git:20260526.5be998e to git:20260531.a0f8b0c

---

name: gemini-prompting

description: Internal guidance for composing Gemini and AGY prompts for coding, review, diagnosis, and research tasks inside the Gemini Claude Code plugin

user-invocable: false

---

# Gemini Prompting

Use this skill when `gemini:gemini-rescue` needs to prepare a prompt for Gemini or AGY.

Prompt the model like an operator, not a collaborator. Keep prompts compact and block-structured with XML tags. State the task, the output contract, the follow-through defaults, and the small set of extra constraints that matter.

Core rules:

- Prefer one clear task per run. Split unrelated asks into separate runs.

- Tell the model what done looks like. Do not assume it will infer the desired end state.

- Add explicit grounding and verification rules for any task where unsupported guesses would hurt quality.

- Prefer better prompt contracts over raising reasoning or adding long natural-language explanations.

- Use XML tags consistently so the prompt has stable internal structure.

Default prompt recipe:

- `<task>`: the concrete job and the relevant repository or failure context.

- `<structured_output_contract>` or `<compact_output_contract>`: exact shape, ordering, and brevity requirements.

- `<default_follow_through_policy>`: what the model should do by default instead of asking routine questions.

- `<verification_loop>` or `<completeness_contract>`: required for debugging, implementation, or risky fixes.

- `<grounding_rules>` or `<citation_rules>`: required for review, research, or anything that could drift into unsupported claims.

Model selection guidance (`<model_selection>` block):

- AGY engine: `--model` is ignored; effort controls are irrelevant. Use AGY for speed and simplicity.

When to add blocks:

- Coding or debugging: add `completeness_contract`, `verification_loop`, and `missing_context_gating`.

- Review or adversarial review: add `grounding_rules`, `structured_output_contract`, and `dig_deeper_nudge`.

- Research or recommendation tasks: add `research_mode` and `citation_rules`.

- Write-capable tasks: add `action_safety` so the model stays narrow and avoids unrelated refactors.

Working rules:

- Prefer explicit prompt contracts over vague nudges.

- Use stable XML tag names.

- Do not raise reasoning or complexity first. Tighten the prompt and verification rules before adding more model power.

- Keep claims anchored to observed evidence. If something is a hypothesis, say so.

Prompt assembly checklist:

1. Define the exact task and scope in `<task>`.

2. Choose the smallest output contract that still makes the answer easy to use.

3. Decide whether the model should keep going by default or stop for missing high-risk details.

4. Add verification, grounding, and safety tags only where the task needs them.

5. Remove redundant instructions before sending the prompt.