查找技能

执行并监控OpenClaw发布候选版本的CI，验证实际服务提供商连接及安装、更新流程，调查失败原因并进行定向重试，整理验证结果和发布决策所需证据。

• 验证OpenClaw发布候选版本
• 调查失败的CI任务并定向重跑
• 确认服务认证及实际推理能力

核对OpenClaw常规版与extended-stable版的发布位置、分发产物来源、测试证据和Gateway实际运行情况，判断版本是否已完整发布并可运行。

• 确认stable版是否完整发布
• 检查插件是否遗漏分发
• 核查extended-stable版证据

在发布前验证OpenClaw插件的安装、卸载、配置修复、启动、SDK兼容性及分发包行为，记录测试结果、失败情况与尚未验证的项目。

• 发布前检查内置插件的安装与卸载
• 在干净环境中验证测试版
• 检查配置修复与gateway启动

根据OpenClaw的变更选择测试和检查，调查失败原因，涵盖本地验证、依赖特定环境的检查，以及转交相应流程的发布验证。

• 为源代码变更选择验证方式
• 复现缺陷并验证修复
• 调查CI失败原因

通过日志和复现操作排查OpenClaw的模型通信、工具执行及响应流问题，并检查已保存的对话和附件，为修复原因与再次验证收集证据。

• 排查本地测试与真实服务的行为差异
• 确认模型实际可见的工具
• 调查响应流的延迟或中断

使用模拟环境或真实服务运行OpenClaw质量验证场景，调查并修复失败原因、检查结果报告，还可比较多个模型的表达方式和角色表现。

• 在模拟环境或真实服务中运行质量验证
• 调查失败场景并重新验证
• 比较多个模型的角色表现

调查OpenClaw CI的排队和运行环境不足问题，根据测量结果调整运行器注册预算、并行数量、测试分组、运行器规格及任务分配位置。

• 调查OpenClaw CI排队原因
• 估算高峰期运行器注册数量
• 调整并行数量和测试拆分

持续开展OpenClaw整体质量验证，从复现缺陷、修复根因到独立审查和确认合并，将真实环境及压力测试的证据和进度记录在可续接的报告中。

• 调查OpenClaw多个领域的缺陷
• 通过回归测试和独立审查验证修复
• 验证实际连接、界面及分发包

用于编写和修改OpenClaw在Docker中的端到端测试，结合模拟服务器与真实服务，核查实际发送的请求、图像理解结果及用户最终看到的聊天回复。

• 添加或修改Docker端到端测试
• 核查发往依赖服务的请求内容
• 验证真实模型服务的行为

Review MCP configuration without running its servers. Identify npm, Python, and Docker references that may fetch different code later, classify their version settings, and recommend pinning versions or image contents that the team has reviewed.

中文简介正在准备中。当前显示英语简介。

• Reviewing MCP configuration before approval
• Checking latest tags and version ranges
• Adding a deterministic configuration check to CI

Prepare web applications for production with Docker configurations, automated testing and deployment workflows, health checks, and rollback plans. Compare release strategies and review application, infrastructure, monitoring, security, and operational readiness before launch.

中文简介正在准备中。当前显示英语简介。

• Set up automated testing and deployment
• Package a web application with Docker
• Choose a production release strategy

Deploy and manage services across an Uncloud cluster using the uc command line. Covers public ports, Caddy routing for incoming traffic, service scaling, log inspection, and management of machines and storage volumes.

中文简介正在准备中。当前显示英语简介。

• Deploying services from Compose files
• Publishing a web application over HTTPS
• Routing traffic to a NAS or router interface

Configure and troubleshoot Vite projects, covering environment variables, API proxies, plugins, and production builds. The skill also guides library packaging, dependency compatibility, and development server performance, with checks for exposed secrets and missing TypeScript validation.

中文简介正在准备中。当前显示英语简介。

• Configuring environment variables and development API proxies
• Investigating slow development servers and update failures
• Optimizing production bundles and checking builds

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

Set up Pi-hole on a home network to block advertising and malware domains. Manage blocklists, encrypt DNS lookups that turn names into addresses, configure device address assignment, add local service names, and investigate connection problems.

中文简介正在准备中。当前显示英语简介。

• Install Pi-hole for home network domain blocking
• Manage blocklists and fix unwanted blocking
• Encrypt upstream DNS queries with DNS-over-HTTPS

Helps prepare web applications for production with automated testing and deployment workflows, Docker packaging, health checks, and rollback plans. Provides examples and checklists for choosing release strategies and reviewing readiness before launch.

中文简介正在准备中。当前显示英语简介。

• Setting up automated testing and deployment
• Packaging an application with Docker
• Choosing a production release strategy

Create and review Docker development environments, including service networking, persistent storage, and security settings. Also guides isolated testing of command-line installers on Linux, while identifying checks that require native macOS or Windows environments.

中文简介正在准备中。当前显示英语简介。

• Set up a local app, database, and Redis stack
• Review container networking and persistent storage
• Harden Dockerfile and Compose security settings

Set up vLLM to serve large language models through an OpenAI-compatible API or process prompts in batches. The skill covers deployment, performance monitoring, and quantization, which reduces model memory requirements.

中文简介正在准备中。当前显示英语简介。

• Deploying an OpenAI-compatible language model API
• Generating text from large batches of prompts
• Serving large models with limited GPU memory

Set up and optimize large language model inference, or response generation, on NVIDIA GPUs. Use quantization, batch processing, and multiple GPUs to improve serving performance, and expose models through a chat completion API.

中文简介正在准备中。当前显示英语简介。

• Serving a language model through a chat completion API
• Processing many prompts in batches
• Configuring quantization to reduce memory use

Track updates across blogs and RSS/Atom feeds, then manage unread articles in one place. Automatically discover feeds, import subscription lists, and filter articles by blog or category using blogwatcher-cli.

中文简介正在准备中。当前显示英语简介。

• Check new posts across multiple blogs
• Import an existing feed subscription list
• Track read and unread articles

Search more than 400 social networks and platforms for accounts using a given username. Receive organized links to matching pages for checking username availability or researching publicly available account information.

中文简介正在准备中。当前显示英语简介。

• Find accounts using a specific username
• Check username availability across platforms
• Gather public account links for authorized research

Search across multiple engines through SearXNG, a service that combines search results. Filter by category, date range, or engine, and get titles, links, and snippets. Public instances require no API key.

中文简介正在准备中。当前显示英语简介。

• Search multiple engines for research sources
• Find recent news within a chosen date range
• Use an alternative when the main search tool is unavailable

Build similarity search with Qdrant, a database for numerical representations of content. Store and retrieve vectors, filter results by metadata, connect retrieval to AI answers, and configure memory usage and deployment for larger workloads.

中文简介正在准备中。当前显示英语简介。

• Retrieving reference documents for AI answers
• Filtering similarity search by category or date
• Building real-time recommendations

Modify and troubleshoot services managed by s6, a process supervisor, inside the Hermes Docker image. Trace startup scripts, inspect profile gateways, add static services, and investigate restart failures or file ownership problems.

中文简介正在准备中。当前显示英语简介。

• Add a static service to the Hermes Docker image
• Investigate profile gateways that fail to start
• Debug gateway recovery after a container restart