Claude Code skill: visual understanding & image generation with multi-channel fallback
// trending (4120)
🎭 cc-best: Turn Claude Code into a full dev team — PM→Lead→Dev→QA autonomous workflow. 44 commands · 19 skills · 8 agents · 43 rules · 30 hooks · auto-learn…
ClaudeDesktopPlusPlus — a Claude ecosystem project on GitHub.
Claude Code skill: showreel-grade brand motion videos (launch, promo, teaser...) in code with HyperFrames + Three.js
Cache-, quota- and capability-aware LLM router with a Claude Code shim
用 Claude Opus 5.5 写代码做视频:先给三个方案和预览,确认后逐帧渲染成片 | Canvas / WebGL / Three.js / Remotion / HyperFrames | Claude Code Skill
Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flags when the agent'…
Local-first MCP security scanner for AI-generated apps. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.
Free, copy-paste Claude skills that run your content growth factory — turn ideas + your NotebookLM memory into scroll-stopping Instagram reels. By Ootto.
One command to cut token usage by up to 50%+
Runs, benchmarks and optimizes your agent-written Python code until it's production-ready. Zero-edit runtime tracing joins every call to source, builds one c…
Local-first analytics dashboard for AI coding sessions. See what you built with Claude Code & Codex CLI.
AI-powered multi-model workspace and routing system for Claude, Codex and other LLM agents. Provides intelligent prompt routing, agent orchestration, evaluat…
專為 Claude Code 與 OpenAI Codex 打造的 AI 協作工具組,讓 AI 更可靠、更好協作:動手前先對齊理解、跨 AI 無縫接手工作,持續擴充中。
Caveman mode skill for Claude. Fewer output tokens, longer usage before hitting limits.
A wall screen for Claude Code and Codex sessions and your GitHub builds
一张 IP 正面照 → 整套可提交的微信表情素材:出图、切图、机检、文案校验、提交清单全脚本化(Claude Code skill)
Games above the Claude Code prompt: snake, Tetris, 2048, Minesweeper, Flappy, Pong, a typing test and Space Invaders, plus a pet that grows as Claude tests,…
A Claude skill that builds PPTX decks matching your real designer decks: extracted design DNA, measured word budget, render-QA loop.
CodeAuditSkill 是一个运行在 Claude Code 中的 Web 项目安全代码审计/漏洞挖掘 Skill, 已经获得了40余个CNVD漏洞编号。 给定一个 Web 项目目录,自动识别语言与框架,按语言专属漏洞清单进行系统化源码审计,对每条高中危漏洞并行启动子 Agent 进行可利用性验证,最终输出…
High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.
Claude Skill that audits your projects for RLS misconfigurations, exposed keys, auth bypasses, and storage vulnerabilities. 27 anti-patterns sourced from CVE…
Scrape JavaScript-heavy sites and extract structured data via reusable CSS schemas. Portable agent skill wrapping the Crawl4AI CLI and Python SDK.
Procedural writing-style skills for AI agents: official frameworks (plain language, business writing, GOV.UK, AP style, STE-100, developer docs) + character…
GitHub Action that runs trustabl — static reliability/safety analyzer for AI agent SDKs (Claude, OpenAI, Google ADK, MCP). Gates CI on risk + severity.
Claude Opus 5.5 directs and renders films in JavaScript: brief → sound (file, YouTube, generated, or AI voiceover) → director's treatment → frame-exact MP4.…
Remote hands for coding agents: an MCP server that runs OpenCode / Claude Code / Codex work on a remote host over SSH, keeps credentials and the local machin…
Run different Claude Code providers in different terminals. 支持同时在不同终端窗口用不同 API Key 跑 Claude Code,互不影响
先议后行——AI 协作变更任务的议行分离机制 skill(Claude Code / DeepSeek Harness / ZCode 通用)