Coding & Development

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.

Report-only pre-merge policy gate as a Claude Code skill — checks a diff against versioned rulesets and returns a PASS/WARN/FAIL verdict. Never edits code.

无剧透看球回放 Claude skill

Control 16 platforms with natural language in Claude Code using your Chrome login, no API keys needed

Fast, language-abstracted idiom enforcement for AI coding agents and humans — teach via a generated skill, enforce via a sub-100ms autofixing gate. Rust core + Python/Node bindings.

Best Free GitHub Skill Publisher Tool 2026 - Auto Deploy Local Skills to ClawHub

🤖 AI agent in your browser — WebGPU local models, skills, MCP, OpenAI/OpenRouter support

AEGIS — a self-improving, multi-provider, multi-channel terminal agent harness in Python (an open replacement for Hermes Agent + OpenClaw): bounded agent loop, OAuth+API-key providers, MCP, skills marketplace, gateway, browser/computer-use, one-line install.

Aggregate and serve specialized Agent Skills across multiple servers with dynamic tool management and human-in-the-loop security controls.

Fable 5 / Mythos style orchestration: a multi-agent company that verifies its own work and cannot stop until every criterion passes.

Explore Claude Code prompt references for system, tool, skill, command, memory, and agent prompts in one organized repo

Drop-in Claude Code / agent skill: turn a work session into a dated journal entry in your own voice, saved to a folder or GitHub repo.

So I don't repeat myself to Codex continuously. :)

Organize scattered AI agent rules into a unified skill-based architecture for better control and modularity.