Blender Addon Development logo

Blender Addon Development

Community
EL4CTEO
blender-addon-development

Write Blender 5.2 add-ons as extensions - blender_manifest.toml, operators/panels/menus/property groups/preferences, bpy.props rules after 5.0, undo/redo, modal and timer patterns, gpu drawing (no bgl), bundling Python wheels, CLI validate/build/install, testing headless, extensions platform publishing. Use when creating or fixing a Blender add-on, tool, or UI.

Overview

PublisherEL4CTEO
Repositoryblender-skills
Skill nameblender-addon-development
Stars
426
Forks
39
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by EL4CTEO on GitHub. Read the source before you install it.

Installation

Install the Blender Addon Development AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/EL4CTEO/blender-skills/tree/main/skills/blender-addon-development
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/EL4CTEO/blender-skills.git /tmp/blender-skills
mkdir -p .claude/skills
cp -r /tmp/blender-skills/skills/blender-addon-development .claude/skills/blender-addon-development
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Blender Addon Development in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Blender Addon Development on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Blender Addon Development is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Add-on (Extension) Development

The execution model is in blender-core. Start from assets/addon_template/ (validated, built, and registered in CI): blender_manifest.toml, __init__.py, operators.py, ui.py.

Procedure

  1. Copy the template, then set id (lowercase_underscores, permanent), name, tagline (no trailing period, ≤ 64 chars), maintainer, version (semver), license (SPDX, GPL-3.0-or-later for code using bpy), and blender_version_min = "4.2.0" or higher if you use newer APIs (e.g. "5.2.0" for the GN properties.inputs API).
  2. Write classes with the prefix convention MYTOOL_OT_x (operator), _PT_ (panel), _MT_ (menu), _PG_ (property group), _AP_ (preferences), _UL_ (UI list). bl_idname for operators is my_tool.verb_noun.
  3. Validate and build:
    blender --command extension validate ./my_tool
    blender --command extension build --source-dir ./my_tool --output-dir ./dist
    blender --command extension install-file -r user_default -e ./dist/my_tool-1.0.0.zip
  4. Test headless: register the package in-process, call operators with temp_override, and assert on data (see tests/test_addon.py in this repo).

Rules (extension-era, 5.x)

  • Relative imports only (from . import ops). The package name is decided by Blender, so preferences use bl_idname = __package__.
  • No bl_info (it's ignored for extensions). Everything goes in the manifest.
  • No network or file access at import/register time. Declare [permissions] (files, network, clipboard, camera, microphone) with a reason. Check bpy.app.online_access before any network call.
  • Third-party Python packages: ship .whl files in ./wheels/ and list them under wheels = [...]. Never pip install at runtime. Platform-specific wheels require platforms = [...].
  • Properties (5.0+): bpy.props values are attributes, not dict entries (scene["my_prop"] no longer reaches them). For read-only props use options={'READ_ONLY'}. get_transform/set_transform adapt values while keeping storage. Register with PointerProperty(type=PG) on an ID type, and del it on unregister.
  • Operators: bl_options={"REGISTER","UNDO"} for undo plus a redo panel. poll() guards the context. Return {"FINISHED"}/{"CANCELLED"}. self.report({"WARNING"}, msg) for user feedback. Don't call other operators in loops if a data API exists.
  • UI: layout.use_property_split = True gives modern alignment. Panels in the N-panel use bl_region_type="UI" + bl_category. Append menu entries with VIEW3D_MT_*.append(func) and remove them on unregister.
  • Unregister everything in reverse order (classes, props, menus, handlers, timers, keymaps, draw handlers). Leaks break reloading.
  • Drawing (overlays): gpu module + gpu_extras.batch. bgl was removed in 5.0. Textures come from gpu.texture.from_image(img). For scene-linear images use draw_texture_2d(..., is_scene_linear_with_rec709_srgb_target=True).
  • Long tasks: a modal operator with a timer (wm.event_timer_add), or bpy.app.timers.register with chunked work. Never block the UI for seconds.
  • Handlers: decorate persistent ones with @bpy.app.handlers.persistent. Keep them cheap (they run every frame/depsgraph update).
  • Keymaps: add them to wm.keyconfigs.addon, store (km, kmi) pairs, and remove them on unregister.
  • Translations / i18n: bpy.app.translations.register(__package__, dict).

Publishing (extensions.blender.org)

The Blender ID account uploads the built zip. Requirements: a valid manifest, a GPL-compatible license, no obfuscated code, no bundled binaries without source, and permissions declared. Screenshots/README go on the website listing. Update with a higher version.

Gotchas

  • context.scene inside a draw function can be None in some editors. Guard it.
  • Storing Blender data references (bpy.types.ID) in Python globals crashes after undo or file load. Store names or session_uid, and look them up again.
  • bpy.utils.register_class fails if annotations use = instead of : for properties.
  • 5.0 made several bundled modules private (rna_info, bl_ui_utils...). Don't import them.
  • 5.1 no longer loads the user site-packages by default. Bundle wheels instead of relying on user installs.
  • 5.2: PreferencesFilePaths.active_asset_library indices are offset (the "All"/"Essentials" entries come first). UILayout.template_palette(color=) is removed. New: UILayout.link, UILayout.textbox, bpy.data.all_ids, Window.screenshot.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Blender Addon Development AI skill do?

Write Blender 5.2 add-ons as extensions - blender_manifest.toml, operators/panels/menus/property groups/preferences, bpy.props rules after 5.0, undo/redo, modal and timer patterns, gpu drawing (no bgl), bundling Python wheels, CLI validate/build/install, testing headless, extensions platform publishing. Use when creating or fixing a Blender add-on, tool, or UI.

Why use Blender Addon Development on TypingMind?

Because you install it once and use it with any model. Blender Addon Development is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Blender Addon Development in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/EL4CTEO/blender-skills/tree/main/skills/blender-addon-development. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Blender Addon Development?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Blender Addon Development?

As many as you like. As long as a model supports skills, you can use Blender Addon Development with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Blender Addon Development AI skill free?

Yes. It is published on GitHub by EL4CTEO under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇