Address an MLX Vulkan Issue
SkillDev toolsInvestigate and address a `goniz/mlx-vulkan` GitHub issue in the MLX submodule. Use when given an issue number and asked to read the issue, plan the work, reproduce a reported bug, implement the scoped fix, and work from an MLX feature branch based on `goniz/mlx:feat/vulkan`.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Address an MLX Vulkan Issue skill
What this skill tells your AI
The instructions your AI receives, as published by goniz/mlx-vulkan in .agents/skills/mlx-issue/SKILL.md and read by ahel’s review.
Use the supplied issue number to inspect goniz/mlx-vulkan. Work on a feature branch inside mlx/ that tracks goniz/mlx:feat/vulkan; do not create implementation changes outside the allowed Vulkan backend scope unless the user explicitly expands it.
- Read the issue with
gh issue view <number> --repo goniz/mlx-vulkan. - Create and maintain a concise plan with
update_plan; update it as work completes. - Inspect the submodule status and create a feature branch based on the
goniz/mlx:feat/vulkanbranch. - For a bug report, reproduce it before modifying implementation. Record the reproduction command and result.
- Execute the planned investigation and implementation. Keep Vulkan work async and GPU-native; prefer
NYIto pipeline-breaking CPU fallback. - Verify proportionately with
./dev.shcommands. Run./dev.sh generateafter Vulkan implementation changes.
Report the issue, plan outcome, branch, reproduction result, changes, and verification. Do not create a PR unless the user asks.
Signals
- GitHub stars
- 38
- Forks
- 5
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
mlx-issue- Source
- github.com/goniz/mlx-vulkan