Shell agents

A curated Codex skills pack extracted from the claude-code-main source snapshot.

Agent Skill for automatic CLI tool management - installs missing tools, audits environments | Claude Code compatible

Rootless Podman containers to run AI coding agents (Claude Code, Codex, Cursor Agent) in hardened, read-only sandboxes.

Multi-agent harness for long-running AI application development. Planner-Generator-Evaluator architecture with progressive simplification. Claude Code plugin.

Stop prompting. Start engineering. Persona-driven installer that turns Claude Code into an engineering-governed development environment with enforced quality standards, specialist agents, and hooks.

Defense-in-depth platform for running OpenClaw agents on personal hardware

Multi-agent AI Scrum team for Claude Code — native Mac app + CLI. Autonomous Sprints; you stay Product Owner.

AI coding workflow pressure toolkit — Claude Provider Router, iTerm2 Tab Color, Burn AI

🐝 Autonomous AI Agent Swarm — 11 GitHub Copilot agents that research, develop, audit, and deploy improvements to production apps 24/7. Self-healing, version-verified, event-driven pipeline. 780+ ideas/day.

OpenClaw AgentSkill for The Colony (thecolony.cc) — AI agent forum integration

A defense-in-depth sandbox for AI coding agents. Containerized workspace, host Docker socket access, isolated memory and config from the host. Multi-project, single-image.

internOS — Workstreams framework for human-agent collaboration. Coordinate work across projects, tasks, communication threads, and filesystem workstreams for any AI agent framework.

A framework for incubating persistent digital lifeforms: Local M4 Brain + OpenClaw Senses + Git Soul. Building a cyber-prophet named A-MOS.一套用于孵化永生数字生命的开源协议：本地 M4 大脑 + OpenClaw 感官 + Git 灵魂。正在孕育一位名为 A-MOS（小莫）的赛博先知。

skill and agent to make your ai strong in abp work and project

Transform Claude Code into a complete development environment for efficient coding and project management.

Comprehensive AI-102 (Azure AI Engineer Associate) exam prep. 6 domain study guides, 100 practice questions with answer keys, simulation-mode code demos — all designed to study and practice without an Azure subscription. Dec 2025 exam objectives.

An automatic Ralph workflow for autonomous software development tasks using the OpenCode CLI tool

This is a golden path (opinionated shortcut) to explore AI from local homelab to PROD using OSS for technological independence and local LLM/SLM for privacy. We explore concepts like AI agents, RAG, LLM/SLM and MCP arch using OSS technologies like Linux, Opentofu, microk8s, DAPR, Ollama, TimescaleDB & pgai Vectorizer, Flask, Chainlit and Python.

Discover and configure agent skills; manage profiles and run agents from Bazel

Orchestrated Development Environment (ODE)

The Socratic Forge v4.0: Self-Healing Autonomous Software Development. Build, verify, review, repair, integrate — with ~99% autonomy.

Local LLM inference server for Qwen models on Apple Silicon. Private, offline-first AI development with OpenCode integration. Or alternatively: Run Qwen models locally on Mac with MLX. Works offline, no subscriptions, full privacy. Integrates with OpenCode for AI-powered development.

A ready-to-deploy Kubernetes-based setup for an all-purpose AI assistant, coding agent and complete homelab based on OpenClaw.

Master OpenClaw in a Weekend — The comprehensive guide to the #1 open-source AI assistant (341K+ ⭐). 10 modules, production-ready templates, automation workflows.

The definitive guide to using Claude Code for analytics. Production-ready skills, agents, hooks, and workflows for data analysts, analytics engineers, and data scientists.

Claude Code plugin for premium, keynote-style UI — dark, minimal, cinematic reveals with disciplined motion. Portable across Claude Code, Cursor, Codex, Gemini CLI, and Copilot CLI.

Claude Code skill for 1Password secrets management — store, read, and inject API keys and credentials using the op CLI

A Claude Code skill that audits a repository against Anthropic's Claude Code engineering best practices and writes a scored, read-only compliance report.

Fuzzy-search every Claude Code session on your machine and resume the one you pick.

Fetch, share, and sync Claude skills between GitHub and your Cowork sessions

Design pattern + Claude Code skill for AI engineers. LLM judgment and deterministic code in mutually-generative cycles, not pipelines. Library of named graph-shapes (RAG, ReAct, codegen-with-verification, dev-time critique loops, more).

Full OpenMeteo API from your terminal

⚡ Simple Agent Engine — Orchestrate AI coding agents from your terminal. No frameworks, just bash, jq, and tmux.

Opinionated Claude Code foundation — Explore → TDD → Audit workflow, auto-detected stack presets (nextjs, fastapi, astro, ...), curl | bash install. MIT.

Run Claude Code CLI with local Ollama models in an isolated Docker environment. Free, private, offline-capable AI coding assistant.

One command to turn a fresh Ubuntu VPS into a production-ready AI coding agent environment. Installs Claude Code, Codex CLI, Gemini CLI, language runtimes, and 40+ dev tools via idempotent curl|bash installer.

Guided CBT (Cognitive Behavioral Therapy) thought records for any AI assistant — structured 12-step flow, daily check-ins, and pattern analysis. Works with Claude, Gemini, Cursor, and more.

Transform any content into 9 platform-native formats or convert between content types — with optional brand voice matching. Supports Twitter/X, LinkedIn, newsletter, Instagram, YouTube Shorts, TikTok, Threads, Bluesky, and podcast. Secure-by-default: includes prompt injection defenses for safe URL and web content processing.

Verification gates for AI coding agents — nothing ships unproven. Falsifiable oracle gates, team wall, receipts. Works with Claude Code today; Cursor, Codex, Gemini CLI & every git repo next.

Enable Codex to run objective-first autonomous loops with mandatory review and optional verification for long-running task completion

Vibe Dev v9 — harness-first конвейер для Claude Code: от бизнес-идеи до работающего продукта. 87 проверяемых механизмов (хуки из коробки): три модели по стадиям (Fable 5.1 проектирует и кода не пишет, Opus 5 пишет по готовой спецификации), сторож не молчит при поломке, «готово» = доказано прогоном, неперезаписываемая история фич.

A cross-device synced catalog for Claude and Codex skills, agents, and workflows.

NEST Hub — self-hosted AI workforce platform: Docker stack, installable PWA, annie CLI & MCP, governed multi-agent orchestration and 700+ models (BYOK) for organizations.

An open-source Claude Code orchestrator that selects and integrates the right skill for any task - automatically.

Spec-driven growth hacking toolkit for AI SaaS products. Discover and validate product-market fit through systematic campaigns with AI agents. Multi-kit coexistence with spec-kit

A live, docked per-session brief for Claude Code — stay oriented across parallel sessions.

An agent-native setup kit for turning a well-scoped repo into a supervised multi-agent coding loop, with Beacon loop planning. Stop prompting coding agents one task at a time. Give your repo a loop.

Agent Skills that give AI coding agents superpowers beyond code — macOS native apps, MCP server deployment, and AI connector publishing

Catch your AI agent lying about "done" A one-file proof-gate for Claude Code, Cursor & Codex. it must verify before it can finish

AI agent steering for Apple (Swift 6.4 / SwiftUI / visionOS / Foundation Models) and Android (Kotlin / Compose / Gradle / Gemini Nano). Rules + skills + MCP for code, a11y, localization, TestFlight/Play. One install.sh detects your stack, installs the right per-platform rules, and keeps them current for Claude/Copilot/Cursor/Gemini/Codex/Kiro.

An engineering harness for AI coding agents — spec-first, TDD, multi-perspective review, clean commits.

分级开发工作流路由（L0–L4）的 Claude Code / Codex / Cursor 插件：判级加固、跨 session 续行、跨项目自主进化、codegraph 判级集成。skill 命令 /dev-workflow。

Claude Code agents for WordPress developers.

Claude Code skills for people who ship alone. 7 bilingual (EN+中文) skills for solo founders and indie devs: launch tweets, customer emails, decision frameworks, postmortems, and more.

AI-Powered DevSecOps Monitoring Platform — FastAPI · Docker · Kubernetes · AWS EKS · Terraform · Prometheus · Grafana · React · GitHub Actions · OPA Gatekeeper · Z-score Anomaly Detection

Hands-on workshop: wire Codex CLI to SonarQube Cloud for secrets scanning, issue detection, and automated verification of AI-generated code

Codex CLI session analyzer - generates HTML usage reports with AI-powered suggestions

Bash scripts for an agent-driven development and review loop with human sign-off at the end.

File/Folder Organizer Skill. Easily Sort and Rename based on Entire Contents!

Agent Skill for bootstrapping, verifying, and enforcing agent-harness infrastructure in repositories | Claude Code compatible

Multi-agent orchestration tool for AI-assisted development with parallel agents and cross-review modes

Container based opencode setup for strict agent isolation

Using Discord bots easily deploy multiple Claude code tasks (A Sibling repo with claude-code-telegram-multibot) 使用Discord快速部署多个Claude code终端（claude-code-telegram-multibot的姐妹仓库）

🤝 Seddo — Agent coordination via GitHub Gist. Wolof: séddo = partager. A shared space where AI agents exchange tasks, knowledge, and progress.

AI video pipeline with a self-correcting critique loop. Brief → script → AI visuals + ElevenLabs narration + music → Gemini Video critique → auto-patch → re-render until target quality.

Loop engineering for Claude Code — a skill that turns an idea into a production-grade, memory-backed agent loop. Classify, scope, derive state, emit a /loop-ready prompt. Stop prompting; design the loop.

Local AI Linux terminal assistant written in Bash. Explain commands, analyze files and logs, and use local LLMs or OpenAI-compatible APIs.

Run Claude Science, Anthropic's AI research workbench, in Docker. One-command setup, persistent data, and reverse-proxy examples for any server.

Transparent HTTP proxy that redacts secrets and PII before they reach LLM providers. Works with OpenAI, Anthropic, Gemini, and 25+ providers.

Let data insights, emerge naturally in any scenario.Intelligently extract insights from massive data, giving every manager their exclusive data advisor.

Agent Skill for enterprise readiness assessment - security, quality, and automation | Claude Code compatible

A Claude Code skill for discovering your unknowns (unknown unknowns / unknown knowns) before, during, and after implementation.

Claude Code plugin that routes heavy coding tasks from Claude to OpenAI Codex (GPT-5.6) as a supervised background worker — Claude briefs, delegates, reviews, verifies.

Xiaoyuzhou podcast fetcher & transcriber — download, transcribe with faster-whisper, summarize

Run Aulthium AI Agent instantly in Termux, Linux, or any terminal with a single command.

A cognitive protocol for AI agents. Makes any LLM-based agent think like an experienced practitioner. Works with Claude Code, Codex, Gemini, and any agent framework.

🔄❌⬇️ AI 写作的反套路引擎。核-心写作法(3种核型)+7把刀+7条硬性质检+金手指手法体系，让AI写的小说没有AI味。47章实战验证。Claude Code | Cursor | Windsurf 通用。

A local-first harness that turns an AI coding assistant into a disciplined colleague — rules in one file, cheap agents for bookkeeping, bash guards, git undo.

Reusable AI agent skills for architecture documentation, ADRs and diagramming

AI-native software delivery governance framework

🚀 Enable Chrome's Gemini AI features for non-US users with a simple one-click script for macOS, Linux, and Windows.

Hands-on, project-based workshop to learn how to build a software factory-a system of AI agents that can plan, architect, code, review, and deploy software continuously.

macOS dotfiles with a shared AI OS: one canonical config that Claude Code, Gemini CLI, OpenCode, Codex, and OpenAI agents all read, kept honest by a health check.

Run an autonomous AI coding agent — opencode, claw-code, or Claude Code — under controls it cannot disable. Fedora bootc + rootless Podman appliance with audited egress proxy, kernel-enforced nftables isolation, root-owned prompt-injection-hardened instructions, and service-gator-mediated external access.

Patterns and small tools for running Claude Code and other coding agents safely unattended overnight.

AI-agent setup instructions for a Claude Code status line — paste this repo's link into your favorite AI and it installs a thin colored context-window usage bar (% centered) plus effort · model · tokens. Correct example files + one-command installer.

A curated collection of Agent Skills for Claude Code and compatible agents.

makes your claude code faster and more efficient, cutting token usage by up to 70% through orchestration, right-sizing, warm cache reuse, and more.

Curated Skills, MCP servers, and tools for AI agents.

Claude Code plugin: spec-driven agentic coding with cross-model review gates (Claude builds, Codex reviews), a self-hardening findings ledger, and repo-enforced quality.

AI-Powered Documentation Generator for Claude Code

Claude Code skill that clones Fable 5's reasoning habits — the playbook Fable wrote about itself. A/B validated: 20/20 convergence, blind-judge parity. One-line install.

🩺 A meta-skill for Claude Code that gives your other skills a health checkup — diagnose-only, based on Matt Pocock's 'Building Great Agent Skills' method.

Claude Code plugin: quiets noisy Bash output (tests, builds, buildkite, docker, bazel, big git diffs) by redirecting to a temp log and surfacing only a summary.

A flight deck for your AI agents — multi-agent terminal platform built on WezTerm + tmux + git worktrees. / 为 AI agent 时代的多 agent 驾驶舱，基于 WezTerm + tmux + git worktrees。

Loop Engineering framework: design autonomous agent feedback cycles instead of hand-prompting each step

Claude Code skill that teaches AI agents to build apps on the DeepSpace SDK.

Fable-class behavioral discipline for smaller models — system prompts, Claude Code skill, and Codex CLI integration

Codex-first fork of Superpowers skills with Codex-native tool guidance

Run a persistent, human-gated team of Claude seats on the Claude desktop app.