Stats
Actions
Tags
From gemini
Internal guidance for composing Gemini prompts for coding, review, diagnosis, and research tasks
How this skill is triggered — by the user, by Claude, or both
Slash command
/gemini:gemini-promptingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Prompt as operator, not collaborator. Give Gemini a concrete task, expected output shape, and follow-through defaults.
Prompt as operator, not collaborator. Give Gemini a concrete task, expected output shape, and follow-through defaults.
<task>: Concrete job and expected end state<structured_output_contract>: Output shape (JSON schema reference)<compact_output_contract>: Concise prose format<grounding_rules>: Ground claims in context<action_safety>: Keep changes scoped/gemini:review or /gemini:adversarial-review for reviewing git changes.task for diagnosis, planning, research, or implementation with custom prompts.| Model | Best for |
|---|---|
auto | General tasks (default) |
pro | Complex reasoning, long context |
flash | Fast tasks, shorter context |
flash-lite | Quick lookups, minimal cost |
<task>npx claudepluginhub rsecss/gemini-plugin-cc --plugin geminiCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.