Shell agents

🧠 Community skill for Claude Code & Codex that helps your agent learn from its mistakes. /aprende reviews the conversation, surfaces durable learnings (memories, Reflexion-style anti-patterns, skill stubs, project-docs), and writes them only after you confirm. Bilingual (EN/ES). Made by tododeia.

ApexPanda 官方仓库 · 仅供合法合规使用，禁止用于任何违法用途

Auto-resize oversized images and repair corrupted sessions in Claude Code

Harness Engineering playbook — deterministic smoke/test/lint harness commands, strict architecture boundaries, entropy-control checks for autonomous agent workflows.

Deterministic pre-action authorization for AI agents. Guardrails run before tool execution, so prompt injection cannot bypass policy checks.

A lightweight orchestration framework that piggybacks your local Agentic CLI setup. Intentionally simple. Yet powerful... like an army of Orcs 👹

Autonomous AI coding agent — 126 skills, 7 subagents, 5 platforms. Iterative optimization with automatic rollback, failure memory, and parallel multi-agent execution. Plugin for Claude Code, Cursor, Codex, Gemini CLI, OpenCode.

👻 ghost gpt– A powerful Termux-based penetration testing suite for ethical hackers. Includes free and premium tools to enhance your security testing workflows.

Autonomous multi-agent orchestration engine for software repos — L0/L1/L2 agents, leases, gates, audits, git-worktree isolation. Detached dispatch by default. GPL-3.0.

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.

Type a thought at your zsh prompt, get an answer — and run the command it suggests

zk-autoresearch — autonomous LLM agent optimizing a production ZK prover via benchmark feedback loop. First known application of Karpathy's autoresearch pattern to a ZK proof system.

A persistent management layer for Claude Code Agent Teams

A multi-skill agent suite that gives any AI tool senior ServiceNow architect, governance, delivery, and development knowledge.

Claude Code + Higgsfield as an automated video production studio: 19 skills, prompting playbook, agent operating manual, and real shipped production prompts

🏥 Self-diagnostic toolkit for OpenClaw AI agents. Find and fix problems before they find you.

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。

Claude Code plugin that stops "almost done" loops — declare your stages in workflow.json, runs them as a state machine that auto-retries until quick tests, code review, and journey tests all pass. Live web viewer + cross-machine resume + templates hub.

A template for creating and publishing Claude Code skills as npm packages

This tool is a wrapper for calling Terraform commands in the Docker, solving the problem of the Terraform version drift and pain with the different sub-projects configurations in a mono-repo. It uses a simple yaml file containing the list of projects and their configurations, which is visible and trackable.

Superseded by howells/skills

Utilities for managing agent memory, context windows, and task-focused state

6 Claude Code skills for solo founders, built from 101 Starter Story founder interviews. Idea evaluation, growth strategy, failure-mode diagnosis, plan roasting — all data-backed. Try in browser: solo-founder-playbook.vercel.app/try

Automatic task memory and keep-alive loop for Hermes agents. Every task gets durable notes in Obsidian. Arm the loop for long tasks, disarm when done.

Great music in your Claude Code sessions, with an AI DJ that understands your vibes

Find vulnerabilities. Ship secure. — Senior security-engineer skill for AI coding agents. OWASP Top 10, CWE Top 25, secrets detection, IaC + CI hardening, and a read-only auditor subagent. MIT.

260+ curated tools, guides, and projects for turning an Apple Silicon Mac mini into a 24/7 agentic AI home server. Ollama, Claude Code, Jellyfin, Vaultwarden, Home Assistant, and more - with one-command installers.

Universal long-term project memory for AI coding agents — Claude Code, Cursor, Windsurf, Cline + 4 more. TDD rules, code graph, spec-driven dev, cross-session recall.

Skill to let your agent pair with claude

Toolkit to run azure agents under linux

A battle-tested skill for managing a professional LinkedIn profile autonomously using Claude AI. 21 automations, 12+ weeks, 0 detection incidents.

187 plug-and-play AI agent personas em Português brasileiro — tradução do agency-agents + 3 originais do mercado brasileiro (PIX/Mercado Livre/WhatsApp Business)

Multi-agent system for product launches: strategy, paid ads, creative, and performance tracking

Multi-agent coding template — persistent memory, spec-driven workflow, skills and security hooks for Claude Code, Cursor, Windsurf, GitHub Copilot and any AGENTS.md-reading tool. No dependencies.

Drop-in skills that stop AI coding agents from shipping garbage — kill-slop, security-review, PR hygiene

A centralized cross-platform cheat sheet for Git, Linux, macOS, and Windows terminal commands, shell scripting, and AI agent setup guides.

A minimal CLAUDE.md template that turns any LLM CLI into a personal knowledge base. Drop in one file, start ingesting articles. Karpathy's LLM Wiki pattern.

Your Hermes agents, one shared brain.

Collection of useful skills for Claude Code - AI agents, frontend design, and more

This is a single NeuroDynamic Brain that can be adaptable across the agents , just point your claude or any agent session to load it one time.

Fork-and-fill bootstrap for AI coding agents (Claude Code first, Codex/Gemini via AGENTS.md) — agents, skills, hooks, tiered rules (P0/P1/P2) and stack presets composed into one enforced pre-commit gate. 한국어/English

Claude Code plugins: Ghostty terminal notifications and permission auto-handling

AGENTIC · OPERATIONS — A second brain for your company, and the team of agents that runs it. Duplicable Company OS template: one question, a bus, two registries, tiered autonomy, self-healing loops. Zero shared keys.

AI coding skill for generating and modifying Metin2 client UI code from screenshots, descriptions, or existing scripts. Works with Claude Code, Cursor, Codex, Windsurf, Cline, Copilot, and Gemini CLI.

Shell scripts for automated transcription on macOS: Integrates whisper.cpp with QuickTime Player and BlackHole-2ch for streamlined audio recording, conversion, and transcription.

Kubernetes helm chart for OpenClaw (former Moltbot/Clawdbot)

AI agents playing Clash Royale autonomously. Claude Code + multi-agent architecture reached 1000+ trophies live on Twitch.

Installable AI coding workflow for risk-based routing, scoped sub-agents, and evidence-backed completion.

The ultimate Claude Code toolkit for Unity — 20 AI agents, 22 slash commands, 41 skills, and safety hooks for AI-assisted Unity game development. Drop-in, production-ready.

A collection of agentic skills developed for AI agents and assistants. These skills extend the capabilities of AI agents by providing specialised instructions, workflows, and templates for various tasks such as documentation maintenance, content creation, diagrams, and more.

We heard you like harnesses, so we built a harness for your harness, so you can harness while you harness. Feel me?

Enterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.

Teach Data Engineers How to Think AI.

187 plug-and-play AI agent personas dalam Bahasa Indonesia — Indonesian translation of agency-agents + 3 Indonesian-market originals (Tokopedia/Gojek/WhatsApp Business ID)

A technical specification for the Jentic API AI-Readiness Framework (JAIRF). Defines the signals, dimensions, scoring model, and normalisation rules used to evaluate how interpretable, operable, and trustworthy APIs are for AI systems and autonomous agents.

Jump Skill Ninjas are intelligent meta-skills — master orchestrators that route your requests to the most appropriate specialized skill from a curated library. Instead of manually searching through hundreds of individual skills, you simply describe your task and the Ninja Identifies specialized skills and Loads the full skill in context

Official CrowdSec skill for Claude Code & Codex: install, configure, operate and debug the engine, bouncers and WAF/AppSec.

Commands, rules, setups, useful wrappers for Claude Code, plus some Claude/Gemini interoperability

A very opiniated configuration for your software development workflow.

Nemo Code — FREE Claude Code alternative. NVIDIA open models + Claude Code CLI framework. One command install. Zero cost. By ClawdWorks.

OpenTelemetry Benchmark - can AI trace your failed login?

Talk to your shell — commands run, questions go to AI. No prefixes.

High-performance toolkit for running AI tools (OpenClaw, Pi Agent, n8n, Ollama, Hermes) natively on Android via Termux.

Spec-driven Claude Code, dropped into your repo in one command.

⚗️ Experimental — A markdown brain that gives your AI coding tools judgment and rigor: sharp defaults, real decisions, and the discipline to verify before saying done. For Claude Code, Cursor and Codex. It improves itself over time.

The ultimate AI-powered art generator

Names your startup, product or side project, then proves you can actually use it. Checks the domain registry, trademark, GitHub, npm, app stores and search. An agent skill for Claude Code, Cursor, Codex and 75 other agents.

Step-by-step guide to creating your own Oracle — from zero to a fully functioning AI agent system

Rasa Docker image for ARMv7. Runs on a Raspberry Pi.

Structured, version-aware AI delivery framework for long-running projects. Deterministic planning (Spec/PRD/Task/Roadmap) + wave-based atomic execution + Git-hook enforcement + zero-manual multi-platform testing (Android/iOS/Chrome) + closed-loop evolution from real production feedback.

Claude Code skill implementing Karpathy's LLM-wiki pattern on a personal GitHub repo, with qmd for on-device hybrid search.

Self-evolving skill engine for Claude Code — skills that create, score, repair, and harden themselves through recursive improvement loops

Bash script to update Claude Code's project references after moving a folder to a new path

Chinese OpenClaw use cases: real-world workflows, prompts, configs, automation examples, and a structured Markdown + JSON dataset.

Claude Code in a Docker image built on aicodebox, with an HTTP API, an OpenAI-compatible endpoint, an MCP server, a Telegram bot and a cron scheduler, in minimal or full-toolchain variants.

Universal AI Agent skill for downloading videos from YouTube/Bilibili/Douyin/Xiaohongshu/Kuaishou/Weibo/Twitter/Vimeo/TikTok. Works with Codex, Claude Code, Cursor, Cline.

跨项目知识库整理 Skill：信息分层归位、权限白名单优化、历史对话提炼。Claude Code 全局整理工具。

Free Claude Code plugin: learn Anthropic products hands-on from the official Claude Academy curriculum, and get your Claude Code setup and habits reviewed against Anthropic's best practices

Run claude with rootless podman

Context Engineering For Writers (with Claude Swarm)

Run claude with rootless podman

Elevate your Terminal's efficiency: harness the unbeatable auto-complete power through seamless ChatGPT integration!

🤯 Stop AI agents from leaving zombie terminals in GitHub Codespaces & VS Code. Copy-paste terminal management rules for Copilot, Claude, Gemini, Cursor, Windsurf, Cline, Aider. Fix "terminal unresponsive" errors, agent refusing to run commands, isBackground true, kill_terminal. Install script + dev container + templates.

Turn Claude Code into a personal AI agent with persistent memory. Interactive setup, 9 skills, 8 hooks, role-agnostic. Verified against v2.1.220.

Orchestrate fully autonomous Claude Code agent teams. Delivery pipelines, fleet operations, DORA metrics, and auto-scaling workers. From GitHub issue to deployed PR — zero human intervention.

PAIONE Vault — Markdown-based AI operating system. Your projects, notes, captures, and agent memory in one Git repo. Self-hosted. DSGVO-ready.

他山 Cursor Skill 体系 — 95个Skills + 32个Rules + 18个SubAgents，让AI在执行任务时能自主判断、按规范执行、并从经验中自我进化

Agent Skill for Overleaf — Automate LaTeX project management, sync, and compilation for AI assistants

Agent Skill guide for structuring skill repositories - multi-channel distribution | Claude Code compatible

Let Codex test multiple fixes in isolated worktrees, compare evidence, and apply only the safest proven solution.让 Codex 不再盲改代码，而是并行测试多个方案，用证据选出最稳的修复。

One command, 28+ top AI CLIs — an interactive launcher for terminal AI coding agents (Claude Code, Codex, Gemini, Aider…). Uzbek & English

Dependency safety gate for Claude Code & Codex CLI — OSV pre-approval, npm lockfile-closure enforcement, and auto-rollback. Local, zero runtime deps.

给 AI agent（Claude Code / openclaw / Codex）用的 VPS SSH 管理技能：统一密钥、别名管理、一键下发公钥、安全关闭密码登录、批量探活

Design UI changes from real source code — verify data, iterate faithful HTML mockups, then delegate. A Claude Code plugin & Codex skill by nlook.me

Universal AI writing skill — tech articles, marketing copy, research reports, Xiaohongshu notes, technical docs. Research-driven, full-pipeline, anti-AI-slop. Bilingual (EN/ZH).

Agent skills for working with Zapier, maintained by Zapier teams. Indexed by skills.sh.

Give Claude a checklist before bed. It can't clock out until every box is ticked, never stalls on a question, and revives itself if the API dies at 3 AM.

Claude Code Growth Operating System (OS): Sales, Marketing, Product and Retention as one Revenue system

Nine eval-built agent workflows for planning, implementation, copy, and repository work.