robcsaszar

@robcsaszar source repo

13 skills
0 followers
5 hours ago last updated

▌
With Canvas · robcsaszar bundle
Canvas implementation and review guidance for vanilla JavaScript, TypeScript, Web APIs, OffscreenCanvas, Web Workers, CanvasRenderingContext2D, WebGL-backed canvas, and canvas libraries including p5.js, Paper.js, Pencil.js, Konva, ZIM, Three.js, and Babylon.js. Use when creating, editing, optimizing, debugging, or reviewing canvas animations, generative art, games, charts, particle systems, interactive drawing tools, layered scenes, high-DPI rendering, RAF loops, hit testing, memory lifecycle, or performance issues. Trigger phrases: canvas, HTML5 canvas, OffscreenCanvas, requestAnimationFrame, getContext('2d'), drawImage, ImageData, particles, retained mode canvas, Konva, p5, Paper.js.

0
installs
▌
With Svelte · robcsaszar bundle
Modern Svelte 5 + SvelteKit guidance and routing. Use whenever creating, editing, reviewing, or debugging a Svelte component (.svelte) or module (.svelte.ts/.svelte.js), or any SvelteKit project. Covers runes ($state, $derived, $effect, $props, $bindable), template directives ({@attach}, {@render}, {@html}, snippets, keyed each), components (Bits UI, web components, forms), SvelteKit routing/layouts/error boundaries, data flow (load functions, form actions, +page.server.ts vs +page.ts, serialization, invalidateAll), remote functions (query/form/command/prerender in .remote.ts), deployment (adapters, Vite, pnpm, PWA, Cloudflare), and the @sveltejs/mcp CLI. Triggers are Svelte, SvelteKit, runes, .svelte, .remote.ts, +page, load function, form action.

0
installs
▌
With Drag Drop · robcsaszar bundle
Expert guidance for implementing drag-and-drop in JavaScript from scratch — free-dragging elements, sortable lists, resizable panels, drop zones. Use when making an element draggable, adding pointer-based dragging, building a sortable or reorderable list, or implementing resize handles, without reaching for a third-party dependency. Covers a single reusable drag engine (activators, modifiers, base+offset tracking), click-vs-drag disambiguation, transform-based live tracking, pointer capture, touch support, cleanup, and keyboard accessibility. Don't use for native OS file drag-and-drop (dataTransfer, File API) or HTML5 draggable-attribute-only reordering.

0
installs
▌
With Svg Animation · robcsaszar bundle
Surfaces the SVG animation traps that go unmentioned when a request sounds simple — dash patterns restarting at every subpath, pathLength normalization, transform-box on inner elements. Use whenever animating an SVG (draw-on, hover spin or scale, path morph, clip reveal, scroll-linked draw), including when the request names none of these and sounds like a one-liner, and when choosing between CSS, SMIL, WAAPI, GSAP, or a morph library. Don't use for raster or canvas animation (see with-canvas) or for non-SVG DOM transitions.

0
installs
▌
AI Forge Eval · robcsaszar bundle
Behavioral eval for skills and agents — whether the artifact actually changes model behavior, not just whether it scores well on a rubric. Use when verifying a skill or agent works in practice, or when tracking its performance across repeated runs to catch regressions. Triggers are test this skill, test this agent, eval this, does this skill work, behavioral eval, run eval, benchmark, benchmark this skill, track regression, verify outputs, does this agent work. Don't use for rubric-only scoring — that's ai-forge-judge.

0
installs
▌
AI Forge Apply · robcsaszar
HITL (Human-In-The-Loop) application of a numbered list one item at a time — status board upfront, per-item approve/skip, approve-all mode, and one opt-in commit bundling all approved items after the loop. Use when stepping through ai-forge-judge findings or any numbered changes. Triggers are apply these, go through each one, apply improvements, step through these findings. Don't use for bulk refactors, one-shot changes, or changes that don't need per-item review.

0
installs
▌
AI Forge Audit · robcsaszar bundle
Batch-evaluate all skills and agents in the repo with ai-forge-judge and render a single consolidated grade report sorted by grade (worst first) so effort is directed correctly. Use when reviewing overall skill/agent quality, finding where to invest improvement effort, or after bulk changes. Triggers are audit all skills, grade report, skill health check, where to focus, audit agents. Don't use for a single artifact — that's ai-forge-judge.

0
installs
▌
AI Forge Judge · robcsaszar bundle
Evaluate any LLM prompt (SKILL.md, agent definition, system prompts, instruction files) for quality — grouped dimensional scoring with letter grade and step-through-ready numbered improvements list. Triggers are judge/review/audit/score/evaluate this skill or prompt, grade this agent. Don't use for behavioral testing — that's ai-forge-eval.

0
installs
▌
AI Forge Recap · robcsaszar
Report what a skill or agent actually does versus what its description claims — drift, undeclared behaviors, verdict. Use before updating a skill or agent, or when a description is suspected of being out of date. Triggers are recap [skill], what does [skill] do, audit [skill] description, summarize [skill]. Don't use for rewriting the artifact — that's ai-forge-update.

0
installs
▌
AI Forge Create · robcsaszar bundle
Create a new skill (SKILL.md), agent definition, or instruction file. Use when converting ad-hoc knowledge into a reusable skill, scaffolding an agent for Claude Code, GitHub Copilot, OpenAI Codex, or Google Gemini, or creating instruction files for glob-pattern matching. Don't use for updating existing artifacts — use ai-forge-update for that. Triggers are create a skill, write a skill, new skill, SKILL.md, build a skill, create an agent, new agent, scaffold an agent.

0
installs
▌
AI Forge Review · robcsaszar bundle
Critically reviews and stress-tests agent, skill, and AI workflow definitions before they ship. Use whenever someone creates, modifies, or proposes an agent config, skill file, system prompt, or AI-powered workflow — including 'review this agent', 'check this skill', 'is this agent safe', or any request for feedback on an AI/LLM integration. Also trigger when someone mentions creating a new agent or skill, even before it is written — help them think before they build. Don't use for rubric scoring — that's ai-forge-judge.

0
installs
▌
AI Forge Update · robcsaszar bundle
Revise an existing SKILL.md or agent definition. Use when an existing skill or agent needs revision, modification, or improvement — including when it misfires, triggers too broadly or too rarely, or has drifted from what its description claims. Don't use for creating new artifacts — use ai-forge-create for that. Triggers are update/modify/revise/change this skill, edit SKILL.md, improve a skill, update this agent, this skill misfires, tighten this agent's scope.

0
installs
▌
Meridian · robcsaszar bundle
Plans a body of work into a durable decision map — a plans/ file by default, or a configured issue tracker — and a route of tracer-bullet tickets. Use whenever the user wants to plan something out — a feature or bug that needs scoping before code, an idea too vague to act on, a wish to brainstorm directions, or a feeling of being stuck in obvious ideas — even if they don't ask for a formal plan. Also use to chart a new map or, once its frontier is empty, to write its spec and route. Trigger phrases — plan this out, help planning, let's brainstorm, scope this, break this down, turn this idea into a plan, roadmap this, chart the route, to spec, to tickets. Don't use for working or implementing a ticket on an existing map (transit), naming or wording brainstorms, personal or event logistics, tasks the user mainly wants done now, a quick sketch of a small in-session change, auditing existing code (crucible), interrogating shipped work (socratic), or reviewing how the session was conducted (retrospective).

0
installs

13 published skills