site banner

Tinker Tuesday for July 14th, 2026

This thread is for anyone working on personal projects to share their progress, and hold themselves somewhat accountable to a group of peers.

Post your project, your progress from last week, and what you hope to accomplish this week.

If you want to be pinged with a reminder asking about your project, let me know, and I'll harass you each week until you cancel the service.

1
Jump in the discussion.

No email address required.

GPT5.6 Sol is something ... I needed a simple 3d printer leather belt skiver jig. The bastard two shotted it.

If you are into 3d printing the models are quite good at creating functional prints.

Can you describe the whole process? Did you upload an image with dimensions? Did you verbally describe what you wanted? I'm not at all sure what the work flow looks like.

I have ocp viewer opened in VSCode, and I have also opened a folder with venv. It also has access to freecad and couple of other python libraries.

› Here is totally unrelated problem for you. I need a 3d printing jig for skiving leather strip - up to 30mm wide. It may use standard utility or box cutter blade. The goal is leather thickness of 2.3 mm. You may use additional imbus bolts and nuts for clamping or so. It should be easy to print sturdy and safe.

It generated a solid first design. and send it to the viewer. from there I just sent one or two more prompts to make the clamps better - it had forgotten some features, there was stuff that was impossible to print, but nothing drastic.

Those are the following prompts

I like it but the clamping mechanism is a bit off. Looks weak between the layers, the holes for the both is unaligned with the hex nut - probably you didn't do the right trigonometry because of the slant, and doesn't looks secure - looks like it is prone to snapping.

Is there a cutout for the bolt head - if you want you can make the end clamps upper end, paralel to the main plane. with a proper cutout. we will still have the slanted clamp but mounting will be more secure.

It's final answer


Reworked the blade seat to eliminate the unprintable parallelogram slots.

The blade now:

  • Drops onto two completely open sloped ramps from above.
  • Has no enclosed gaps or trapped support cavities.
  • Is supported beneath both ends, outside the leather path.
  • Registers against small open lips integrated into the removable clamps.
  • Has its sharp ends covered when the clamps are installed.

I also moved the exit guide behind the complete raised blade envelope, removing another hidden intersection previously carved out by the slot.

Validation confirms one valid base solid, zero blade-seat obstruction, and an unobstructed 30 × 2.3 mm path. Updated files were regenerated and sent to OCP port 3939. Changes remain uncommitted for inspection


Everything else - proper positioning and depth of nut, holes, the guiding rails for the leather the whole size of the object, the mounting holes so that it could be bolted to a worktable and a few other unasked for but proper features were all its idea.