Skip to content
Back to skills

Agy Prompting

ASecurity

Internal helper — how to tighten a user request into a sharp prompt for the Antigravity CLI (agy / Gemini 3.x with native web search and agentic tools)

  • 28 stars
  • 0 votes
  • 0 copies
  • 7 views
  • Added June 6, 2026
ai-agentsgoapi

Works with

  • cli
  • api

Security analysis

A100/100

Scanned June 6, 2026

npx -y skills add MarcosNahuel/antigravity-plugin-cc --skill agy-prompting --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agy Prompting?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Agy Prompting
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/marcosnahuel-agy-prompting/badge)](https://www.skillsdirectory.com/skills/marcosnahuel-agy-prompting)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: agy-prompting
description: Internal helper — how to tighten a user request into a sharp prompt for the Antigravity CLI (agy / Gemini 3.x with native web search and agentic tools)
user-invocable: false
---

# Prompting agy (Gemini 3.x via Antigravity CLI)

Use this skill ONLY inside the `antigravity:agy-rescue` subagent when shaping the text you pass to `agy --print`. Do not use it to do independent reasoning, file inspection, or research yourself.

## What agy is good at

- Native web search with citation grounding (real URLs, not hallucinated).
- Long-context reasoning over multiple sources.
- Following structured-output instructions (markdown tables, JSON, frontmatter).
- Tool calling for code generation and file edits when run with `--dangerously-skip-permissions`.

## What agy is worse at than Claude

- Following complex multi-turn workflow rules. Keep the prompt single-shot and self-contained.
- Inferring implicit context — if a constraint matters, write it down.
- Localized linguistic nuance — explicitly ask for the target dialect ("Spanish (Argentina)", "Brazilian Portuguese", etc.) when the output language matters.

## Prompt shape that works

```
<TASK in one sentence>.

Rules:
- <constraint 1>
- <constraint 2>
- ...

Output format:
<exact markdown / json schema you want>

<DATA / TOPIC>:
<the actual content>
```

Keep the rules to <= 8 bullets. More than that and Gemini starts dropping the tail.

## Things to ALWAYS include

- Output language when relevant.
- Whether citations are required and the citation format ([N] style works best).
- The exact output structure with markdown headers.
- An anti-hallucination clause ("if you could not find a solid source, say so explicitly" / "mark weak claims as [WEAK EVIDENCE]").

## Things to AVOID

- Multi-step "first do X, then do Y, then call me back" instructions. agy in `--print` mode is single-shot; chain steps from the caller side instead.
- Demanding more than ~20 sources unless the user asked for it — quality drops fast past that.
- Free-form "be creative" — for research, structure is what makes the output usable.
- Mixing rescue work (code edits) and research (web search) in the same call. Pick one.

## Routing flags reminder

These are CALLER-SIDE controls, never include them in the agy prompt text:

- `--print` — non-interactive
- `--dangerously-skip-permissions` — auto-approve tool use
- `--print-timeout 20m0s` — high-intensity research needs long timeouts
- `--continue` — resume the most recent agy conversation
- `--conversation <id>` — resume a specific past conversation

> **Removed in v0.1.1**: `--model` is not a valid `agy` CLI flag in 1.0.x — passing it makes the binary exit with `flags provided but not defined: -model`. Model selection is internal to the CLI. If you need a specific model, change it via `agy` interactive settings, not via the prompt.

## When in doubt

Default to the templates baked into `agy-rescue.md` for research mode. Only deviate when the user explicitly asks for a different shape.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.