Skip to content

arxdsilva/agent-office / .claude/skills/asset-change

asset-change

Verified

Change agent-office's Blender-built 3D assets — the atrium, Main Street, wings and their themes, garden, cap, furniture kit, lighting/bake, the character mesh, rig or animation clips, the manifest or the graphics contract. Use for any edit under assets/ (assets/blender/**, assets/build.mjs, assets/validate*.ts), to docs/graphics-contract.md, or for anything in packages/web/public/assets/.

Change the 3D assets

Rules: SCENE.md (budgets, animation rules, no logos), TESTING.md (asset validation), docs/graphics-contract.md (the contract both sides follow).

  1. Contract first. If anchors, roles, clip names, coordinates or budgets change, edit docs/graphics-contract.md additively and plan the renderer side (packages/web/src/app/manifest.ts and friends) in the same change. Extend the fixture tests in assets/validate.test.ts red-first.
  2. Edit the scripts in assets/blender/** (modules, furniture kit, materials, themes, character). Never edit a .glb by hand or export from the GUI: every shipped file comes from make assets.
  3. Iterate fast: make assets-draft (low bake samples, small lightmaps, gitignored output).
  4. Look at it:
    • With the Blender MCP connected (optional: claude mcp add blender --scope user -- uvx blender-mcp, then Connect in Blender's MCP sidebar), use get_scene_info and viewport screenshots to review proportions, materials and lighting. Use only the Poly Haven integration; leave Hyper3D and Sketchfab off.
    • make asset-previews renders Eevee stills of every module into assets/previews/. Read the images.
  5. Test:
    • make assets-test: Blender-side checks (naming grammar, counts, loop pose continuity, ≤ 4 weights, applied transforms, no text objects except the runtime sign).
    • pnpm vitest run --project unit assets/validate.test.ts: gltf-validator 0 errors, budgets, anchors, nav connectivity, clips, ≤ 45 MB.
  6. Final build: make assets (final bake). Then /run-office and make screenshots to check the assets in the app, and make perf if triangle counts or materials changed (≥ 55 fps at Medium with 150 agents).
  7. License and branding checklist before handing off:
    • Every new texture or HDRI is CC0 (Poly Haven), pinned by asset id and SHA-256, and listed in assets/LICENSES.md with its URL.
    • No logos, trademarks or real company names anywhere (textures, decals, text objects, material names). Wing signs stay blank planes; the runtime draws the provider id.
    • No AI-generated or Sketchfab models.
  8. Git LFS: .glb, lightmap .png and .hdr files under packages/web/public/assets/, plus assets/out/** and assets/previews/**, are LFS files (.gitattributes). Make sure git lfs install has run before the human commits. Prepare the commit commands; never commit yourself.

2D RPG mode: see docs/2d-architecture.md. The pure logic is in web/src/app/pixel/*, the Canvas2D drawing in web/src/adapters/pixel/*, the art in assets/pixel/src (make pixel-assets), and the floor plans come from make assets-plan. Check both modes with pixel.spec.ts and the existing 3D specs.

rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall