* **Purpose:** A simple, reliable macOS desktop app that lets me (I will be the only user ever of this app) enter a **YouTube URL + start/stop times**, pick **quality/container** options, and **save**
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 →* **Purpose:** A simple, reliable macOS desktop app that lets me (I will be the only user ever of this app) enter a **YouTube URL + start/stop times**, pick **quality/container** options, and **save**
- `cmd/similarityd/`: Go REST server (`/similar`, `/healthz`, `/config`).
**MUST READ** before working on this codebase:
> A self-hosted agent is **your machine**, running **Microsoft’s agent software**, executing **pipeline jobs under your responsibility**.
This document provides guidelines for AI coding agents working in the JSON Visualization codebase.
**Project:** Wanderland\
TUI layer built on Ratatui + Crossterm. State machine with 3 modes (Solver/Game/History), handler-per-concern pattern, and modular rendering.
Operational guide for agentic coding assistants in this repository.
Keep the layout aligned with `PRD.md`. Library-style pipeline logic belongs in `pipelines/`, while thin CLI wrappers live in `scripts/`. Harvested inputs flow from `data/legacy_ro/` (read-only) into `
This repository contains the `vibepress` workspace: a WordPress-to-React pipeline plus supporting apps.
The Agent Task Framework helps transform ambiguous user requests into clear, structured instructions that background agents can execute successfully. This tutorial shows practical examples from real p
Executable units in Agentron: node agents (graphs) and code agents (scripts in sandboxes).
- AI infrastructure lives in `core/ai/` (models, checkpointer, graph factory). Agent definitions live in `core/agents/` (graph, tools, state per domain).
- Core code: `fim_rlvr_lean4/` (Lean verifier, curriculum logic, masking utilities).
This repository contains `vue3-ts-jsoneditor`, a Vue 3 wrapper/plugin around `vanilla-jsoneditor`.
A desktop star map and astronomy planning application built with Next.js 16 + Tauri 2.9. Integrates with Stellarium Web Engine for sky visualization, observation planning, equipment management, and as
This repository is designed to be maintained by AI coding agents.
`index.html` is the runtime entrypoint. The app is browser-only, with script load order documented in `MODULE_MAP.md`. Keep feature code split by responsibility:
`internal/services` is the backend domain core: collector, arbitrage engines, signal pipeline, technical analysis, notifications, cleanup, and resilience components.
This is an out-of-tree ONNXRuntime Execution Provider (EP) that uses AMD's
AGENTS.md — guidance for agents in this repo
This file provides guidance to AI coding agents when working with this repository.
Hugo personal blog. Theme (`themes/fortyten`) is a **git submodule** — it will be an empty directory after a plain clone.
freeq is an IRC server designed for agents. Not a chatbot framework bolted onto a messaging platform — the protocol itself treats agents as first-class participants with cryptographic identity, struct
Yosoi is an AI-powered tool that discovers resilient selectors for web scraping. The core philosophy is "Discover once, scrape forever." We use LLMs to analyze HTML structure and find selectors that a
This is a PHP 8.5 library with PSR-4 autoloading (`Dev\\MetadataBundle\\` mapped to the repo root).
- This project computes Austrian E1kv capital-income tax figures for **foreign / non-steuereinfache brokers** from CSV exports.
- **Framework**: Next.js 16 (App Router) with React 19.
Welcome to the **Interactive Library** project! Whether you are adding new interactive elements, resolving layout bugs, or modifying existing elements, read this document for reference.
TalentScout is a Next.js application that helps companies find talent and helps talent find jobs. The application uses MongoDB, GraphQL with Apollo, and Next.js with TypeScript and Tailwind CSS.
How to avoid burning tokens when nothing is happening. The core principle: **use zero-token bash checks as gates before invoking the LLM**.
This document provides context for AI assistants working on this Hugo static site project.
Learnings and patterns for future agents working on this project.
This document provides guidance for AI coding agents working in the Lolek codebase.
The infrastructure layer owns all side-effects: storage, embedding, importers, ingestion,
Read [../AGENTS.md](../AGENTS.md) first.
This repository is centered on [`supervisor.py`](./supervisor.py), which defines the LangGraph workflow, subgraphs, retrieval helpers, reporting, and the CLI entry point. Domain knowledge lives in [`k
Utilize Bruin MCP and use Bruin CLI to run assets and query the tables. Reference Bruin docs.
This file defines the reproducible analysis and plotting rules for the `nsd_evaluation/` workflow.
**Always use the project's custom agents and skills for porting work. Never do their jobs manually or with generic agents.**
>-
FedSpeak is a Federal Acronym Decoder maintained by MetaPhase. The core data lives in `src/shared/data/acronyms.json`. The API runs as Netlify Functions, the website is Vite + React.
MyWebIntelligence est une API FastAPI (V2 sync-only) encapsulant un crawler web. Elle permet l'integration avec MyWebClient via Docker Compose (API + Celery + PostgreSQL + Redis).
macOS menu bar app for managing Spaces (virtual desktops). Built with AppKit, uses Core Graphics private APIs for space detection and Mission Control accessibility actions for space lifecycle manageme
This document defines the workflow for AI agents working with the Data Visualizer project under `.claude`.
Autonomous multi-step systems that combine tools and skills to accomplish complex, coordinated development tasks. Each agent has a defined objective, execution pipeline, decision logic, fallback handl
Step 1: RESEARCH (all agents parallel)
> Design intelligence for UI/UX generation and critique; use for layouts, typography, color palettes, tokens, and UX best practices. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (Reac
Playwright v1.56에서 도입된 AI 기반 테스트 에이전트.
- **Framework**: FastAPI