Submit compact NCBI Entrez E-Utilities requests for PubMed, Gene, Protein, Nucleotide, PMC metadata, and GEO metadata workflows. Use when a user wants concise Entrez search, fetch, summary, or link results; save raw JSON or XML only on request.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Submit compact NCBI Entrez E-Utilities requests for PubMed, Gene, Protein, Nucleotide, PMC metadata, and GEO metadata workflows. Use when a user wants concise Entrez search, fetch, summary, or link results; save raw JSON or XML only on request.
Build a practical meeting prep brief from a connected Google Calendar event and its nearby context. Use when the user wants to prepare for an upcoming meeting, understand what to read beforehand, pull in linked notes or docs, or get a concise brief on what the meeting appears to require.
Vercel Workflow DevKit (WDK) expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.
Vercel CLI expert guidance. Use when deploying, managing environment variables, linking projects, viewing logs, managing domains, or interacting with the Vercel platform from the command line.
building-ai-agent-on-cloudflare
Design and implement App Intents, app entities, and App Shortcuts for iOS apps so useful actions and content are available to Shortcuts, Siri, Spotlight, widgets, controls, and other intent-driven system surfaces. Use when exposing app actions outside the UI, adding `AppEntity` and `EntityQuery` types, shaping shortcut phrases and display representations, or routing intent execution back into the main app.
This file provides guidance to agents working in this repository.
This document provides an overview of the Dart-Code VS Code extension project for AI assistants.
AI assistant instructions for the Kubernetes Agent project. This is an experimental project - prioritize simplicity over backwards compatibility.
Instructions for AI coding agents working on the React on Rails codebase.
- **Name**: Crunch
An AI client and API for WordPress to communicate with any generative AI models of various capabilities using a uniform API. Built on top of the [PHP AI Client](https://github.com/WordPress/php-ai-cli
This file provides persistent instructions for AI coding agents (Cursor, Copilot,
This is the master repository for curated Claude Code workflow collections.
- **Language**: Go 1.25+
- When you start, the first thing you should do is tell the user if you understand these instructions and list the config files you are aware of.
This file provides guidance to Codex CLI when working with code in this repository.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
This repository is part of the Ziggy* codebase and is primarily a Zig project.
This provides essential guidance for AI coding agents working on this repository.
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
merjs is a Next.js-style web framework written in Zig. Zero Node.js.
- Ivy is a declarative full-stack UI framework that allows developers to build user interfaces using a component-based approach very similar to React.
This repository contains a Next.js 15 application written in TypeScript with Tailwind CSS and shadcn/ui components. The
Read these before making changes; they are authoritative for repo workflows.
> This document helps AI coding agents quickly understand the BuyyBox B2B marketplace codebase.
Agent API architecture, chat orchestration, tools, and workflow execution
Bring an OpenAI Agents Python app into the TraceCore workflow
TypeScript/JavaScript SDK for Filecoin Onchain Cloud (FOC). Published as `@filoz/synapse-sdk`.
This file provides context for LLM assistants (Claude Code and similar tools) working in this repository.
The adapters directory implements the host abstraction architecture that enables Cogni to run on different platforms (GitHub, GitLab, Forgejo, Bitbucket, Gerrit, Radicle, local git CLI) with identical
> **FOR AI CODING ASSISTANTS**: This is your guide to working with the MCP (Model Context Protocol) self-registering framework in this codebase.
This file provides guidance to AI agents when working with code in this repository.
This file provides guidance to agents when working with code in this repository.
The Stan models live in `code/` (e.g., `code/bsplines.stan`, `code/csplines.stan`) with companion R helpers such as `code/smoothing_diagnostics.R`. High level examples reside in `examples/`, including
**CRITICAL: UNLESS THE USER STATES "ignore rule zero" this rule is ALWAYS READ FIRST and ALWAYS ENFORCED in the prompt before any agent begins work on a user prompt.**
> **TL;DR**: This is a fully reactive Svelte 5 app with encrypted storage. Read the skill guides below based on what you're working on.
<!-- Parent: ../AGENTS.md -->
- Use **TypeScript** and **React** functional components.
**Purpose:** Guide AI agents to build evidence-based outbound messaging for Affirma sales motions.
- `app/` holds the Next.js route tree, including route handlers and shared layouts; use the `@/` alias for imports.
- `frontend/`: Vite + React app. Entry in `src/main.jsx`, UI in `src/App.jsx`, styles in `src/styles.css`, config defaults in `src/config.js`, API helpers in `src/api/client.js`, and token helpers exp
- `firmware/esp32s3_audio_min/` implements the ESP32-S3 bridge; it now emits binary `AUD0` frames and obeys `PAUSE` / `RESUME` commands.
This repository contains the Minnesota Conciliation Court Case Agent, a FastAPI
This document provides essential context for AI agents and developers working on this project.
- Static marketing pages sit at the repo root (`index.html`, `reservas.html`, legal pages) with shared styling in `assets/css`, scripts in `assets/js/main.js`, and media in `assets/img`.
This document provides guidelines for AI coding agents working on the WookiepediaStatusArticleData project.
<laravel-boost-guidelines>
- `main/` holds Electron main-process entry (`main.ts`), IPC channels, and SQLite helpers.
MCG is a Rust Cargo workspace for a browser-based card game. The frontend crate (`frontend`) compiles to WebAssembly with `wasm-pack` and renders using `egui`/`eframe`. The backend crate (`native_mcg`