From gemini
Presents Gemini helper output back to the user, handling review findings, general delegation, errors, and empty responses with specific formatting rules from the rescue subagent.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gemini:gemini-result-handlingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When the helper returns Gemini output:
When the helper returns Gemini output:
Handling empty output and failures:
Gemini did not return a final message., surface that line plainly to the user. Do not invent a replacement answer. Suggest a retry or /gemini:status if the task was substantive.{"status":"error","message":"...","stderr":"..."} or a line beginning with Gemini companion failed:), report the error message and the most actionable stderr lines verbatim, then stop. Do not attempt to execute the task yourself.gemini:gemini-rescue, do not turn a failed or incomplete Gemini run into a Claude-side implementation attempt. Report the failure and stop.gemini:gemini-rescue, if Gemini was never successfully invoked, do not generate a substitute answer at all./gemini:setup and do not improvise alternate auth flows.Review-specific safety:
/gemini:rescue output that happens to contain code suggestions, follow normal delegation-output handling — surface what Gemini produced and let the user decide what to do next.npx claudepluginhub m-ghalib/gemini-plugin-cc --plugin geminiInternal guidance for presenting Gemini 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.
Delegates tasks to Gemini CLI for large-context analysis like broad codebase reviews or long-document processing. Activates on explicit requests such as 'use gemini' or 'delegate to gemini'.