Explore
5,644 skills indexed with the new KISS metadata standard.
A filesystem-based stigmergy communication protocol. Use this to leave invisible "pheromones" (signals) on files to communicate context, risks, or status to other agents or your future self without modifying file content.
Manage Raindrop.io bookmarks, collections, tags, and highlights via API. Use when user mentions raindrop, bookmarks, saving links, organizing URLs, bookmark collections, or web highlights.
Assiste au développement avec le framework e-commerce Vendure pour Node.js. Gère le commerce headless, les APIs GraphQL, la gestion des commandes, les catalogues produits, l'intégration des paiements et le développement TypeScript e-commerce. Utiliser lors du travail sur des projets Vendure, la création de plugins, ou l'intégration de storefronts.
This skill should be used when the user asks to "explain", "break down", "help me understand", "teach me about", or requests clarification of technical concepts (AI, ML, software development, or other technical topics). Transforms complex ideas into clear, accessible explanations using narrative storytelling frameworks.
Use this skill when users want to generate images using OpenAI's image generation API (DALL-E or gpt-image-1), or extract text from images using OCR. Invoke when users request AI-generated images, artwork, logos, illustrations, visual content from text prompts, or need to extract text/data from images.
Manage hierarchical project plans in SQLite. Tree-based structure with phases and tasks. Multiple output formats (text, JSON, XML, markdown).
AI context persistence - tags in code = permanent memory across sessions
Repo Updater - Multi-repo synchronization with AI-assisted review orchestration. Parallel sync, agent-sweep for dirty repos, ntm integration, git plumbing. 17K LOC Bash CLI.
**Generated:** 2026-02-12
This repository expects any automation agent (Codex CLI, LLM assistants, scripted bots) to follow the rules below before delegating to folder-specific AGENTS guides. Treat this document as the global source of truth; per-directory `AGENTS.md` files (for example `agent/AGENTS.md`) extend these rules
The n8n-copilot-shim is an **orchestration agent** that manages multiple specialized subagents, each configured to handle specific domains and tasks. This document describes the agent system architecture and how to work with agents.
**Version 1.0.0**
你正在 `/Users/bensz/Nutstore Files/PythonCloud/Agents/pipelines/skills` 中工作：该目录用于开发与维护一组"可复用 Agent Skills"。
Nix-darwin/NixOS service module wrapping [nix-openclaw](https://github.com/openclaw/nix-openclaw) for Telegram AI assistant.
generic skill
- **Category**: Feature
PhiCookBook adalah repositori buku resep yang komprehensif berisi contoh praktis, tutorial, dan dokumentasi untuk bekerja dengan keluarga Small Language Models (SLMs) dari Microsoft, yaitu Phi. Repositori ini menunjukkan berbagai kasus penggunaan termasuk inferensi, fine-tuning, kuantisasi, implemen
PhiCookBook is a comprehensive repository of cookbooks containing practical examples, tutorials, and documentation for working with Microsoft's Phi family of Small Language Models (SLMs). The repository showcases various use cases, including inference, fine-tuning, quantization, RAG implementations,
**Load this reference when:** creating or editing skills, before deployment, to verify they work under pressure and resist rationalization.
Progressive Web App for The Blue Alliance, a data archive site for the FIRST Robotics Competition, built with TanStack Start / Router, TypeScript, and Tailwind CSS.
Someone built a multi-agent orchestration system for VS Code Copilot with dedicated agent files for each role. The economics are wild, but the architecture patterns are what I can't stop thinking about.
Statespace is an open-source AI runtime/framework. This monorepo contains the Rust implementation.
<title>Cloudflare Workers Monorepo Guidelines for AmpCode</title>
By themselves, language models can't take actions - they just output text. A big use case for LangChain is creating agents. Agents are systems that use an LLM as a reasoning engine to determine which actions to take and what the inputs to those actions should be. The results of those actions can the