Three shifts in your day.
You stop waiting for an engineer
Prototype-grade Blueprints, scene tweaks, and data changes no longer queue behind engineering. You direct; Claude builds; engineering hardens what survives playtest.
Iteration count explodes
When a layout variation costs one sentence instead of one afternoon, you try eight ideas instead of two. More reps is the whole job — Claude buys you reps.
The spreadsheet fights back
Balance data stops being a wall of numbers. Ask what happens to time-to-kill if armor scales differently, and get the curve, the outliers, and the edited table back.
The playbooks you'll use most.
You don't need to write a line of code to use any of these. Talk to Claude the way you'd brief a very fast level scripter who never mishears you.
Browse all Design skills in the Library →
The workhorse. Through the Unreal MCP, Claude spawns, moves, and arranges actors, edits properties in bulk, queries the scene ("list every enemy spawn point in this map and its patrol route"), and runs console commands — with our project's folder rules and actor conventions baked in.
Blockouts, set-dressing passes, mass tweaks, spawn-point audits: things that used to be an afternoon of clicking are now a paragraph of intent.
Claude reads and builds Blueprint graphs through the MCP, following our conventions so your prototypes are legible to engineering instead of spaghetti. It also knows our BP-vs-C++ boundary — so when your prototype proves out, the handoff to native code is a request, not a rewrite negotiation.
After any change, Claude launches PIE, exercises the thing it just built, watches the log, and screenshots the result. You start your playtest from "it runs" instead of "does it run?"
Our data tables and curve assets, read and edited safely. Claude models the downstream effects of a tuning change before making it — damage curves, economy flow, progression pacing — then applies it across every affected row instead of you hand-editing forty cells.
Checks your levels and content against studio rules — naming, folder placement, missing references, actors that will break the cook. Run it before you submit and your changelists stop bouncing.
Docs, narrative, and the thinking work.
Design docs that stay current
Talk through a mechanic for ten minutes; get a structured one-pager back. Better: after the mechanic changes in-engine, ask Claude to diff the doc against what's actually built and update it. Docs stop lying.
Narrative & barks at volume
First-pass ambient dialogue, item descriptions, and lore variants in the game's established voice — generated in batches, curated by you. You stay the author; Claude is the writers' room that never runs dry.
Reference & research
"How do the best roguelites handle meta-progression pacing? Give me the patterns, the outliers, and what would fit HEX." A structured competitive teardown in minutes, not a weekend of YouTube.
Playtest synthesis
Dump raw playtest notes, survey exports, and session recordings' transcripts on Claude; get back themes, severity, and the three changes most likely to move the fun. Signal from noise, same day.
Your conventions belong in the skills.
If you find yourself correcting Claude twice about the same thing — metrics, naming, "we never place ammo in boss arenas" — that's not a prompt fix, that's a skill update. Say: "add this rule to editor-ops and open a PR." Every designer's Claude learns it at once. See exactly how →
Connect the tools you already work in.
Same idea as the Unreal MCP on the Setup page — a live wire between Claude and a tool you already use, instead of a written playbook. These five matter most for design work. The studio's full, verified list lives on the Connections page.
Notion
OfficialIf our GDDs live in Notion, Claude reads and updates them directly — which is what keeps a design doc current instead of six weeks stale.
First time only: open each page you want visible → ••• → Add connections → select Claude.
Figma
OfficialHUD and menu mockups, UI flow wireframes. Claude reads the file's real structure, not a screenshot of it.
Needs Dev Mode enabled on the file.
PostHog
OfficialThe other half of balance-data. Instead of tuning a data table on instinct, ask where players actually fall off — then tune it and watch the funnel move.
Only relevant if we're sending telemetry to PostHog — check with production first.
Airtable
OfficialItem tables, quest lists, dialogue trees — with real relational structure instead of a flat sheet nobody trusts.
Then /mcp → sign in, or use a Personal Access Token.
ElevenLabs
OfficialHear a bark or an item description read aloud before there's a VO budget. Cheap way to find out a line doesn't land.
Key at elevenlabs.io/app/settings/api-keys. Personal key — always add with -s user.
Nine more, including Miro, Blender, Linear, and research.
Whiteboards, 3D blockout, trackers, and web research all have verified connectors too — plus the ones that need IT to provision them, and the four we deliberately recommend against. It's all on one page, filterable by department, with a trust level on every card. Open the Connections library →