Skip to content

t1k:minimax-design

FieldValue
Modulet1k-multimodal
Version2.10.46
Effortmedium
ToolsBash, Glob, Grep, Read, Write

Keywords: game art generation, game asset generation, generate image with minimax, icon set generation, image generation mcp, mcp minimax, minimax design, minimax-design, transparent background image, ui asset generation

/t1k:minimax-design
<what to generate> [project] — generation, batch, reskin, troubleshoot

MiniMax Design MCP — image generation for game art and UI

Section titled “MiniMax Design MCP — image generation for game art and UI”

minimax-design is an MCP server that drives the MiniMax Design desktop app: it generates images into a project the user has open, bills credits to the account signed in to that app, and saves every result as a version inside the project. This skill is the tool procedure. Project conventions (which folder an art style lives in, a particular game’s naming) belong in project memory, not here.

Executed by whichever session actually holds the mcp__minimax-design__* tools. Whether that includes a sub-agent depends on how the server is registered: when it is registered at user scope, Claude Code lists the namespace in each spawned sub-agent’s own tool set, and a sub-agent can run a generation lane (measured on Claude Code 2.1.316: six general-purpose agents at spawnDepth: 1, 222 MiniMax tool calls, every agent finished: true; the is_error results in that sample were ToolSearch probes, not generation calls). When the connection belongs to one session only, the tools are absent from the child and the lane has to run inline. Do not assume either direction: probe with one read-only call (list_projects) in the child before handing it a batch, and fall back to inline if the namespace is missing. Contact-sheet review (step 5) stays delegated through the router vision role either way.

Every execute call bills. Never resubmit a task — poll it with task_wait on the SAME taskId. Never call confirm_cost on your own behalf: the cost prompt belongs to the user in the MiniMax app, and confirm_cost may be called only after the user explicitly agreed to that amount in the conversation. State a credit estimate and smoke-test before any batch.

IntentRead
“Generate an icon / asset / UI screen”Steps 1–6 below
Batch, level sets, reskinned screens, prompt craft, local resize, Figma uploadreferences/production-playbook.md
Exact tool arguments, execute/deliver/get_output payload shapes, error codesreferences/tool-reference.md
Something failed (PROJECT_NOT_OPEN, OUTPUT_UNAVAILABLE, INVALID_ARGUMENT)Gotchas table below

The tools are DEFERRED: load their schemas first, or every call fails with InputValidationError.

ToolSearch select:mcp__minimax-design__list_projects,mcp__minimax-design__open_project,...

If they are missing entirely right after the server was registered, the tool list was snapshotted at session start — reconnect (/mcp) or restart before trying again. The endpoint/port is machine-specific: check claude mcp list, never assume one.

  1. Find the project. list_projects returns projectId, name, folderPath and an open flag. Only a project with open: true is usable. Never guess between similar names (two near-identically named projects, one open): pick the open one and say which you picked. open_project(projectId) switches; calling it again switches again.
  2. Reuse before generating. composition_search browses what the project already holds and composition_get lists members with their resourceId/currentVersionId. Generate only what is genuinely missing; imported references are billed on every task that carries them (see Costs).
  3. Read the parameters once. capability_list(kind="media", operation="generate_image") lists models; capability_get(ids=[...]) returns each one’s paramSchema. Default model unless the user names another: generate_image:gpt-image-2.5-sunburst (supports transparent background). Every other model is “use only when explicitly requested”.
  4. Import approved style references. deliver is synchronous and unbilled; it turns local files into resourceIds you can pass as references. The path MUST be a regular file inside the project’s folderPath — copy it into a subfolder of the project first. Import once, reuse the ids.
  5. Smoke, then look. Generate 3–4 images covering the hard cases (lowest and highest of a level set, an odd aspect ratio, one other colour). Then review them the way a human would: build a contact sheet and run the vision role (bun <claudeDir>/scripts/mr-role.cjs call --role vision --file <sheet> --prompt "..."). Show the user and stop for approval before scaling.
  6. Batch in waves, costed. State the estimate before a batch of more than ~10 images or more than ~2 minutes, and re-check visually between waves — never spend the next wave on unverified output. Multi-level sets and reskins: references/production-playbook.md.
  7. Finish locally, then deliver. The model cannot take pixel sizes (see Parameters), so resize or pad on disk, verify with a final contact sheet, and only then hand off. Results already live inside the project; get_output(versionId) returns their absolute local path. Getting them into Figma is a separate hand-off: references/production-playbook.md § Figma.
KeyValuesNotes
aspect_ratio1:1, 16:9, 9:16, 3:4, 4:3, 3:2, 2:3, 5:4, 4:5, 21:9, 2:1, 1:2, 3:1, 1:3Required when there are no image references; with references it inherits the nearest ratio of the FIRST reference if omitted
resolution1k | 2k | 4k (default 2k)A tier above the default costs more and needs the user to have asked for it
qualitylow | medium | high | xhigh | max (default high)low garbles small UI text — raise only with user approval
backgroundauto | transparent | opaqueTransparent is what game assets usually need

prompt is ≤ 7500 chars and describes one finished result; count (1–9) is only for variations of the SAME prompt. Up to 16 image references, ordered — the prompt can address “FIRST reference image” / “LAST reference image”.

There are no pixel sizes. A request is a ratio plus a 1k/2k/4k tier (1:1 at 1k returned 1024×1024; 9:16 at 1k returned a ~576×1024-class portrait). To hit an exact game-asset size, generate the nearest ratio and crop/pad/resize locally. An aspect the model cannot express (a 4.5:1 slot when the widest ratio is 3:1) means keeping proportions and leaving transparent margins, or stretching — say which one you did.

Costs (observed, gpt-image-2.5-sunburst at 1k / quality low)

Section titled “Costs (observed, gpt-image-2.5-sunburst at 1k / quality low)”

No references: 20 credits per image. 3 references: 50. 4: 60. 5: 70. References raise the price, so import once and reuse. At ~60 credits/image no confirmation prompt appeared in the observing session — the trigger threshold is UNVERIFIED, so never assume a batch is cheap. execute reports billing.estimatedCredits per task.

Independent execute calls may be sent together (13–15 at once was observed working); some return status: "completed" immediately, the rest status: "running". For a running task, call task_wait(taskId) with that same taskId until it completes — never resubmit, which starts and bills new work. Queue waits of several minutes are normal at 13+ parallel tasks; one task sat provider_queued for ~15 minutes and still completed.

SymptomCauseFix
PROJECT_NOT_OPENThe project is not open in the MiniMax Design appAsk the user to open it, retry open_project
Tools missing right after registering the serverThe tool list is snapshotted at session startReconnect (/mcp) or restart the session
INVALID_ARGUMENT … inside the workspace on deliverThe path is outside the project folderCopy the file into a subfolder of the project, then deliver from there
OUTPUT_UNAVAILABLE on get_outputA user-created version with no readable content (not on disk)Ask the user to re-upload or save it into the project folder; never invent its content
running after executeProvider queuetask_wait the same taskId; never resubmit
Image is 1024×1024 for a 129×129 slotThe model has no pixel sizesResize/crop locally
Small UI labels come out wrongquality: lowRaise the tier only with the user’s approval
Generated light rays / borders turn to noise at small sizesFine detail below the target resolutionAsk for “no sharp jagged rays” / a very thick border, regenerate that one image

Image and media generation inside a MiniMax Design project, through the minimax-design MCP server. Refuses: hardcoded project ids, ports, or credentials; writing into the user’s existing Figma frames; and any spend the user has not agreed to. Project-specific conventions (game folders, art style, naming) belong in project memory — do not add them here.

Lessons that outlive this page go to the gotcha ledger under skills/t1k-rsi/ledger/gotchas/ (as t1k-minimax-design.md once one is recorded) via a [t1k:lesson] marker; a wrong step in this skill itself is a [t1k:skill-bug].

  • references/tool-reference.md — exact tool payloads and error codes
  • references/production-playbook.md — smoke/wave batching, level progression, reskins, local resize, vision QA, Figma hand-off
  • modules/t1k-multimodal/rules/image-analysis-routing.md — why image review goes through the router vision role
  • skills/t1k-mcp-management/SKILL.md — installing, inspecting and guarding MCP servers