blender-arwaky
Skill0 starsChanged 5 days agoMITView on GitHub
Blender asset search, GLB import/export, scene assembly, and rendering via MCP or CLI.
In this repository75 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/skill-authoring/tools/AGENTS.mdAGENTS.md
- aes-docsSkill
- aes-fixSkill
- aes-layerSkill
- aes-migrationSkill
- android-emulator-linux-gpsSkill
- computer-useSkill
- flatpak-chromium-automationSkill
- qwen-webSkill
- grok-buildSkill
- hermes-agentSkill
- omnirouteSkill
- orcaSkill
- account-managerSkill
- brave-setupSkill
- password-managerSkill
- codegraphSkill
- deep-cleanSkill
- dogfoodSkill
- reviewSkill
- systematic-debuggingSkill
- comfyuiSkill
- llm-writingSkill
- vision-arwakySkill
- playwright-toolingSkill
- setup-ci-quality-gatesSkill
- statuslineSkill
- systemd-headless-serviceSkill
- xdg-spec-complianceSkill
- figcraft-builderSkill
- figcraft-iconsSkill
- figcraft-motionSkill
- figcraft-prototyperSkill
- figcraft-reviewSkill
- figcraftSkill
- figcraft-svgSkill
- figcraft-typographySkill
- github-authSkill
- issue-makerSkill
- issue-workerSkill
- mergifySkill
- pr-babysitSkill
- releasingSkill
- repo-managerSkill
- ascii-artSkill
- ascii-videoSkill
- gif-searchSkill
- media-acquisitionSkill
- docxSkill
- emailSkill
- google-workspaceSkill
- notionSkill
- pdfSkill
- pptxSkill
- xlsxSkill
- competitor-news-monitorSkill
- product-price-monitorSkill
- weekly-review-planningSkill
- arxivSkill
- The first 60 shown.
The file
Files
BlenderArwaky
You script Blender through the BlenderArwaky toolkit: CLI sub-commands or the
MCP execute_command(action=..., args=...) surface, which dispatches every
action (scene, object, viewport, render, io, job, config, code).
Global Rules
- Two entry surfaces. CLI exposes every action as a direct sub-command;
MCP routes all actions through one
execute_commandtool — theactionparameter selects the feature. Five MCP tools:execute_command,list_commands,health_check,get_config,help. - Commands. The full CLI↔MCP mapping, parameter tables, and screenshot
parameters:
references/commands.md. - Add-on. TCP server on port 9876; auto-starts on Blender load (30 retries × 2s); headless mode requires an active camera for screenshots.
- Workflows. Scene discovery, object creation/transform, viewport
analysis, asset import/place, render + task status, and custom bpy code:
references/workflows.md. - Troubleshooting. Connection refused, missing active camera, MCP
server won't start, tools not showing up:
references/troubleshooting.md. - Completion.
health_checkreports a live Blender connection and the requested action returned the expected result.
Routing
| Step | Reference | Purpose |
| Commands | references/commands.md | Every CLI sub-command and MCP action, with parameter tables, screenshot parameters, and the five MCP tools. |
| Workflows | references/workflows.md | Scene discovery, object creation/position, viewport analysis, asset import, render/status, custom code. |
| Add-on & Troubleshooting | references/troubleshooting.md | Blender add-on architecture, port/timeout details, and fixes for the common failure modes. |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.