Pi Result Handling

by agents365-aibc55bf9869f3No license81 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 5 days ago

Internal guidance for presenting Pi helper output back to the user

Instructions onlyAI & Agents
AI-generated overview

Guides how an agent presents Pi helper output, preserving verdicts, findings, evidence boundaries and next steps.

What it does
This skill provides internal, non-user-invocable guidance for relaying output from a Pi helper back to the user. It specifies preserving the helper's verdict, summary, findings and next steps structure, ordering review findings by severity, and keeping file paths, line numbers and evidence boundaries exactly as reported. It also covers reporting failed or malformed Pi runs, noting edits and touched files, and directing users to setup when required.
When to use it
Use it when an agent has received output from a Pi helper and needs to present that output to the user. It applies to review results, failed or incomplete runs, malformed output, and cases where Pi setup is missing.
Requirements
No scripts or tools are required; it is instructions only. It assumes a Pi helper and, for setup cases, a pi binary and configured provider.

Pi Result Handling

When the helper returns Pi output:

  • Preserve the helper's verdict, summary, findings, and next steps structure.
  • For review output, present findings first and keep them ordered by severity.
  • Use the file paths and line numbers exactly as the helper reports them.
  • Preserve evidence boundaries. If Pi marked something as an inference, uncertainty, or follow-up question, keep that distinction.
  • Preserve output sections when the prompt asked for them, such as observed facts, inferences, open questions, touched files, or next steps.
  • If there are no findings, say that explicitly and keep the residual-risk note brief.
  • If Pi made edits, say so explicitly and list the touched files when the helper provides them.
  • For pi:pi-companion-forwarder, do not turn a failed or incomplete Pi run into a Claude-side implementation attempt. Report the failure and stop.
  • For pi:pi-companion-forwarder, if Pi was never successfully invoked, do not generate a substitute answer at all.
  • CRITICAL: After presenting review findings, STOP. Do not make any code changes. Do not fix any issues. You MUST explicitly ask the user which issues, if any, they want fixed before touching a single file. Auto-applying fixes from a review is strictly forbidden, even if the fix is obvious.
  • If the helper reports malformed output or a failed Pi run, include the most actionable stderr lines and stop there instead of guessing.
  • If the helper reports that setup is required (pi binary missing, no provider configured), direct the user to /pi:setup and do not improvise alternate flows.

Source and attribution

Source:agents365-ai/365-skillsinplugins/pi-plugin-cc/skills/pi-result-handlingat commitbc55bf9

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal