bama
BAMA: Build Any Mac App. Agent skills to research, clone, design, build, optimize, and test native macOS apps with Swift and SwiftUI.
agent-eval, questionnaire-review and i-have-ocd. They run on your computer. Nothing comes back to me.
SkillsPython · HTMLGitHub @luoy2OnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Agent skills from real engineering work. Starts with agent-eval: evaluate models and thinking effort on the mistakes your own agents made.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Agent skills from my own engineering work, straight from my .claude directory.
They work with Claude Code and Codex.
Two skills learn from your own session history, on your own computer, to help
you work better with Claude Code: agent-eval finds which model and thinking
effort avoid the mistakes your agents actually made, and questionnaire-review
turns the way you answer your agents into rules they follow. The third,
i-have-ocd, keeps the current task focused: consequential findings retain
a responsible owner, and the human sees only unresolved decisions.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
Agent skills from my own engineering work, straight from my .claude directory.
They work with Claude Code and Codex.
Two skills learn from your own session history, on your own computer, to help
you work better with Claude Code: agent-eval finds which model and thinking
effort avoid the mistakes your agents actually made, and questionnaire-review
turns the way you answer your agents into rules they follow. The third,
i-have-ocd, keeps the current task focused: consequential findings retain
a responsible owner, and the human sees only unresolved decisions.Read the full README ↗