From pi
Presents Pi helper output back to the user, preserving verdict, findings, and next steps. For reviews, stops after presenting findings and asks user which issues to fix.
How this skill is triggered — by the user, by Claude, or both
Slash command
/pi:pi-result-handlingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When the helper returns Pi output:
When the helper returns Pi output:
pi:pi-rescue, do not turn a failed or incomplete Pi run into a Claude-side implementation attempt. Report the failure and stop.pi:pi-rescue, if Pi was never successfully invoked, do not generate a substitute answer at all./pi:setup and do not improvise alternate flows.npx claudepluginhub agents365-ai/pi-plugin-cc --plugin piInternal guidance for presenting Copilot helper output back to the user
Presents Codex helper outputs per strict rules: preserves structure/verdict/findings/next-steps, orders by severity, forbids auto-fixes or code changes.
Presents structured output from multi:* helper tools (Cursor, Gemini, Copilot, etc.) preserving verdict, summary, findings, and next-steps sections. Handles messy interleaved output and failed runs.