Coding & Development

Agent skill for turning App Store reviews into product insights and SEO/GEO-ready pages.

A local-first workstream journal for tracking meaningful work across humans and AI agents.

A Claude Code skill that security-audits vibe-coded SaaS apps. 50 common ways AI-generated apps get pwned, turned into a repeatable checklist, severity scoring, and findings report!

Miniprogram skills tool - npx mp-skills 让小程序快速接入微信 AI 开发模式——通过安装现成的 Skill（咖啡点单、医院挂号、出行打车等），快速为用户提供 AI 驱动的对话式服务体验。支持快速创建新的 AI 小程序和 Skill，或将现有小程序改造为支持 AI 开发模式，并提供评测校验工具保障质量。

Loop Verify agent skill for Goal Contracts, AC mapping, verification gates, and drift checks

Pass the baton before your context runs out: a Stop-hook + skill that hands a long agent session off to a fresh one to cut token cost.

Transform public expressions and interpersonal insights into a standardized modular skill set for cross-platform application.

Harden a plan or decision with independent AI reviewers that don't know what you want — an unprimed thesis→antithesis→synthesis (정반합) loop. Essay + Claude Code skill.

OnyxAgent — Open-Source Super AI Assistant | Planning • Memory • Knowledge • Evolution • Skills • Multi-Channel

Protect AI coding agents with incident response skills for dependency and supply chain compromise.

Codex skill for running LLM and agent experiments on remote GPU servers

Get a second opinion from ChatGPT Pro for Claude Code reviews with one command.

Daily Leetcode masterclass with Claude code DSA mentor

mori MCP server — A shared memory layer for AI coding agents — one that compounds.

One Works application monorepo for AI agents, plugins, desktop, web, CLI, and Relay.

SuperX Autonomous AI Agent 2026: 14 Specialized Coders, 10x Parallel Execution & Adaptive Skill Learning

缠论技术分析 Agent Skill —— 零依赖、纯知识的缠论教科书。让任何 AI Agent 学会缠论：分型、笔、线段、中枢、背驰、买卖点、多级别联立分析。

Zero-cost hybrid skill router for AI agents. Graph spreading activation + cosine similarity + keyword fusion. Pure local, 40ms/query, no API calls.

面向中国家庭代际沟通的 Agent Skill：先判风险，再选哄、拖、谈、换、硬、走，提供边界、安全方案和可复制话术。

内置八层金融求职安全方法论：证据、隐私、附件与真实投递预检 Agent Skill

Scan codebases for dead code, unused imports, duplicates, secrets, and circular deps with vtrigger CLI and Claude Code skill

Automate structured product discovery using JTBD, Opportunity Solution Tree, and Lean frameworks within Claude.

Lightweight agent skill for recording deferred follow-up checks in repository-local WATCHLIST.md. No daemon, no cron — just structured pending-check notes for AI agents.

Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.