AGENT SKILL

art

Make game and app art using the official fal MCP, studio art direction, local capture and asset checks.

License 许可
Apache-2.0
最近更新
2026-11-14
Stars
★ 1.6k
Forks
491

01 前言 Front Matter

name
art
metadata
{ "providers": "fal" }
description
Make game and app art using the official fal MCP, studio art direction, local capture and asset checks.
compatibility
Node 22 and the official fal plugin in the AI client. Local media processing uses ffmpeg and Chrome where needed.

02 资源文件 3

03 SKILL.md 正文

Art for this studio

Read the game's or app's style, codex and existing scene before writing a prompt. Use its palette, shape language, materials, lighting and camera. Keep approved references and the style revision. Covers must describe what the playable experience really offers. A frame from the running game is free and often the best cover.

For generated art use fal's recommend_model or search_models, get_model_schema and get_pricing, then run_model. Continue a pending request with check_job and get_job_result. Use upload_file only as documented by the official plugin for references. Set an explicit image count. Inspect the first result before any dependent generation.

Local scripts/art.mjs keeps check, frame, cover, tile, fit and sheet. Use cover <game> --from <image> for a 1600×900 cover and game.json reference; fit <image> --out <file> for phone-sized delivery. Check tile seams with a repeated 2×2 preview, transparency against light and dark, readability at phone size, and compression after fitting. Do not replace an engine effect with a large image by default.

Official generation workflow

The owner's AI uses the provider's official plugin/MCP in its own client. Homie never asks for, stores, reads or prints provider credentials. Read the current provider skill and discover its available tools and input schemas; host prefixes vary. Connection instructions and verified sources: official integrations. If tools are missing, connect that official plugin once in the client's browser flow. Do not fall back to a Homie client, key file, environment key or CLI generation wrapper.

Before spending, state the model, count/duration, estimated cost and remaining approved budget. Use the owner's existing authorization; ask only if the spend is outside it. Record the request ID as soon as accepted. Poll that same request; never resubmit to retry a slow job. Unknown cost is unknown, never zero. Provider billing is authoritative; Homie's local receipt cannot enforce spending in another client.

Place and prove the result

Download the completed tool's output using the AI client's file/download facilities. Keep temporary signed URLs out of committed records. Keep the original in the studio's art/job folder; put the optimized delivered asset beside its game/app, or in music/ or videos/ for a published work. Record a receipt with these fields:

{
  "provider": "fal",
  "tool": "run_model",
  "model": "exact endpoint returned by the provider",
  "requestId": "actual request ID",
  "prompt": "the actual prompt, including style constraints",
  "styleRevision": "revision from the studio's style",
  "rights": {"source": "provider/model terms URL", "checkedAt": "YYYY-MM-DD", "commercial": false, "note": "record the actual plan and permitted use"},
  "cost": {"status": "unknown"}
}

For ElevenLabs use its actual discovered tool and model, and its flow/session or request identifier. A measured cost uses {"status":"actual","amount":1,"unit":"credits"}; a quote uses estimate. Never claim commercial rights from the fact that generation succeeded. Read the provider and model terms for the account's plan; record attribution, reference-image permissions and any restrictions. Mark test fixtures "fixture": true.

Wire the delivered path into the scene or manifest, then run:

npx --no-install homie-studio media import --file <downloaded-file> --receipt <receipt.json> --out games/<id>/assets/<name> --used-by games/<id>/view.ts

This copies bytes, verifies a static reference, hashes the asset and records allowlisted provenance in media/provenance.json. Reimporting the same output is idempotent; it never generates or charges. Include each generation step's receipt for derived assets. Run the scene and look/listen: a file and static reference are not proof that it renders or plays. Report the placed path, usage evidence, rights and actual/estimated cost.

The toolkit’s lib/media-workflows.mjs declares this skill’s verified tool references. Validate them against the host’s current tool inventory before execution; tool discovery is required for generation capabilities that have no stable documented name.

04 同仓库更多 Skills

hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-review-with-annotations

Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-find-and-synthesize-context

Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-update-docs

Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-manage-records

Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-manage-interactive-html

Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-collaborate-threads

Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.

★ 1.6k