If you're tired of clicking through the same permission prompts over and over, this analyzes your approval patterns and generates alwaysAllow and alwaysDeny rules to cut down the noise. It scans your session data to identify safe read-only operations like file reads and git status that can be auto-approved, flags destructive commands like rm -rf and git push --force for auto-deny, and leaves the risky-but-necessary stuff like commits in ask mode. The workflow is straightforward: it checks your current .claude/settings.json, categorizes operations by risk level, then presents a JSON snippet you can review before applying. Best used after a session where you approved the same operations repeatedly or when starting a new project.
npx -y skills add rohitg00/pro-workflow --skill permission-tuner --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
rohitg00/pro-workflow
supercent-io/skills-template