查找技能

为Web应用正式上线准备Docker配置、自动化测试与部署流程，比较更新方式，规划运行检查和版本回退，并通过清单核查上线前的配置与运维准备。

• 自动化测试与部署
• 将应用打包为Docker容器
• 选择生产环境更新方式

协助编写和审查Kubernetes配置文件并排查故障，提供健康检查、权限控制、资源限制及自动伸缩的配置示例和调查命令，用于检查重启、内存不足和部署问题。

• 编写Kubernetes部署配置
• 审查健康检查与资源限制
• 排查容器反复重启的原因

Set up reproducible development environments with Flox on macOS and Linux. Define tools, package versions, setup steps, and local services in one configuration, then share it with teammates or add project-specific tools for AI agents.

中文简介正在准备中。当前显示英语简介。

• Sharing a consistent development setup across a team
• Combining language tools and system dependencies
• Running local PostgreSQL and Redis services

为Web应用上线整理部署流程与检查项，涵盖CI/CD测试和部署自动化、Docker容器化、健康检查及回滚计划，帮助选择发布方式并检查上线准备情况。

• 自动化测试与部署
• 将应用打包为Docker容器
• 选择生产环境发布方式

Check shell commands before they run and warn about destructive actions such as file deletion, database removal, and Git history changes. Users can approve ordinary warnings, while certain catastrophic command patterns are denied.

中文简介正在准备中。当前显示英语简介。

• Check destructive commands in production
• Review deletion commands in shared environments
• Catch Git operations that discard work

Review recent Claude Code session logs to find frequently used read-only Bash commands and MCP tools, which connect agents to services. Rank suitable permission rules and merge them into project settings to reduce repeated approval prompts.

中文简介正在准备中。当前显示英语简介。

• Reduce prompts for frequently used read-only tools
• Choose permission rules from actual usage
• Add project rules while preserving existing settings

Compare job requirements with your current skills and experience to identify learning priorities. Get a report with ranked gaps, study resources found through web searches, estimated learning time, and a recommended study sequence.

中文简介正在准备中。当前显示英语简介。

• Identify skill gaps across tracked jobs
• Build a learning plan for one job posting
• Choose study resources and a learning sequence

Consult bundled technical documentation to understand and integrate Hindsight, a memory system for AI agents. Find guidance on storing and retrieving memories, API calls, configuration, deployment, SDKs, troubleshooting, and performance.

中文简介正在准备中。当前显示英语简介。

• Learning how memory storage and retrieval work
• Checking API endpoints and request parameters
• Planning server setup and SDK integration

Follow guidance to create and operate Kubernetes clusters on Azure Kubernetes Service. Configure groups of worker machines, automatic scaling, networking, monitoring, identity integration, and upgrades, with command examples and Terraform configuration for repeatable setup.

中文简介正在准备中。当前显示英语简介。

• Create an AKS cluster on Azure
• Add GPU or spot node pools and configure automatic scaling
• Connect monitoring, Key Vault, and Azure Container Registry

Set up ArgoCD to keep Kubernetes deployments aligned with configuration stored in Git, an approach called GitOps. Follow guidance for multiple environments, automatic synchronization, deployment ordering, access permissions, and troubleshooting differences.

中文简介正在准备中。当前显示英语简介。

• Set up Kubernetes deployments driven by Git changes
• Manage staging and production configurations
• Configure synchronization order and pre-deployment jobs

Review system architecture and major design changes for scalability, resilience, and maintainability. Identify risks, compare design tradeoffs, and document recommendations and next steps across services, APIs, data storage, security, and deployment.

中文简介正在准备中。当前显示英语简介。

• Reviewing microservice boundaries
• Assessing a move to event-driven architecture
• Comparing serverless and container deployment

Design production alerts, route notifications by severity, and organize on-call schedules. Use configuration examples to define backup contacts, escalation steps when alerts go unanswered, and runbooks that guide responders through incident investigation.

中文简介正在准备中。当前显示英语简介。

• Define alert thresholds and severity levels
• Route notifications to Slack and PagerDuty
• Plan on-call rotations and holiday coverage

Plan security controls for LLM applications and AI agents, covering malicious instructions, data leakage, model tampering, and API access. Includes guidance and code examples for filtering outputs, enforcing permissions, isolating networks, and recording audit events.

中文简介正在准备中。当前显示英语简介。

• Reviewing defenses against prompt injection in AI agents
• Filtering personal information from LLM responses
• Designing authentication and rate limits for LLM APIs

Design scheduled AI workflows for document ingestion, batch processing, and model training using Prefect, Airflow, or Dagster. Compare orchestration tools and plan task dependencies, retries, caching, and monitoring through implementation fragments.

中文简介正在准备中。当前显示英语简介。

• Schedule document ingestion and RAG index refreshes
• Design batch workflows for LLM requests
• Connect model training with quality evaluation

Define security controls for AI coding agents used by a team. Covers command and file permissions, secret scanning, isolated execution environments, code review gates, and audit trails, with configuration examples to adapt.

中文简介正在准备中。当前显示英语简介。

• Set team rules before introducing AI coding agents
• Restrict access to credentials and infrastructure files
• Design an isolated environment for agent execution

Design traffic controls for AI inference services using Istio configuration examples. Covers mutual authentication, model version routing, gradual releases, retry limits, failure containment, and monitoring, with guidance for validating changes on the target cluster.

中文简介正在准备中。当前显示英语简介。

• Secure communication between inference services
• Gradually route requests to a new model version
• Review retries and failure containment for GPU services

Develop incident response procedures for LLM outages, declining answer quality, spending spikes, and unsafe outputs. Use example monitoring alerts, severity levels, recovery playbooks, and postmortem guidance to organize detection, response, and follow-up work.

中文简介正在准备中。当前显示英语简介。

• Plan fallback procedures for model provider outages
• Investigate declining answer quality after a deployment
• Prepare emergency controls for token spending spikes

Guide reviews of Linux Kernel patches for memory safety, Terraform plans for costly resource changes, and Kubernetes configurations for restricted permissions. A separately installed tool and configured AI model produce advisory findings and candidate manifests for validation.

中文简介正在准备中。当前显示英语简介。

• Review Linux Kernel patches for memory safety issues
• Check Terraform plans for potentially costly resource changes
• Draft Kubernetes permission settings from security requirements

Add monitoring to AI agents with response times, token usage, estimated costs, and error metrics. Trace records follow model and tool calls step by step, helping teams investigate failures and understand operating costs.

中文简介正在准备中。当前显示英语简介。

• Investigate slow agent responses
• Track token usage and estimated costs
• Trace failures in model and tool calls

Build repeatable evaluations for AI agent responses, tool choices, and multi-step tasks. Use reference datasets and scoring criteria to compare changes, detect quality regressions, and set automated checks that must pass before deployment.

中文简介正在准备中。当前显示英语简介。

• Compare agent quality before and after prompt changes
• Test tool selection and multi-step task execution
• Evaluate resistance to prompt injection

Prepare Apache Airflow provider releases by classifying pending changes, inspecting pull request diffs for compatibility risks, and applying version bumps and changelog entries. Use existing breeze tooling to regenerate release documentation and consult the release manager on uncertain decisions.

中文简介正在准备中。当前显示英语简介。

• Prepare documentation for a regular provider release cycle
• Classify changes for a selected set of providers
• Review breaking changes and choose version bumps

Adapt a resume to one specific job posting by mapping requirements to evidence from real experience. Identify gaps, revise emphasis and wording, check readability for applicant tracking systems, and optionally draft a cover letter.

中文简介正在准备中。当前显示英语简介。

• Tailoring a resume to a specific job posting
• Mapping job requirements to relevant experience
• Checking wording and readability for hiring systems

Analyze running containers in a CTF sandbox by comparing declared configuration with live processes, mounts, and routes. Trace how secrets and helper containers affect behavior, then document the earliest mismatch and a minimal evidence chain.

中文简介正在准备中。当前显示英语简介。

• Comparing container manifests with live runtime behavior
• Identifying which process consumes a mounted secret
• Tracing changes made by sidecars or init containers

Investigate Kubernetes permissions and cluster behavior in CTF sandboxes. Trace role-based access control, service accounts, and automated controllers to explain workload changes, secret exposure, and differences between configuration files and live objects.

中文简介正在准备中。当前显示英语简介。

• Checking service account API permissions
• Tracing secret exposure through workload changes
• Comparing YAML manifests with live cluster objects