adamhjk

Use this skill when adding screen reader and keyboard navigation to PixiJS v8 apps. Covers AccessibilitySystem options (enabledByDefault, debug, activateOnTab, deactivateOnMouseMove), per-container accessibility properties, shadow DOM overlay, mobile touch-hook activation. Triggers on: accessibility, a11y, screen reader, ARIA, keyboard navigation, tab order, AccessibilitySystem, accessibleTitle, accessibleHint, tabIndex, accessibleChildren.

Use this skill when creating and configuring a PixiJS v8 Application. Covers new Application() + async app.init() options (width, height, background, antialias, resolution, autoDensity, preference, resizeTo, autoStart, sharedTicker, canvas, useBackBuffer, powerPreference, eventFeatures, accessibilityOptions, gcActive, bezierSmoothness, webgl/webgpu/canvasOptions per-renderer overrides), app.stage/renderer/canvas/screen/domContainerRoot access, ResizePlugin, TickerPlugin, CullerPlugin (cullable, cullArea), custom ApplicationPlugin creation via ExtensionType.Application, start/stop lifecycle, and app.destroy() with releaseGlobalResources. Triggers on: Application, app.init, app.stage, app.renderer, app.canvas, app.screen, app.domContainerRoot, ApplicationOptions, ApplicationPlugin, ExtensionType.Application, resizeTo, preference, autoStart, sharedTicker, useBackBuffer, powerPreference, skipExtensionImports, preferWebGLVersion, preserveDrawingBuffer, cullable, CullerPlugin, app.start, app.stop, app.destroy, rele

Use this skill when loading and managing resources in PixiJS v8. Covers Assets.init, Assets.load/add/unload, bundles, manifests, background loading, onProgress, caching, spritesheets, video textures, web fonts, bitmap fonts, animated GIFs, compressed textures, SVG as texture or Graphics, resolution detection, per-asset data options, and forcing a specific loader with the parser field (for extension-less URLs). Triggers on: Assets, Assets.load, Assets.init, loadBundle, manifest, backgroundLoad, Spritesheet, Cache, LoadOptions, unload, parser, loadParser, loadWebFont, loadBitmapFont, loadVideoTextures, GifSource, VideoSourceOptions.

Use this skill when compositing display objects with blend modes in PixiJS v8. Covers standard modes (normal, add, multiply, screen, erase, min, max), advanced modes via pixi.js/advanced-blend-modes (color-burn, overlay, hard-light, etc.), batch-friendly ordering. Triggers on: blendMode, additive, multiply, screen, overlay, color-burn, color-dodge, advanced-blend-modes, glow, erase.

Use this skill when creating, converting, or manipulating colors in PixiJS v8. Covers Color class input formats (hex, CSS names, RGB/HSL objects, arrays, Uint8Array), conversion methods (toHex, toNumber, toArray, toRgba), component access, setAlpha/multiply/premultiply, Color.shared singleton. Triggers on: Color, ColorSource, hex, rgb, hsl, tint, premultiply, Color.shared, color conversion.

Use this skill when understanding how PixiJS v8 renders frames: the systems-and-pipes renderer, the render loop, and how the library adapts to different environments. Covers WebGLRenderer/WebGPURenderer/CanvasRenderer selection, renderer.render() pipeline, environment detection, and pointers to per-topic deep dives. Triggers on: renderer, WebGL, WebGPU, Canvas, render loop, render pipeline, systems, environments, autoDetectRenderer.

Use this skill when scaffolding a new PixiJS v8 project with the create-pixi CLI or adding PixiJS to an existing project. Covers npm/yarn/pnpm/bun create commands, interactive vs non-interactive flows, bundler vs creation template categories, available template presets (bundler-vite, bundler-webpack, bundler-esbuild, bundler-import-map, creation-web, framework-react, extension-default), Node version requirements, `npm install pixi.js` for existing projects, post-scaffold dev flow, and the Vite top-level-await production-build gotcha. Triggers on: create pixi.js, npm create, npm install pixi.js, scaffold, template, bundler-vite, bundler-webpack, creation-web, framework-react, new project, existing project, getting started, quick start.

Use this skill when writing custom shaders, uniforms, filters, or batchers in PixiJS v8. Covers Shader.from({gl, gpu, resources}), GlProgram/GpuProgram, UniformGroup with typed uniforms (f32, vec2, mat4x4), UBO mode, textures as resources, custom Filter via Filter.from, GLSL ES 3.0 conventions (in/out, finalColor, texture()), uBackTexture sampling, pixi.js/unsafe-eval for strict CSP, custom Batcher via extensions. Triggers on: Shader, GlProgram, GpuProgram, UniformGroup, Batcher, Filter, Filter.from, GLSL, WGSL, UBO, uniform, custom shader, finalColor, uBackTexture, blendRequired, unsafe-eval.

Use when ledgerlite HTTP handlers, status codes, request headers, JSON serialization, OpenAPI, or the generated client change or should change.

Use when ledgerlite OpenAPI, schemas, generated client code, or generator behavior changes or a generated artifact may be stale.

Use for ledgerlite implementation and review work that changes Go code, tests, validation, CLI behavior, or cross-package behavior. Run the smallest focused test first and the aggregate offline validation before handoff.

Use when ledgerlite invoice/payment persistence, idempotency, account scoping, mutation, replay behavior, or audit recording changes.

Drive @adam/software-factory runs: a fully generic, model-driven state machine for software development lifecycles with adversarial review gates, verified testing, and human approvals. Use when the user wants to start factory work on a work item, check factory status, drive a run forward, author a new factory definition, report on how a work item was implemented, or pull specific fields out of recorded run data (plans, review findings, evidence, the journal). Triggers on "software factory", "factory run", "start work on", "factory status", "advance the factory", "author a factory", "what happened with <work item>", "work item history/report/summary", and any question about artifacts or findings a factory recorded. Consult this skill the moment a message mentions a factory, factory run, or work item — before answering or running any command.

Interactive getting-started walkthrough for new swamp users. Guides through understanding the user's goals, creating and running a first model, inspecting output, and choosing next steps. Uses a state-machine checklist with verification at each step. Triggers on "getting started", "get started", "new to swamp", "first time", "tutorial", "walkthrough", "onboarding", "how do I start", "what do I do first", "quickstart", "quick start", "hello world", "first model", "just installed swamp", "show me how swamp works", "intro to swamp", "new user", "set up swamp", "learn swamp".

Swamp CLI — create and run models, build and validate workflows, query and manage data, store and retrieve vault secrets, develop and publish extensions, initialize repos, run reports, file issues, and troubleshoot errors. Triggers on swamp commands (swamp model, swamp workflow, swamp vault, swamp data), extension development, repo setup, or diagnostic questions. Do NOT use for getting started / onboarding (use swamp-getting-started), pull requests, git operations, worktree management, cron/agent scheduling, or general coding tasks unrelated to swamp.

Drive @swamp/software-factory runs: a fully generic, model-driven state machine for software development lifecycles with adversarial review gates, verified testing, and human approvals. Use when the user wants to start factory work on a work item, check factory status, drive a run forward, author a new factory definition, report on how a work item was implemented, or pull specific fields out of recorded run data (plans, review findings, evidence, the journal). Triggers on "software factory", "factory run", "start work on", "factory status", "advance the factory", "author a factory", "what happened with <work item>", "work item history/report/summary", and any question about artifacts or findings a factory recorded. Consult this skill the moment a message mentions a factory, factory run, or work item — before answering or running any command.

Swamp CLI — create and run models, build and validate workflows, query and manage data, store and retrieve vault secrets, develop and publish extensions, initialize repos, run reports, file issues, and troubleshoot errors. Triggers on swamp commands (swamp model, swamp workflow, swamp vault, swamp data), extension development, repo setup, or diagnostic questions. Do NOT use for getting started / onboarding (use swamp-getting-started), pull requests, git operations, worktree management, cron/agent scheduling, or general coding tasks unrelated to swamp.

Comprehensive two-pass review for Adam's blog essays before publishing. Use whenever asked to review, edit, proofread, copy-edit, critique, or give feedback on a blog post or draft in src/content/blog/ — even if the user just says "look at this post" or "is this ready?". Pass 1 applies mechanical copy-editing (spelling, grammar, punctuation, clarity) directly to the draft while protecting Adam's voice. Pass 2 evaluates whether the essay is compelling, personal, honest, and worth reading, and checks quotes, links, and frontmatter. Outputs edits in place plus a written review note. Does not touch git.

Convert RPG adventure locations into the set design quick-reference format for DMs. Use this skill whenever the user wants to reformat, restructure, or convert dungeon rooms, adventure locations, encounter areas, or keyed entries into a scannable reference format. Also use when the user mentions "set design", "room keying", "location formatting", "adventure conversion", "dungeon key", mentions Courtney Campbell or Hack & Slash blog, or asks to make adventure text more usable at the table. Works with pasted text, files, or PDFs from any RPG system.

Write and structure documentation using the Diataxis framework. Diataxis identifies four kinds of documentation — tutorials, how-to guides, reference, and explanation — each serving a distinct user need and requiring a distinct writing approach. Use this skill when: (1) writing new documentation of any kind, (2) restructuring or improving existing documentation, (3) reviewing documentation for quality, (4) deciding what type of documentation to write, (5) the user asks to "write docs", "add documentation", "document this", or mentions tutorials, how-to guides, reference docs, or explanation pages.