, metadata, and initialization.

Mirror rsyslog run_checks.yml container validation locally, including the change-gated Ubuntu 26.04 run-ci.sh check run, the clang static analyzer job, late prompt-based audit passes, Cubic review where applicable, service-skip validation, clean-tree rules, and container path caveats.

Triage rsyslog GitHub issues one issue or cluster at a time, classify stale and current reports, draft or post closure comments, and maintain a local evidence board.

Guidelines for maintaining structured, RAG-optimized documentation and module metadata.