Pi Result Handling
agents365-ai/365-skillsWhen an AI agent uses a Pi helper to review code, the results need to be shown clearly. This skill tells you how to present those results. You keep the helper's verdict, summary, and findings. You put findings in order of severity.
If the helper found no issues, you say that clearly. If the helper made edits, you list the touched files. For a failed Pi run, you do not try to fix things. You just report the failure.
The most important rule is to stop after showing review findings. You must ask the user which issues to fix. You cannot make any code changes without asking. This stops mistakes and keeps the user in control.
Add Pi Result Handling skill to your workflow
Global
mkdir -p ~/.claude/skills/pi-result-handlingProject
mkdir -p .claude/skills/pi-result-handlingSource Repository
More Code Review & Quality Claude Code Skills
Improve Codebase Architecturemattpocock/skills
Scan your codebase for architecture improvements with visual reports and pick one to refactor
Web Design Guidelinesvercel-labs/agent-skills
Review your UI code for compliance with web interface guidelines
Caveman Reviewjuliusbrussee/caveman
Ultra-compressed one-line code review comments that cut noise
Zoom Outmattpocock/skills
Get a big picture view of your code with a simple map of modules and callers
Codebase Designmattpocock/skills
Create deep modules with tiny interfaces and lots of hidden logic for testability
Requesting Code Reviewobra/superpowers
Catch code issues early with focused automated reviews before every merge
Request Refactor Planmattpocock/skills
Plan safe code refactors with tiny commits and clear GitHub issues
Receiving Code Reviewobra/superpowers
Think first, then code. Verify feedback before making changes. Stay objective