26 skills found
assafelovic / gpt-researcherAn autonomous agent that conducts deep research on any data using any LLM providers
eugene1g / agent-safehouseSandbox your local AI agents so they can read/write only what they need
poco-ai / poco-clawA more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, and a sandboxed runtime for improved safety. Under the hood, it is powered by a Claude Code–based agent.
kenryu42 / claude-code-safety-netA coding agent hook that acts as a safety net, catching destructive git and filesystem commands before they execute.
MoizIbnYousaf / Ai-Agent-Skillsmy curated agent skills library
vinkius-labs / vurb.tsVurb.ts - The TypeScript Framework for MCP Servers. Type-safe tools, structured AI perception, and built-in security. Deploy once — every AI assistant connects instantly.
harrymunro / nelsonThe gap between "spawn agents" and "safely coordinate a squadron" is vast. Nelson is a Claude Code skill that bridges it with structured planning, risk-tiered quality gates, recovery procedures, and auditable decision logs.
ssut / Remote-MCPA type-safe solution to remote MCP communication, enabling effortless integration for centralized management of Model Context.
smart-mcp-proxy / mcpproxy-goSupercharge AI Agents, Safely
ktr0731 / go-mcpdeprecated: use the official MCP sdk! (https://github.com/modelcontextprotocol/go-sdk) / ⚡ A type-safe, intuitive Go SDK for building MCP servers with ease and confidence
ergut / mcp-bigquery-serverA Model Context Protocol (MCP) server that provides secure, read-only access to BigQuery datasets. Enables Large Language Models (LLMs) to safely query and analyze data through a standardized interface.
blueraai / clauder> CLAUDER - a safer and supercharged Claude Code
syrin-labs / cliRuntime intelligence system that makes MCP servers debuggable, testable, and safe to run in production.
Robotti-io / copilot-security-instructions✨ A customizable copilot-instructions.md ruleset & prompts to guide GitHub Copilot toward secure coding defaults in Java, Node.js, C# and Python. Blocks risky patterns, teaches safe habits.
framix-team / skill-email-html-mjmlClaude Code skill — generate cross-client HTML email with MJML. Outlook-safe, Gmail-optimized, WCAG 2.1 AA accessible.
SDLLL / claude-for-safariGive your AI Agent the power to control Safari on macOS. No extensions, no separate browser.
SpillwaveSolutions / mastering-typescript-skillClaude Code skill for enterprise-grade TypeScript development with type-safe patterns, modern tooling, and framework integration (React, NestJS)
jzOcb / upgrade-guardSafe OpenClaw upgrades with snapshot, pre-flight checks, controlled upgrade, post-verification, and emergency rollback. Never lose a working system to a bad update.
bryant24hao / macos-calendar-assistant-skillOpenClaw-native macOS calendar skill for IM-first schedule management (planning, execution, review, and safe dedup cleanup).
teehooai / spidershieldScan, rate, and harden MCP servers for AI agent safety
achiya-automation / safari-mcpNative Safari browser automation for AI agents. 80 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chrome DevTools MCP with 40-60% less CPU/heat on Apple Silicon.
0xshariq / github-mcp-serverA Model Context Protocol (MCP) server that provides 29 Git operations + 11 workflow combinations for AI assistants and developers. This server exposes comprehensive Git repository management through a standardized interface, enabling AI models and developers to safely manage complex version control workflows.
TeamSafeAI / LIFELIFE — Persistent identity architecture for AI agents. 16 MCP servers: drives, heart, memory, patterns, journal, genesis, garden, vision, voice, and more. Zero dependencies. Built across 938 conversations.
agentfront / enclaveA secure JavaScript sandbox designed for safe AI agent code execution. Protects against code injection, prototype pollution, and sandbox escapes. The security layer that makes AI-generated code safe to run.
volleio / claude-permissions-auditAudit and optimize Claude Code permissions — flags overly permissive patterns, deprecated syntax, credential exposure, and missing safety rules. Includes discover mode for new CLI tools and usage logging.
maslennikov-ig / push🎼 Turn Claude Code into a production powerhouse. 33+ AI agents automate bug fixing, security scanning, and dependency management. 19 slash commands, 6 MCP configs (600-5000 tokens), quality gates, and health monitoring. Ship faster, ship safer, ship smarter.
