A curated directory of third-party Agent Skills, organized by use case, platform and safety rating. Before installation, review package permissions, dependencies and runtime risks.
Found 16 Agent Skills
An integration between OpenClaw Gateway and Unreal Editor for developers with UE5 and the required plugin. It is not just advisory: documentation includes actor creation and deletion, property edits, level saving and console execution. The package does not contain the complete UE plugin and does not establish cross-host readiness.
PostgreSQL's native job queue implements priority scheduling and progress tracking with zero dependency, and is suitable for technical teams that already have PG infrastructure and pursue architectural simplification.
K8s configuration skills maintained by openclaw provide production-grade YAML templates and built-in security hardening strategies to help build safe and reliable cloud-native deployment solutions.
Senior DevOps expert's Terraform practice guide provides AWS/Azure/GCP multi-cloud modular development and remote status management to ensure the security and reusability of infrastructure code.
The enterprise-level AnalyticDB management tool based on Alibaba Cloud's official OpenAPI supports resource inventory, configuration changes and fault diagnosis, and realizes automated operation and maintenance and standardized management of cloud data warehouses.
An infrastructure-as-code automation tool based on Ansible supports server configuration management, security hardening and OpenClaw deployment, and follows DevOps best practices.
A CI/CD automated management tool based on the official Jenkins API, which implements build triggering and status monitoring through the standard REST interface, helping the development team to operate and maintain the pipeline efficiently.
The local vector memory storage solution based on LanceDB supports semantic search and long-term memory management. The data is completely localized and is suitable for building personal knowledge base and conversation history system.
The proxy host, SSL certificate and access control of Nginx Proxy Manager are managed through REST API, which is suitable for operation and maintenance personnel to quickly configure reverse proxy and automated domain name management.
The database operation tool based on Supabase's official technology stack supports SQL query, CRUD and vector search, providing enterprise-level data storage and retrieval capabilities for AI applications.
Java library release guide based on Central Portal provides standardized Maven configuration and simplifies GPG signing and deployment.
A complete guide to community-level Homebrew commands, providing a complete reference for macOS package management from search and installation to troubleshooting, helping developers efficiently manage software dependencies and development environments.
An official Vercel React and Next.js performance ruleset covering request waterfalls, bundle size, server and client performance, and re-renders. Use it to produce located recommendations before code review or refactoring, not as direct guidance for Laravel Blade or every frontend framework. This listing checks version 1.0.0 at commit 063bee9. The skill consists mainly of Markdown rules and examples, with no executable scripts of its own; that does not establish correctness or security certification for generated edits.
Vercel's interface-guideline review skill checks specified page source for accessibility, form labels, keyboard focus, images, animation and interaction issues, returning files and line numbers. The skill is documentation, but defaults to fetching the latest remote main-branch rules on every review. Pinning the installation does not pin those rules. Use it for read-only source review first, not as a replacement for browser or assistive-technology testing.
An official Anthropic web-testing skill that guides an agent to use Python Playwright for local page checks, element discovery, screenshots and browser logs. Its with_server.py helper can start development servers, wait for ports, run tests and stop the processes it starts. It has real command and browser-action capabilities, so use an isolated test project rather than production accounts. This site performed only a static review of the pinned commit, not installation, server execution or end-to-end tests.
An official Anthropic frontend-design guidance skill for new pages, landing pages and interface redesigns. It helps an agent organize real content, typography, color and layout into an intentional interface, complementing performance and guideline-review skills in this directory. The pinned target folder contains only SKILL.md and LICENSE.txt, with no executable scripts. Our review was static, not an installation test; generated pages are not automatically accessible or brand-compliant.