neurotoxic-game

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 such as "agent instructions", "coding agent setup", "AI-friendly repo", or "Copilot/Codex/Claude instructions".

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 such as "agent instructions", "coding agent setup", "AI-friendly repo", or "Copilot/Codex/Claude instructions".

Use when writing, revising, or reviewing TSDoc comments for TypeScript APIs, IntelliSense hover text, exported functions, classes, interfaces, type aliases, generic helpers, parameter docs, examples, deprecation notices, defaults, thrown errors, release tags, TypeDoc or API Extractor output, or documentation lint feedback.

Audit GitHub Actions workflow efficiency and recommend fixes to reduce CI minutes and costs.

Use when Neurotoxic test commands, CI test jobs, or runner-owned suites need diagnosis or optimization: slow/flaky/hanging/OOMing runs, runtime regressions, worker tuning, sharding, fixture duplication, suite topology, `pnpm run test`, `pnpm run test:all`, node:test, Vitest, Playwright, perf, or locale coverage.

Audit GitHub Actions workflow efficiency and recommend fixes to reduce CI minutes and costs.

Use when Neurotoxic test commands, CI test jobs, or runner-owned suites need diagnosis or optimization: slow/flaky/hanging/OOMing runs, runtime regressions, worker tuning, sharding, fixture duplication, suite topology, `pnpm run test`, `pnpm run test:all`, node:test, Vitest, Playwright, perf, or locale coverage.

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 before/after diffs, debugging visual glitches, or producing visual regression tests.

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 snapshot with actionable, grouped fix queues.

React performance optimization patterns using memoization, code splitting, and efficient rendering strategies. Use when optimizing slow React applications, reducing bundle size, or improving user experience with large datasets. Trigger this skill proactively when user phrasing matches its domain, keywords, or expected workflow outcomes;. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Prioritize profiling-backed React optimizations: render hotspots, memoization validity, and split strategies.

align skills with repository conventions. Trigger when a skill feels outdated, references missing files, or uses incorrect commands. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Align skills with repository conventions and resolve stale/misaligned instructions precisely.

validate skill structure and metadata. Trigger when developing skills, checking CI, or debugging skill loading issues. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Validate skill schema/metadata/tests and report failing IDs, cause category, and rerun command.

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

Strict TypeScript guidance for the NEUROTOXIC React/Three.js game codebase. Use when writing, reviewing, or migrating TypeScript; fixing tsc errors; and handling project-specific patterns like discriminated unions, action creators, lookup maps, and React 19 refs. Also use when touching src/types, src/context/action*, gamestateutils clamps, or @ts-expect-error suppressions.

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, difficulty), optimize performance (render loops, memory leaks, bundle size), refactor code (clean up tech debt, improve readability), fix UI inconsistencies (broken layouts, color mismatches), or test new systems. Routes to specialists: balance→game-balancing-assistant, audio→audio-debugger-ambient-vs-gig or webaudio-reliability-fixer, UI design→convention-keeper-brutalist-ui, state bugs→state-safety-action-creator-guard. Use for: core game logic, feature implementation, bug fixes, performance wins, refactoring, testing. Covers reducer changes, hook logic, data transformations, asset loading, persistence, and end-to-end testing.

run a comprehensive linting suite (MegaLinter style). Trigger when asked to check code quality, security, or style across multiple languages.

diagnose environmental and build issues. Trigger when the repo is broken, tests fail mysteriously, or setup is needed. Checks Node version, dependencies, and build status.

React performance optimization patterns using memoization, code splitting, and efficient rendering strategies. Use when optimizing slow React applications, reducing bundle size, or improving user experience with large datasets.

validate skill structure and metadata. Trigger when developing skills, checking CI, or debugging skill loading issues.

diagnose and fix asset loading issues. Trigger when assets fail to load (404), have incorrect MIME types, or when paths are undefined. Checks import.meta.glob, new URL(), and public folder references. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Focus on undefined paths, MIME mismatches, and import strategy fixes with exact file-path remediation.

debug audio playback issues. Trigger when music fails to start, plays the wrong track, stutters, or when ambient/gig transitions fail. Covers Tone.js, AudioContext, and asset loading. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Prioritize ambient/gig transition diagnostics, playback source correctness, and startup-unlock edge cases.

plan code changes and draft commit messages. Trigger when preparing to modify code, refactor, or fix bugs. Ensures commits follow Conventional Commits standard. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Return an actionable plan plus Conventional Commit candidates aligned to scoped change intent.

improve CI reliability, speed, and clarity. Trigger when CI is slow, flaky, fails silently, or needs optimization. focus on GitHub Actions workflows. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Prioritize flaky-failure root causes, workflow observability, cache strategy, and deterministic CI outcomes.

enforce brutalist UI design system. Trigger when creating or modifying UI components. Checks for correct colors, borders, shadows, and Tailwind v4 usage. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Enforce brutalist token usage, contrast/readability constraints, and component-level style consistency.

add debug tools, overlays, and logging. Trigger when asking for diagnostics, visualizations, or dev-tools. Use existing logger and debug viewer. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Add diagnostics that are visible, togglable, and low-noise in normal gameplay paths.

enforce pinned dependency versions. Trigger when asked to upgrade packages, install new dependencies, or when reviewing package.json changes. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Prevent unpinned upgrades and verify version-lock integrity before accepting dependency changes.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

analyze and tune game balance. Trigger when adjusting difficulty, economy, progression, or event effects. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Optimize economy/progression tuning with explicit trade-offs and measurable balancing deltas.

improve gameplay, balance, and code quality. Trigger when asked to fix bugs, add features, optimize performance, or refactor code. Acts as a general-purpose game engineer. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Prefer minimal, test-backed gameplay improvements with clear regression guards and state-safety checks.

write integration tests for the main game loop (Golden Path). Trigger when asked to add regression tests, verify game flow, or check critical paths. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Author end-to-end regression coverage for the main game loop with realistic user-path assertions.

create minimal reproduction cases for bugs. Trigger when asked to isolate an issue, create a test case, or debug a complex interaction. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Create deterministic minimal repros that isolate root causes with the fewest moving parts.

diagnose environmental and build issues. Trigger when the repo is broken, tests fail mysteriously, or setup is needed. Checks Node version, dependencies, and build status. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Diagnose environment/setup breakage quickly and return one-command recovery steps where possible.

run the full test and lint suite. Trigger when preparing to commit, submitting a PR, or verifying a change. Runs lint, test, and build in order. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Run lint-test-build gating in order and stop at first blocker with reproducible failure output.

optimize bundle size and runtime performance. Trigger when the app is slow, bundle is too large, or build warnings appear. Checks lazy loading, asset sizes, and render loops. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Enforce runtime/bundle budgets with concrete deltas and rollback-safe optimization suggestions.

detect and fix memory leaks in Pixi.js components. Trigger when reviewing Pixi code, scene transitions, or when performance degrades over time. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Audit mount/unmount lifecycle, texture cleanup, and long-session memory stability in Pixi flows.

generate comprehensive project context and instructions. Trigger when onboarding a new agent, creating a README, or summarizing the project architecture. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Generate high-signal project context that improves agent decision quality without redundant prose.

refactor code without breaking functionality. Trigger when asked to clean up, restructure, or optimize code. Enforces test coverage and quality gates. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Refactor in small verified steps with preservation of behavior and explicit rollback points.

create release notes from commit history. Trigger when preparing a release, summarizing changes, or writing a changelog. Understands Conventional Commits. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Synthesize release notes by commit intent, user impact, and migration/testing implications.

Generate strict project guardrails and checklists that enforce consistency, prevent common mistakes, and align teams on standards. Trigger when defining rules for new repos, setting up new agents/projects, enforcing technical constraints (version pinning, dependency management), creating team practices (code review, testing standards), preventing specific failure patterns (flaky tests, style inconsistencies), or integrating guardrails with existing documentation (AGENTS.md, CLAUDE.md). Works for monorepos with multiple project types and helps avoid rule conflicts across teams.

route requests to the correct domain and `AGENTS.md`. Trigger when asked where code lives, who owns a feature, or how the repo is organized. Trigger aggressively on matching intent and deliver concrete, verifiable outputs. Route requests to the correct domain files/owners with minimal lookup ambiguity.