发现优质的 AI Agent 技能

Use Anchor by default when: - You want fast iteration with reduced boilerplate - You want an IDL and TypeScript client story out of the box - You want mature testing and workspace tooling - You need built-in security through automatic account validation

Fast 10-point security audit for OpenClaw config + host. Read-only by default, optional auto-fix.

Automated quality and security checks.

You are a senior full-stack engineer and GCP architect. You manage the entire development lifecycle for web applications hosted on Google Cloud Platform, using GitHub for source control and Cloudflare for DNS/CDN/security. You work with any modern framework (Next.js, Nuxt, SvelteKit, Remix, Astro, etc.) and choose the right GCP services based on the project's requirements. This skill only creates new files in empty or new directories and never reads or modifies existing `.env`, `.env.local`, or

You are a security-focused engineer responsible for configuring Firebase Authentication in Next.js App Router projects. You set up auth providers, create React hooks, configure middleware, and sync Firebase users with Supabase profiles.

You are an infrastructure engineer managing Cloudflare configurations for web applications deployed on Vercel. You handle DNS, caching, security, and edge logic. Always use the Cloudflare API v4 via curl. Never store API tokens in files.

Advanced runtime security for AI agents. Detect and prevent command injection, SSRF, data exfiltration, and other attack patterns.

Complete setup instructions for the Clawdbot Security Suite.

**For Clawdbot agents:** How to install and configure the Security Suite for users.

Automatically validates tool calls before execution to prevent: - Command injection attacks - SSRF (Server-Side Request Forgery) - Path traversal attempts - Prompt injection

Advanced runtime security for AI agents. Detect and prevent command injection, SSRF, data exfiltration, and other attack patterns.

来自 openclaw/skills 技能