[Feature]: Workspace prep #2276
Description
Prerequisites
- I will write this issue in English (see our Language Policy)
- I have searched existing issues and discussions to avoid duplicates
- This feature request is specific to oh-my-opencode (not OpenCode core)
- I have read the documentation or asked an AI coding agent with this project's GitHub URL loaded and couldn't find the answer
Problem Description
Agents can always benefit from best practices for a given project type, language, etc.
However we should go beyond the "agents.md" type practice, to improve protections against sloppy/bad code.
Proposed Solution
One way, in my opinion, is to set up robust CIs, static testing, pre-commit hooks, etc.
So that the relevant testing/verification is ran before every commit, on each pull request and so on.
This should be done via a skill and command, so that the agent interviews on the nature of the project, then proposes best practices and tools, sets them up for the user before the project begins.
Alternatives Considered
No response
Doctor Output (Optional)
Additional Context
No response
Feature Type
New Agent
Contribution
- I'm willing to submit a PR for this feature
- I can help with testing
- I can help with documentation