NVIDIA / NVIDIA/TensorRT-LLM

[auto-dev]: Auto discovery of auto-dev skills

Open
#15,218 0 comments 0 reactions 1 assignee View on GitHub

Nobody has claimed this yet.

AutoDeploy feature request
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

🚀 The feature, motivation and pitch

auto-dev skills were added in https://gitlab-master.nvidia.com/autodeploy/auto-dev/-/merge_requests/42
The skills are positioned as part of the repository, and aren't automatically discoverable by agents.
Resolve this to allow auto-discovery.

Main alternatives:

  1. Register as auto-dev claude/codex plugin - standardized mechanism
  2. Symlink to user's main skill dir on auto-dev install (see draft here: https://gitlab-master.nvidia.com/autodeploy/auto-dev/-/merge_requests/42/diffs?commit_id=4a7f99bdfea7977f1c7ab3d88d117b77cece5f81)

Considerations:

  1. Agent-agnostic, minimally discoverable by both claude and codex
  2. Skills auto-update along with auto-dev
  3. Automatic installation - users use various clusters, we don't want an additional manual setup step
  4. Easy maintenance - skills are expected to be updated regularly with auto-dev
Alternatives

No response

Additional context

No response

Before submitting a new issue...
  • Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.