DaFum

Take Playwright screenshots of any Neurotoxic game scene (INTRO, MENU, OVERWORLD, PREGIG, GIG, POSTGIG, GAMEOVER, CLINIC), UI overlays, PixiJS canvas, modal states, and visual regression baselines. Trigger when capturing screenshots, documenting UI, recording…

Guided workflow to eliminate copy-paste duplication detected by jscpd. Refactor clones using extract function, module, constant, or base class strategies.

run a comprehensive linting suite (MegaLinter style). Trigger when asked to check code quality, security, or style across multiple languages. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Produce a prioritized lint/security…

Use this whenever users ask to create a skill, improve/refactor an existing skill, evaluate skill behavior, benchmark variance, or convert a repeatable workflow into a reusable agent instruction set. Trigger aggressively on phrases like "make a skill",…

Implement bug fixes, features, balance adjustments, and performance optimizations for NEUROTOXIC. Trigger when: asked to fix bugs (state corruption, crashes, logic errors), add features (new items, upgrades, mechanics), tune balance (costs, rewards,…

create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis. Also trigger…

Use when asked to create, improve, review, migrate, sync, or validate repository context files for coding agents, including AGENTS.md, CLAUDE.md, CODEX.md, GEMINI.md, .cursorrules, or .github/copilot-instructions.md. Trigger on close synonyms and paraphrases…

Use when asked to create, improve, review, migrate, sync, or validate repository context files for coding agents, including AGENTS.md, CLAUDE.md, CODEX.md, GEMINI.md, .cursorrules, or .github/copilot-instructions.md. Trigger on close synonyms and paraphrases…

Skill-gap workflow for this project. Use when no existing repo skill fits a task after consulting skill-router, or when repeated work reveals a missing reusable workflow; guides agents to decide whether to create a new skill, define its scope, scaffold it,…

Master router for repository work. Use before changing, extending, optimizing, validating, documenting, committing, or preparing pull requests for this project; route to the dedicated thinking, plan-writing, plan-execution, idea-developer, frontend-phaser,…

Architecture workflow for this project. Use for state flow, services, hooks, Phaser scene coordination, AI orchestration, persistence, system boundaries, and cross-file design decisions.

Documentation workflow for this project. Use for README, memory.md, ARCHITECTURE.md, scoped AGENTS.md, skill documentation, durable project knowledge, and deciding whether instructions belong in docs.

Frontend Phaser workflow for this project. Use for Phaser scenes, sprites, canvas integration, game-loop presentation, input handling, animation timing, scene tests, and React-to-Phaser coordination.

Performance workflow for this project. Use for runtime smoothness, bundle or build performance, Phaser rendering, React render frequency, AI/API efficiency, responsiveness, and measurement-driven optimization.

Plan execution workflow for this project. Use when carrying out an approved plan step-by-step, keeping edits surgical, checking progress after each step, and preventing scope drift.

Planning workflow for this project. Use when turning a request into a concise, verifiable plan with assumptions, tradeoffs, success criteria, scoped steps, and exact checks before repository work begins.

Write high-quality AGENTS.md, CLAUDE.md, or CODEX.md context files for code repositories. Use this skill whenever the user asks to create, write, generate, improve, or review a repository context file for coding agents — including any mention of "AGENTS.md",…

Implement bug fixes, features, and targeted improvements for the Neurotoxic codebase — a 3D narrative adventure game built with React, Three.js (R3F), Zustand, and Rapier physics. Trigger when: the user wants to fix bugs, add features, refactor code, or…

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or…

Implement bug fixes, features, and targeted improvements for the Neurotoxic codebase. Trigger when: requested changes touch `dialogue`, `inventory`, `quests`, `scene` wiring, audio, physics, or store/state logic — or when small, repository-conforming…

**WORKFLOW SKILL** — Produce a reusable SKILL.md from a conversation, PR, or code change. Outputs a conservative draft, concise clarifying questions, and runnable example prompts tailored to this repository.

Implement bug fixes, features, and targeted improvements for the Neurotoxic codebase — a 3D narrative adventure game built with React, Three.js (R3F), Zustand, and Rapier physics. Trigger when: the user wants to fix bugs, add features, refactor code, or…

Implement bug fixes, features, and targeted improvements for the Neurotoxic codebase — a 3D narrative adventure game built with React, Three.js (R3F), Zustand, and Rapier physics. Trigger when: the user wants to fix bugs, add features, refactor code, or…

Write high-quality AGENTS.md, CLAUDE.md, or CODEX.md context files for code repositories. Use this skill whenever the user asks to create, write, generate, improve, or review a repository context file for coding agents — including any mention of "AGENTS.md",…

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Apply the Null Agent instruction model for literal, immediate execution using repository AGENTS.md semantics. Use when tasks require strict instruction-following behavior, scoped AGENTS.md adherence, minimal interpretation, direct tool-driven execution steps,…