nix-config

Provides an interface to the user's keyboard. Use this skill when working with keyboard operations, key events, text input, or any keyboard-related operations in LÖVE games.

Can simulate 2D rigid body physics in a realistic manner. This module is based on Box2D, and this API corresponds to the Box2D API as closely as possible. Use this skill when working with physics operations, collision detection, rigid body dynamics, or any physics-related operations in LÖVE games.

Load when working with LÖVE 2D, the LÖVE engine, love2d, .love archives, Lua 5.1/LuaJIT 2.1 game development, or LÖVE callbacks, modules, conf.lua, and packaging.

The primary responsibility for the love.graphics module is the drawing of lines, shapes, text, Images and other Drawable objects onto the screen. Its secondary responsibilities include loading external files (including Images and Fonts) into memory, creating specialized objects (such as ParticleSystems or Canvases) and managing screen geometry. LÖVE's coordinate system is rooted in the upper-left corner of the screen, which is at location (0, 0). The x axis is horizontal: larger values are further to the right. The y axis is vertical: larger values are further towards the bottom. In many cases, you draw images or shapes in terms of their upper-left corner. Many of the functions are used to manipulate the graphics coordinate system, which is essentially the way coordinates are mapped to the display. You can change the position, scale, and even rotation in this way. Use this skill when working with drawing operations, sprites, animations, shaders, or any visual rendering in LÖVE games.

Load for objective audio analysis from ffmpeg metrics - spectral statistics, spectrograms, loudness, EBU R128, LUFS, LU, RMS, dBFS, dBTP, true peak, crest factor, dynamic range, and noise floor. Covers the aspectralstats, astats, ebur128, and loudnorm filters: what each metric measures, how ffmpeg computes it, its units and range, and the external loudness standards and platform targets. Use when reading or producing ffmpeg audio measurements, even when the user names only a metric, filter, or standard.

Use when the user mentions `gh`, `gh api`, the GitHub CLI, the GitHub API, or wants to view, query, search, or change GitHub. Covers querying the GitHub API, raw API calls, PRs/pull requests, issues, workflows/Actions/CI, releases, repos, notifications, status, and any task that views or queries GitHub data.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Use when creating, updating, refactoring, or reviewing an AI assistant or sub-agent system prompt - persona, role, capabilities, tools, output format, examples, and constraints. Covers Claude Code agents, OpenAI Codex / Responses-API agents, Pi assistants, and OpenCode agents. Use even if the user only says "agent prompt", "assistant", "subagent", "persona", or names the artefact by file path.

Use when creating, updating, or reviewing a slash command - shims that delegate to a skill or agent, standalone commands with an inline output format, and the `description` / `argument-hint` / `model` headers per provider. Covers Claude Code custom commands and the merged skill-as-command format, OpenCode commands, Pi prompt templates, and the legacy Codex `/prompts:` route. Use even if the user only says "slash command", "prompt template", "command shim", "create-command", or names the artefact by path.

Load when working with Nix, NixOS, Home Manager, nix-darwin, nixpkgs, flakes, derivations, overlays, modules, options, or registries; with .nix files such as configuration.nix, home.nix, default.nix, shell.nix, or flake.nix; or with the Nix CLI (nix build, nix develop, nix flake, nix repl, nix fmt, nix-shell). Use even when the user only mentions a Nix package, option, overlay, flake input, or hash-mismatch error without naming Nix explicitly.

Use when creating, updating, consolidating, or reviewing an AGENTS.md (or CLAUDE.md, CLAUDE.local.md, .claude/rules/*.md, .cursorrules, .cursor/rules/*.mdc, AGENTS.override.md, or .github/instructions/*.instructions.md) project instruction file. Covers the open agents.md spec, Codex precedence rules, Claude Code memory loading, and migration from legacy formats. Use even if the user only says "instructions", "rules", "project memory", or names a single legacy filename.

Use when creating, updating, or reviewing an Agent Skill - authoring or revising a `SKILL.md`, its frontmatter, layout, references, and progressive disclosure. Use when the user mentions writing, editing, splitting, renaming, or auditing a skill, even if they do not say "skill" explicitly. Covers cross-platform portability across Claude Code, Codex, OpenCode, and Pi.

Provides an interface to create noise with the user's speakers. Use this skill when working with sound effects, music playback, audio recording, or any audio-related operations in LÖVE games.

Provides functionality for creating and transforming data. Use this skill when working with data operations, encoding/decoding, compression, data transformation, or any data-related operations in LÖVE games.

Manages events, like keypresses. Use this skill when working with event management, event callbacks, event pumping, or any event-related operations in LÖVE games.

Provides an interface to the user's filesystem. Use this skill when working with file operations, directory management, file reading/writing, or any filesystem-related operations in LÖVE games.

Allows you to work with fonts. Use this skill when working with font operations, text display, text formatting, or any font-related operations in LÖVE games.

Provides an interface to decode encoded image data. Use this skill when working with image operations, texture management, image data manipulation, or any image-related operations in LÖVE games.

Provides an interface to the user's joystick. Use this skill when working with game controllers, joystick input, gamepad operations, or any input device-related operations in LÖVE games.

Provides system-independent mathematical functions. Use this skill when working with mathematical operations, random number generation, geometric calculations, or any math-related operations in LÖVE games.

Provides an interface to the user's mouse. Use this skill when working with mouse operations, cursor management, mouse events, or any mouse-related operations in LÖVE games.

Provides functions for love operations. Use this skill when working with core functionality for LÖVE games.

This module is responsible for decoding sound files. It can't play the sounds, see love.audio for that. Use this skill when working with sound operations, audio decoding, sound data manipulation, or any sound-related operations in LÖVE games.

Provides access to information about the user's system. Use this skill when working with system operations, platform detection, system information retrieval, or any system-related operations in LÖVE games.

Allows you to work with threads. Threads are separate Lua environments, running in parallel to the main code. As their code runs separately, they can be used to compute complex operations without adversely affecting the frame rate of the main thread. However, as they are separate environments, they cannot access the variables and functions of the main thread, and communication between threads is limited. All LOVE objects (userdata) are shared among threads so you'll only have to send their references across threads. You may run into concurrency issues if you manipulate an object on multiple threads at the same time. When a Thread is started, it only loads the love.thread module. Every other module has to be loaded with require. Use this skill when working with multi-threading, parallel processing, background tasks, or any thread-related operations in LÖVE games.

Provides an interface to the user's clock. Use this skill when working with time measurement, frame rate control, performance monitoring, or any time-related operations in LÖVE games.

Provides an interface to touch-screen presses. Use this skill when working with touch operations, multi-touch gestures, touch events, or any touch-related operations in LÖVE games.

This module is responsible for decoding, controlling, and streaming video files. It can't draw the videos, see love.graphics.newVideo and Video objects for that. Use this skill when working with video operations, video decoding, video streaming, or any video-related operations in LÖVE games.

Provides an interface for modifying and retrieving information about the program's window. Use this skill when working with window operations, display settings, fullscreen modes, or any window-related operations in LÖVE games.

Condensed prose rules for docs, READMEs, blog posts, guides, scripts, and long-form content; do not load for routine status, implementation reports, audit findings, or delegation responses.

Extended writing reference for documentation and content creation. Load for blog posts, READMEs, technical guides, and long-form writing.

Run Semgrep static analysis scans and create custom detection rules. Use when asked to scan code with Semgrep, find security vulnerabilities, write custom YAML rules, or detect specific bug patterns. IMPORTANT: Also use this skill when users ask to 'scan for bugs', 'check code quality', 'find vulnerabilities', 'static analysis', 'lint for security', 'audit this code', or want to enforce coding standards — even if they don't mention Semgrep by name. Semgrep is the right tool for pattern-based code scanning across 30+ languages.