Probably the most impressive output I received from this skill:
A street light with adjustable pole height and light distribution.
You're able to see the light move between the road, the houses and the sky.
Things get interesting when the LUX map gets turned on.
Six projects from the last few weeks that caught our attention:
A wildfire analysis prototype that maps the fire’s spread over time and tracks hot spots, made with Opus 5.5.
AN OPEN-SOURCE DEV JUST BUILT A FREE LIBRARY OF PRO MOTION DESIGN. NOW YOU CAN MAKE ANY VIDEO IN THIS STYLE YOURSELF.
Every video was built with Claude Opus 5.5. The prompt that made it sits right under it.
How it works:
→ Find a video you like
→ Copy the prompt
→ Swap the text and colors
→ Hand it to your agent
Got a brand book? Drop it in and the video builds in your colors.
The real trick: I sent Claude a sample video with my rough edits and text. It fixed everything and rebuilt it in the reference style.
Free library: https://t.co/1p9mMkg70U
indie studios, hello
how i add fishing to my cozy farm game with Opus 5.5
the trick is adding one new verb per zone. this zone's verb is fishing:
step 1 -> Claude Code drives Unity 6 via unity-mcp, Blender via blender-mcp
step 2 -> village as a new scene, farm HUD carried over as one prefab
step 3 -> Tripo for the set: pier, lighthouse, 4 boats, crab traps, fish stall
step 4 -> Opus rigs the cast in Blender and builds the water with URP shaders
step 5 -> fishing as one system: cast, tension bar, catch card, coins
step 6 -> 12 fish species in a sheet, Opus balances rarity and prices before code
step 7 -> ElevenLabs for splashes, gulls, reel clicks. Cinemachine follows the player
who does what:
> tripo: every new model
> unity 6: scenes, water, lighting
> opus 5.5: c# scripts, rigging, the fish economy
> you: fish until it feels right
one new zone, one new verb. the farm plays the same, the island just got bigger
next zone: the mine or the forest?
Now that AI can use Blender, I’m seeing more people use high-fidelity 3D to drive AI video.
IMO, that’s a bad idea if you want realism. Lower-fidelity input lets the model translate your intent better.
No MCP or outside grading app involved. Claude worked in a cloud workspace with Python and ffmpeg. It pulled frames from the video and looked at them, found every cut (19 shots) and measured each shot’s exposure and color. Then it wrote the grade as code: a per-shot balance plus a filmic Ghibli-style look, baked into 3D LUTs. It rendered the final 4K with bloom, vignette and fine grain added. No DaVinci, no plugins, just code. It even exported a .cube LUT I can reuse in Resolve.