SkillsBaseAgent Skill Exchange

高风险需谨慎 Skill

集中展示带有高权限、凭证、脚本或安全提醒信号的 Skill,安装前请先核对仓库与命令。

查看排行榜

data structure protocol

GitHub 已审核来源

Graph-based long-term memory skill for AI (LLM) coding agents — faster context, fewer tokens, safer refactors

Claude Code 可用高风险提示近期维护
#universal#agent-skills#calude#claude-code
53 +140
数据与分析

dembrandt skills

GitHub 已审核来源

UX and design system skills for AI agents based on 20 years of experience

Claude Code 可用高风险提示近期维护
#universal#accessibility#agent-skills#claude-code-skills
16 +240
设计与前端
GitHub 已审核来源

Claude Code skill for secure environment variable management with Varlock. Never expose secrets in Claude sessions.

Claude Code 可用高风险提示近期维护
#claude#claude-code#claude-code-skills#claude-skills
250
安全与审计

resend skills

GitHub 已审核来源

Agent Skills for working with Resend to send and receive emails.

Claude Code 可用高风险提示近期维护
#universal
133 +1190
办公与文档

anydesign

GitHub 已审核来源

Claude skill that analyzes images, websites, and Figma files and generates a structured design.md with token system, component inventory, and reconstruction notes.

Claude Code 可用高风险提示近期维护
#claude#ai-agents#anthropic#claude-code
110 +760
多媒体处理

claude security skills

GitHub 已审核来源

Production-ready Claude Code skills for cybersecurity — secret scanning, SAST, prompt-injection testing, HTTP/JWT/dependency auditing. Zero dependencies.

Claude Code 可用高风险提示近期维护
#claude#ai-security#anthropic#appsec
850
安全与审计

SocratiCode

GitHub 已审核来源

Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.

Claude Code 可用高风险提示近期维护
#universal#mcp#ai#ai-assistant
2961 +683860
数据与分析

Unity MCP

GitHub 已审核来源

AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.

Claude Code 可用高风险提示近期维护
#claude#cursor#gemini#copilot
3182 +602920
设计与前端

caveman

GitHub 已审核来源

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Claude Code 可用高风险提示近期维护
#claude#ai#anthropic#caveman
73587 +212141520
Agent 搭建

html anything

GitHub 已审核来源

✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.

Claude Code 可用高风险提示近期维护
#claude#codex#cursor#gemini
6885 +2806780
内容创作

memU

GitHub 已审核来源

The memory harness for proactive AI agents — structured storage, intent capture, 10x token reduction.

Claude Code 可用高风险提示近期维护
#universal#agent-memory#agentic-workflow#claude
13878 +4710370
Agent 搭建

oh my openagent

GitHub 已审核来源

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

Claude Code 可用高风险提示近期维护
#codex#ai#ai-agents#anthropic
62475 +55250580
Agent 搭建

Venice Skills

GitHub 已审核来源

Agent skills for the Venice API covering chat, responses, embeddings, image generation, audio, video, billing, API keys, and crypto RPC surfaces.

Claude Code 可用高风险提示近期维护
#claude#codex#venice#api
90 -2130
AI Platform

prompt master

GitHub 已审核来源

A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention

Claude Code 可用高风险提示近期维护
#claude#claude-ai#claude-skills#llm
9425 +31211110
Agent 搭建