zimppy
Zcash Machine Payments Protocol — private payments for AI agents
ai・機械学習タスク向けの 7,354 件のツールとスキル
Zcash Machine Payments Protocol — private payments for AI agents
AI agent skill for reading and editing Apple Numbers documents on macOS
基于循证学习科学的AI互动学习协议skill.AI agent skill for evidence-based interactive learning: spaced repetition, active recall, Feynman technique, interleaving & causal questioning. Compatible with OpenClaw, WorkBuddy, Claude Code, Hermes Agent.
Structured Adversarial Synthesis - Financial Analysis System
把前任蒸馏成 AI Skill，用ta的方式跟你说话。本项目基于 therealXiaomanChu/ex-skill 开发，扩展了 RAG 检索增强能力
MCP server for agent team chatrooms — real-time SQLite-backed chatrooms for AI agent coordination
Send tasks between Claude Code instances on different machines over SSH. Claude-to-Claude collaboration with session continuity.
Graph-backed cognitive context engine for OpenClaw. Brain transplant for your AI lobster.
>
Claude Code agent skill: search medications & check real-time stock at Clalit (כללית) pharmacies in Israel
Public connector that wires Codex CLI / Claude Code to Google NotebookLM via MCP. MIT licensed.
Turn any folder of notes into an AI-powered second brain in one conversation. One command to install, one command to start. Claude does the rest.
OpenClaw plugin for Kalibr autonomous routing. Captures LLM telemetry and agent outcomes via plugin hooks, reports to Kalibr for autonomous path optimization.
An experiment for doing spaced repetition and active recall using LLMs
API interation for Willys.se with a CLI + Claude Code skills
1Claw skill for ClawHub — HSM-backed secret management for AI agents
This repository contains a Claude skill for analyzing the exposure of companies to AI transformation for investing purposes
Work with Scarf insights directly from your favorite LLM provider
A comprehensive collection of AI agent templates, patterns, and sketches for rapid development.
纯文件维持的LLM记忆系统
🛒 AI Agent-ready CLI for the Bring! shopping list app 🧠✨
Install 7-law discipline + instinct-based learning (Mulahazah) into Claude Code — hooks observe every session, instincts strengthen or decay with confidence scoring
Expert skill manager for Claude Code — install, scope, sync, and curate skills with secure config handling
正常人.skill / 让 GPT 5 模型说人话。/ Please "optimize" Sam Altman rather than 4o in OpenAI
Claude agent skill: Generate proven ad concepts from 320+ templates. 16 universal angles + category-specific formulas.
Claude code skill that makes your vibe-coded app shippable. Go from 80% to 99% overnight
"用 DeepSeek API 训练 SkillOpt agent skill，从零到 best_skill.md"
ShortVideoDirector 是一个独立的 Claude Code skill plugin，通过 3 个 subagent 协作，将故事创意转化为 AI 视频分镜提示词和资产图像提示词。支持持续创作，保持人物和资产在整个故事中的一致性。每集短视频时长约 1-2 分钟。
A skill for bootstrapping reusable repository documentation that helps AI agents quickly understand and safely navigate any codebase.
Review OpenStack Gerrit changes for code quality, correctness, and OpenStack best practices
基于 Claude Code 官方 skill-creator，我融入了自己对提示词架构、Skill 架构以及 CLI 工具运行机制的理解，对其进行了全面重构，打造了一个新版 Skill Creator。 在测评环节，我采用 Codex 的 Headless 模式（无需打开图形界面，也无需进入 CLI 页面，直接在终端执行）进行了三轮以上的独立对话测试。测试结果显示，新版在各项维度上全面超越原版。完整的测试标准与评测报告已归档至「测评报告」文件夹，可供参考。 此外，新版在可维护性上也有显著提升——原版 Skill 一旦生成，提示词后续极难修改和维护；而新版的架构设计使得迭代和调整更加便捷，也更利于团队协作和长期维护。欢迎 star
🎯 中文大厂大模型面试教练 | 不是泛泛刷题，按真实面试逻辑做「项目深挖+追问+诊断+个性化训练闭环」，适配算法岗/应用岗/RAG/推理优化/训练微调等全岗位
Claude Code skill for systematic C/D round company investment analysis
Clean up LLM-generated artifacts and traces from code and comments
Claude Code skill for systematic documentation hygiene when making significant changes (license migrations, tier changes, API updates)
Claude Code skill: enforces strict no-direct-useEffect rule in React. Use derived state, event handlers, useMemo, key-based resets, or useMountEffect instead.
AI-native design system with BM25 reasoning engine — 9 palettes, 600 W3C DTCG tokens, 68 components, WCAG 2.1 AA validated, Tailwind/React/Vue/Svelte output, 57 industry sectors
Multi-model AI deliberation system querying 12 AI consultants (Gemini, Codex, Claude, Mistral, Ollama, etc.) in parallel. Features unique personas, confidence scoring, multi-agent debate, weighted synthesis, presets, and self-exclusion. Claude Code skill compatible with agentskills.io
Professional Taiwan equity analysis skill for AI agents, market ranking, and single-stock deep dives.
Shared memory and identity for your AI agents — Git-native, self-hosted, no vendor lock-in
first scratchpad&DeeperResearch-skill.md format from Claude
特斯拉.skill — 用心智仿真、系统结构与故障预判在动手前先把设计跑通。Nikola Tesla.skill — Run systems mentally, simplify design, and find failure points before building.
🔬 PubMed from your terminal. Search, fetch, cite, traverse — built for humans and AI agents. Zero dependencies, structured JSON, agent-ready.
Claude Code /buddy companion reroll skill — search for your perfect pet
"Help people install Predy and repair local setup on a fresh or half-configured machine. Use when the request is specifically about Predy or Predy MCP setup, for example: 帮我装 Predy, 帮我配 Predy MCP, Predy 装不上因为没有 Node, Predy 证书有问题, 我不是工程师你一步步带我把 Predy 装好. This repo can install setup guidance into Codex, Claude, Cursor, CodeWiz, and Copilot. It can auto-configure MCP for Codex, Cursor, and CodeWiz, and render a manual MCP-setup prompt fallback for supported clients when needed."
一个面向 Codex / AI Agent 的 Bashar（巴夏）原文资料检索与回答辅助 Skill。
完整的 Claude Code (ACP) 配置指南，让 OpenClaw 社区快速上手复杂编程任务。包含权限配置、故障排除和最佳实践。
Token pruning skill for Codex and Claude Code with vendored RTK, jq, qsv, jc, and TOON helpers.
A Claude Code Skill for deep analysis of open-source LLM projects. Inspired by howPrompt.
A Claude Code skill that maps your backend API routes