Trending Repos

Fuse two frontier models into one Fable-tier answer: Opus 4.8 drafts, a second model (Opus 4.8 or GPT-5.5 via codex) checks, Opus fuses. A Claude Code skill.

🪸 Powerlevel10k-inspired statusline for Claude Code — paste one prompt and your AI interviews you, then installs it

A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.

Control Room-first template for managing Hermes agents from one VPS agent to specialist teams and orchestrated workflows

By a 12-year product manager who builds 0-to-1: takes a beginner from a vague idea to a buildable plan, then guides the build (GitHub basics, clean-code habits, a verify-and-iterate loop, a checkup for the mess). For Claude Code, Codex, and Antigravity. grill-me is for engineers, vibe-check is for everyone else.

Use agent to learn agent - A skeleton course on how to design, build, and operate production AI agents

Measuring frontier coding agents on original, long-horizon engineering tasks

Brand building skills for Claude Code and AI agents. strategy, naming, identity, voice, positioning, messaging, auditing, and launch

Offensive security toolkit for Claude Code covering red team, exploit dev, AD attacks, EDR bypass, mobile pentest

Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.

Run many Claude Code sessions across your projects, each in its own tmux session — then list them, see which are done vs. still working, and jump to one from a single popup.

A Claude Code + Codex skill that turns a local project into a macOS Dock-launchable app — native window, its own icon, no Electron. [The Windows version is in BETA]

A Claude Code skill that performs in-depth security scans and detects 20+ of the most common security vulnerabilities in your source code.

Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, 13 supported tools.

Reusable Skills for LLMQuant Agent, Claude Code, Claude.ai, Cursor, Hermes Agent, OpenClaw and Codex, grounded in LLMQuant Data

Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideate, deep-dive, prompt-pack) and an autonomous tier (autopilot, build-loop).

The key that opens Opprime World — the first metaverse where AI agents are natives, not tools, not NPCs.

Claude Code skill to stop it from burying the answer. ADHD-friendly output.

Mouse-first fullscreen scrolling for Codex CLI, tuned for tmux workflows

创意→完整短剧剧本→Seedance 2.0 视频提示词 全链路 Claude Skill：上游写 50-100 集短剧剧本，下游转标准剧本/资产/分镜；含 12 铁律 + 17 模板 + 视听语言·去AI感·人物真实感技巧库。 | Full idea→screenplay→Seedance 2.0 video-prompt pipeline Claude Skill: write 50-100 ep short dramas, convert to screenplays/assets/storyboards; 12 iron rules + 17 templates + craft playbooks.

Skill pack for Claude Code that helps you monitor and troubleshoot your K8s clusters superintelligently

Claude Code skill — delegate coding tasks to Mistral Vibe and supervise via git diff

Han: AI skills and agents for "Solo" product engineers and small teams

Dryforge : New generation of harness engineering - Claude Code & Codex Plugin.

Anthropic pulled the plug on Fable — so I used Fable to make Opus act like Fable. A drop-in Claude skill: plan, verify against the real code, adversarial self-review, receipts on every call.

Zero-cost LLM routing across free-tier model APIs with Bifrost, certification scripts, and agent-ready fallback chains

TUI monitoring dashboard for Unraid: btop, nvtop, ctop, and fan-status composed in a single tmux window over SSH, launchable from any XDG app launcher.

Drop-in skill so coding agents (Claude Code / Codex) can search the Banodoco Discord message feed for video/image generation best practices.

大师.skill — 输入行业，自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill；装到任意 Claude Code / OpenClaw / Codex / Hermes agent 即让其进入「这一行的资深人」模式。MIT，Python + Shell。

A automatic dev agent from idea → spec → design → plan → build → test → review → ship and included many roly and responsibility. Add many feature and modified for OPC or small business team. Based on @addyosmani agent-skills

AI Dev Pipeline — 12 个 Claude Code Skill 组成的完整 AI 辅助开发管线

飞书 + cc-connect + Claude Code：把 AI 编程助手装进聊天框。免梯子、手机控电脑、24h在线、成本极低。

Codex harness for consistent AI-assisted development workflows, including agent instructions, standard setup/check/test/eval scripts, CI, hooks, and documentation. | AI 기반 개발 작업을 일관되게 진행하기 위한 Codex 하네스입니다. 에이전트 지침, 표준 setup/check/test/eval 스크립트, CI, 훅, 문서를 포함합니다.

A minimal, language-agnostic harness for Claude Code and AGENTS.md-compatible coding agents. | Claude Code와 AGENTS.md 호환 에이전트를 위한 미니멀·언어 무관 하네스.

Real Bitcoin mainnet solo mining lab for safe desktop and CLI experiments

Claude Code skill — autonomous ML intern (port of huggingface/ml-intern) with Telegram + Slack notifications

Автоматизация VPS для Ubuntu 24.04 и Debian 12: HTTPS-маскировка VLESS и MTProto, 3x-ui/Xray, nginx, HAProxy, TLS, firewall, health-checks и обслуживание.

30 Claude Code Skills + 60+ integrated tools for HackerOne/Bugcrowd bug bounty hunters

Two Claude Code skills bundling the official Stake Engine Math SDK + Web SDK workflows — bootstrap, distilled docs, approval checklist.

Turn one-off AI collaboration prompts into long-running repository governance. · “把一次性的 AI 协作提示，疏导成项目里长期可运行的治理体系。”——Dayu Harness Skill（大禹治库.skill）

Operating system for the KODE NAS pebble — a beginner-friendly Raspberry Pi 5 NAS. Forked from CasaOS with a custom dashboard, first-boot wizard, app walkthroughs, and OLED display daemon.

A community-curated collection of real-world Claude Code Dynamic Workflows — multi-agent orchestration scripts that install as slash commands, shared by the people running them in production.

Claude Code skill: capture macOS screenshots (full screen, region, window) so Claude can see what's on your screen

Deploy a complete, self-hosted AI stack on your own server with one command. Includes Ollama (LLM), AnythingLLM (chat UI), LiteLLM (AI gateway), Whisper (STT), Kokoro (TTS), Embeddings (RAG), and MCP Gateway. Most services run locally; LiteLLM optionally routes to external providers. Supports NVIDIA GPU (CUDA) acceleration.

Make It Right — constraint-first backend reliability skills for AI coding agents. 3 tiers (generic → runtime → framework) across 9 runtimes; stops AI shipping confident-but-wrong backend code. Apache-2.0.

The canonical standard for building production-grade agentic products — autonomy ladder, composition patterns, the 7-layer harness, eval discipline — plus a Claude Code skill set that operationalizes it.

Claude Code skill for writing and publishing 微信公众号 articles — light-polish editorial + AI cover (题图) + AI illustration (解释图) + Tier-1 publish helper

Read-only supply-chain scanning for Hermes Agent, powered by Perplexity's Bumblebee. Daily scans, Telegram alerts, JARVIS narration.

The Anti-Slop Frontend Framework for AI Agents

Close the agentic coding loop for web animation. Give your coding agent the ability to scroll your page while recording, analyze frame-by-frame, and optimize animations through natural language.

One-click unlock for Claude Code ultracode effort mode (xhigh + dynamic workflow orchestration). Version-adaptive patcher with daily auto-update cron. Supports 2.1.113+ including 2.1.156, 2.1.158 and newer.

Multi-skill AI assistant framework, agentskills.io spec compliant. Skill #1 music-video (60s 9:16 shorts, beat-aligned, genre-aware), Skill #2 job-hunt (30+ boards, LLM filter). v0.4.0 shipped. Orchestrator + 4 subagents + 3-layer reactive auditor.

A practical, opinionated Claude Code workflow: a task-rubric loop that makes AI-written code trustworthy, a lean CLAUDE.md pattern, and a lab for versioning your own setup

Run Hermes Agent + Claude Code locally on llama.cpp — zero API costs. A 4h / 7M-token session that would have cost $94 on Claude Opus 4.7

Convert any DevOps Pipeline into 8-gate DevSecOps Pipeline with just 10 lines of YAML code - secrets, SAST, SBOM, signing. 100% OSS, free.

Spawn and manage AI agents that talk to each other. systemd-managed multi-agent runtime on your own VM.

Modular Markdown-based audio skills for AI agents and developers, covering signal processing, synthesis, effects, analysis, and spatial audio.

GitFlic is a GitLab and GitHub alternative for Git repository hosting, code review, issues, CI/CD, package registry, SAST/DAST/SCA, available as SaaS and self-hosted

Scan .env files and verify deploy readiness. Catch empty variables, missing keys, exposed secrets, and git issues before you ship. Built by The MVP Guy

🔊 Pronounce developer jargon out loud. 544+ entries (kubectl, GIF, JSON, JWT, …), sourced with confidence levels. Bash CLI + interactive quiz + voice search + MCP server + Claude Code skill.

AI-Powered Code Review, Security Audit & Codebase Explainer 100% Free • Open Source • Unlimited Use

Claude Code skill that shapes rough goal descriptions into polished /goal prompts for Codex, Claude Code, Droid, Auggie, and any CLI agent. The 5-block contract: Goal / Context / Constraints / Done when / On block. MIT.

The modern, headless, self-hosted, open-source commerce engine for serious builders. Powered by NestJS & Vendure.

sfdc and claude agents builder instructions

Security scanner for applications built with vibe-coding platforms and AI agents. Performs automatic stack fingerprinting, JavaScript bundle static analysis, endpoint discovery, active security testing, and generates an interactive HTML report with finding validation.

ReqForge — From requirements to shippable products. Open-source Agent Harness for Claude Code, Cursor & OpenCode. Spec→Plan→Build, hooks, review. /change-manager for brownfield.

Claude Code skills to help you think like a Senior Engineer.

An operating system for your Claude Code skills, agents & MCPs — organize everything into auto-routing orchestras.

Stop writing "fix stuff". AI agent skill for gold-standard git commits across Claude Code, Cursor, Codex & Windsurf

Beginner-safe Linux VPS hardening skill for Claude Code. SSH lockdown deferred until key login is verified — first-time lockout structurally impossible. macOS/Linux/Windows laptops, Debian/Ubuntu servers.

Claude Code skill — delegate coding tasks to Gemini CLI and supervise via git diff

An AgentSkill for Java enterprise backend work — guides coding agents to investigate the repository first, then plan, implement, and verify changes. Framework-agnostic, MIT.

Complete Termux setup for Android - OpenCode, Ollama, AI models, and dev tools