베스트 & 인기 Agent Skill
리뷰, 리서치, 글쓰기, 데이터 분석을 위한 재사용 가능한 워크플로.

Structured context management framework for LLM agents. Implements Git-like operations (COMMIT, BRANCH, MERGE) to manage long-horizon agent memory.

Describe your dashboard. An agent builds it. Live market data, no API keys.

A Claude Code / Cowork skill that interviews you relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.

Autonomous Background Coding Agents on AWS

智能体控制 PS 插件:让 Codex 接管本地 Photoshop,自动新建画布、图层编辑、可编辑路径、质感换色和批量导出。

这是一套帮你写公众号的 Skill,可以直接装到 OpenClaw 里用。当然,这套 Skill 不是让 AI 替我们写一些很水的文章,我开源的核心目的是希望让 AI 可以降低我们的写作门槛,同时,也把写作过程中的资产,能够固化为一个的Skill。

OpenClaw登陆 IBKR 进行只读数据查询(无交易功能)。用于查看持仓、余额、实时行情。触发词:IBKR、盈透、持仓、股价、行情、portfolio。

CLI + Skill wrapper official Xcode 26.3+ MCP tools, so the "Allow access to Xcode?" popup only appears once per computer boot, plus a Skill that saves ~5K tokens of context per conversation.

A public library of reusable skills for investment professionals.

Resources from David Ondrej's interview with Micky / Michael Shimeles about serious AI building and agentic engineering.

Just Code, No Configs. The Library Bundler That Respects Your Time

本仓库是根据静水2008投资体系总结一文蒸馏成 13 个可调用的 AI Skills,仅供参考,原文链接: https://zhuanlan.zhihu.com/p/2056833702274110592

通用盗号网站注册轰炸机 适用于针对QQ、Steam等平台的各类盗号网站

A to run (Anthropic) on the host via the claude CLI (Agent SDK).

A compact high-signal benchmark for evaluating frontier agents

这是一个面向 LSPosed 模块开发 的低 Token Skill 包。它保留完整知识,但通过“启动版 + 按需知识库 + 模板 + 案例索引”的结构降低常驻上下文占用。

simple, type safe, elegant command line framework. the CLI framework for agents

Skills helping you write robust Zig code.

A coding agent harness built specifically for Motif-3

Official plugin marketplace repository for PI-Desktop

ReasBook main branch mirror for self-hosted CI

A single, readable bash script that takes a fresh Ubuntu/Debian VPS from default install to a hardened, ready-to-use server.

Skill for Hermes, and other agents, to ask typesafe's jev

A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference