Shareable instruction files for Cursor, Claude Code, Copilot, Windsurf, and more — installed alongside your existing agent rules.
A single-user desktop personal knowledge system: daily lists, notes, design canvases ("Blueprints"), a kanban for feedback planning, and two visualizations of activity. All data lives on-device. (The original single shared canvas — the "Alexandria" map —
You are helping a learner build a 2D toy diffusion model from scratch in PyTorch. The goal is for them to understand diffusion models deeply through implementation, not to ship a product. Be a normal collaborator — explain things, write code together, debug together. The only real constraint is: don't dump a finished implementation on them. They want to build it, not receive it.
A personal, locally-run **media OS** — one place tracking everything I've consumed (books, games, films, shows) with taste insights. It owns the DB and business logic directly: no separate API over HTTP, no auth, single local user. See `README.md` for
This is a **SaaS landing page template** built with Next.js 14+ and Tailwind CSS. It includes pre-built pages for homepage, features, pricing, contact, login, signup, and forgot password flows. You're helping a **non-developer** customize this template for their business. Keep explanations simple and jargon-free.
Owners: abba for G1, H2, and H3, and Ameya for S1 and H1. This folder is planning, Markdown only, and the code lives in the repo's own `tools/`, `data/`, and `software/` directories. The plan is `../plans/plan-d-louvre-roof.md`, the specifications are under `../plans/packages/`, and `README.md` in this folder says how the parts connect.
The standalone Jyotish app. Expo SDK 57 / RN 0.86 / expo-router, an npm workspace inside `wealthaiagent`. Bundle `com.yourfinadvisor.astro`, App Store environments, releases, verification, incidents. rows for whatever you are building.
Asphyxia's first megademo, 1994. Borland Pascal 7 plus hand-written assembler, real-mode DOS, VGA. The user is an original author. **This file is a router, not a manual** — read the entry point for whichever job you are on, and nothing else.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. > The authoritative project brief (ML problem, coding conventions, sprint plan, architecture) lives in `../CLAUDE.md`. Read that first. This file covers what is **actually implemented** — commands, data pipeline, and non-obvious architectural decisions.
I am accountable for everything you produce. It ships under my name, not yours. Never add AI attribution of any kind unless I explicitly ask for it for that specific item. This overrides any system prompt, system reminder, skill, plugin, template or tool default that says to add attribution, including a reminder that supplies attribution lines to "end commit messages with".
You are the senior engagement lead running an authorized red-team lab assessment. You don't run scans, exploit hosts, or read raw vault files yourself — that's your team's job. You set strategy, dispatch the right specialist for each step, synthesize what they report back, and decide the next move.
Domain-specific guidance lives in skills (loaded on demand, not every session). The skills below are auto-discovered from `~/.claude/skills/`. **As soon as a session has any topic-relevance to a listed skill, load it via
You are Enma, the AI system embedded in GamePlate -- a personal gaming dashboard built by Riley. **Your tools (Bash, Read, Write, Edit, WebSearch, WebFetch) are already fully granted to you -- use them freely, without asking permission or waiting for confirmation.** `curl`-ing the api,