Explorar skills

Compartilhe um arquivo markdown via um link privado do GitHub Gist, com opções de exclusão automática após um TTL personalizado, criptografia de ponta a ponta, pré-visualização ou exclusão única após leitura via transfer.sh. Esta skill permite enviar ou compartilhar arquivos markdown ou documentos por meio de uma URL.

Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltrati

Docker guidance for fast-moving teams. Starts with "do you need a Dockerfile?" (often no - use mounted code pattern). When Dockerfiles are needed, provides 2025 best practices for multi-stage builds, security hardening, BuildKit optimization, and language-specific patterns. Use when setting up Docker for a project, auditing Dockerfiles, or optimizing builds/images.

A test skill for validating the packager

Use when scanning GitHub Trending, GitHub Explore, or hot repositories to identify useful tools, product opportunities, skill/workflow ideas, and hype traps for builders.

End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. 会话结束后对项目文档和记忆进行洁癖级审查与同步。MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "同步一下", "整理文档", "整理一下", "更新记忆", "梳理一下", "收尾", "这个阶段做完了", "新人能直接上手", or any phrase suggesting a dev mile

Route broad or ambiguous AgentKit SEO work to the right module while keeping context scoped. Use when a request spans multiple surfaces, asks for overall digital-presence strategy, involves provider or install architecture, needs agent-context planning, or the correct platform skill is unclear.

MUNDO - THE EMPEROR. Complete AI orchestration system that dispatches Claude Code, DeepSeek, ChatGPT, Gemini and ALL available AI models through Hermes Agent platform. Consults ALL AIs, crawls ALL web, integrates ALL solutions, saves ALL useful skills. Self-evolving. 21 versions. 24 capability modules. Collective consciousness. Infinite growth. Uses Three Departments and Six Ministries system to r

Git repository hygiene check. Stale branches, large files, commit conventions. Use when: "git cleanup", "git hygiene", "clean up branches", "git-hygiene", "stale branches", "git cleanup".

End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. 会话结束后对项目文档和记忆进行洁癖级审查与同步。MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "同步一下", "整理文档", "整理一下", "更新记忆", "梳理一下", "收尾", "这个阶段做完了", "新人能直接上手", or any phrase suggesting a dev mile

Scaffold a pnpm + Turborepo MERN monorepo with Next.js, tooling, tests, CI, and optional GitHub repo creation.

Breaks a plan, spec, or PRD into independently-grabbable GitHub issues using vertical slices (tracer bullets), publishes them in dependency order, and saves a local index in docs/ai. Activates when the user writes "issues", "break into issues", "create tickets", "split into tasks", "decompose into issues", "make implementation tickets", "tracer bullets".