Explore
MCP servers and skills: search, filter by where they run, and compare.
r3ckon-stylelocalhostd3veloper
LocalSix Claude Code skills that make an agent write code and prose the way I do.
SkillMIT★ 1Few starsNo key
MCP servers and skills: search, filter by where they run, and compare.
Six Claude Code skills that make an agent write code and prose the way I do.
SkillMIT★ 1Few starsNo key
将秒哒（MIAODA）导出项目迁移为可独立本地运行、构建和部署的 Codex Skill，支持清理百度与秒哒平台耦合、localhost 验证及 Cloudflare Pages 部署准备。
SkillMIT★ 3Few starsNo key
Publishes localhost services to the agentic web through self-hostable, trustless relays.
SkillMIT★ 288No key
Screenshot Time Machine is like a Wayback Machine for your own website, a visual archive of every page over time. One command screenshots every page into dated folders on your machine, and shows which
SkillMIT★ 4Few starsNo key
A verification layer for AI coding agents. 250+ real-protocol service emulators (Stripe, Postgres, Slack, S3, OpenAI…) on local Docker.
SkillMIT★ 8No key
Context-aware marketing skills for Claude Code, with B2B, industrial, regulated, and consumer playbooks.
SkillMITFew starsNo key
The open source orchestration & observability your ai agent workflows (hermes, openclaw, claude-code, codex, pi, gpt, opus, fable, kimi, etc.)
SkillMIT★ 2Few starsNo key
Proof-of-concept demonstrating invisible Unicode prompt injection in AI agent skill files. This project shows how the Unicode Tags block (U+E0000–U+E007F), zero-width characters, and bidirectional ove
SkillMIT★ 2Few starsNo key
OpenClaw Real-time security monitoring dashboard for the OpenClaw applicaiton and Linux server infrastructure
SkillMIT★ 5No key
SkillMIT★ 2Few starsNo key
On-demand local dev-server proxy: every project gets a permanent .localhost URL that wakes its dev server on request and sleeps it when idle.
SkillMIT★ 3Few starsNo key
Permanent local URLs on your Cloudflare domain—one browser sign-in, one command per project.
SkillMIT★ 3Few starsNo key
Local-only web GUI for inspecting agent skills (SKILL.md) across user, project, plugin, cache, and marketplace sources
SkillMIT★ 74No key
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
SkillMIT★ 248No key
Defensive security audit tool for AI Agent and MCP (Model Context Protocol) environments. Detects risky localhost exposure, weak bindings, and confused-deputy risks. Lightweight, SARIF + HTML reports,
SkillMIT★ 1Few starsNo key
A UI around your Claude Code and Codex terminals that your agents build, so the only model in your head is yours.
SkillMIT★ 9No key
opencode-artes: 115 production-grade OpenCode skills for fullstack web development, localhost security auditing and AI agent automation. Frontend, backend, devops, testing and AI-ops skill ecosystem i
SkillMIT★ 2Few starsNo key
SkillMIT★ 5No key
Agent skills for Codex, Claude, Cursor, and other AI coding agents.
SkillMIT★ 5No key
A beginner foundation skill for AI coding agents — from product idea, data and Git to security, deployment and launch.
SkillMIT★ 100No key
把 App Store 评价变成产品研究证据，发现痛点、机会和版本风险 | Turn App Store reviews into product research evidence: pain points, opportunities, and version risks.
SkillMIT★ 226No key
Codex TeamViz: dynamic Codex team mode with a localhost workgroup dashboard.
SkillMIT★ 3Few starsNo key
让 Codex 和 Claude Code 自动为远程生成的 HTML、静态站点和浏览器文件返回可点击预览链接。
SkillMIT★ 1Few starsNo key
Who stands behind it
