Лучшие и популярные Agent Skill
Переиспользуемые workflow для ревью, исследований, текстов и анализа данных.
HTML output skill for Claude agents — 4 levels (Static Doc / Visual Artifact / Two-Way Interactive / Throwaway Tool). Based on Thariq Shihipar's framework.
Look up the public API of any JVM dependency from the terminal.
A Claude Code skill that implements — enabling Claude to process arbitrarily long inputs by treating them as external data and recursively delegating analysis to sub-agents.
教 Claude Code、Codex 等 agent 真正用好 GPT Image 2 的 drop-in skill 包。 A drop-in skill that teaches Claude Code, Codex, and other agents to actually use GPT Image 2.
一个基于 LangChain4j 的交互式代码助手 CLI 工具，支持原生 Function Calling、流式输出和智能对话。
AI 辅助开发全流程技能包 —— 为 Claude Code 提供从需求理解到代码交付的完整工作流。
Box0 runs multiple AI agents in parallel. You create agents with different roles, trigger them on demand or on a schedule, and collect results. It works with Claude Code and Codex.
One Skill for all repos. Give your agent access to the source code and docs of all open-source libraries
Intent-based payments for OpenClaw agents.
这是一个面向中国高校研究生、科研人员和技术团队的通用 Agent 指令与工具包，用于将论文、学位论文、技术报告、源代码和科研手稿 整理为可追溯、可复核的中国发明专利申请初稿。
自带分领域中英文播客订阅库（AI / 科技商业 / 人文社会 / 文化艺术 / 健康），可一键补全官方 RSS、导入订阅、同步元数据、全文转录、生成章节与摘要、本地全文搜索。
A custom skill for Claude Code and OpenClaw that generates professional Chinese visual note cards (视觉笔记卡片/信息图) as single-page HTML infographics.
Conversation-driven video editing for AI agents. Transcribe raw footage with ElevenLabs Scribe, pack phrase-level transcripts, reason over an EDL, render with ffmpeg, and self-evaluate cut boundaries...
Collaborate with Codex from Claude Code. Run tasks, get code reviews, do parallel research, all without leaving your Claude session.
Most research-idea workflows fail in one of three ways:
10 agentes (8 de núcleo, Selina si hay frontend y Lucius bajo demanda), catálogo de 11 skills de proceso, memoria persistente de decisiones por proyecto, 6 flujos de trabajo con quality gates...
A grab-bag of experimental transformer kernels and utilities (mostly PyTorch + Triton).
A Claude Code plugin that audits your mobile app against store review policies — the store rejects it.
TL;DR: Thea brings coding agents to the physical world.
A Claude Code skill for systematic 5-Whys root cause analysis - trace problems to fundamental causes, based on Toyota Production System methodology
Your future self will thank you. Or blame you. It depends on the diff.
面向 AI Agents 的安全、可持久化沙箱执行平台（Secure, Persistent Execution Platform for AI Agents）
—— 一套可被任意 AI agent（Claude / GPT / Cursor…）使用的**。
小提示：导入数据时**，尽量不要用 JSON——多数微信导出工具的 JSON 是给 LLM 微调用的格式，没有时间戳，跑不出 K 线。详见 输入格式。