agentleFS
yeaight7yeaight7/agent-powerups/skills/ask-gemini/SKILL.md

ask-gemini

Skill6 starsChanged 4 months agoApache-2.0View on GitHub

Use when a Codex or generic local agent needs a focused second opinion from Gemini CLI without MCP routing.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use local Gemini CLI as an external advisor for brainstorming, design feedback, or focused reviews.

    line 10
  2. Distinctive:

    Do not use when Gemini CLI is missing or unauthenticated.

    line 16
  3. Distinctive:

    Do not use as an MCP fallback.

    line 17
  4. Very specific:

    If gemini is missing, stop and ask the user to install/configure Gemini CLI.

    line 45
  5. Very specific:

    Missing CLI: do not use MCP; ask user to install/configure gemini.

    line 78
  6. Distinctive:

    Auth failure: keep artifact if APX created one, report CLI stderr.

    line 79

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ask Gemini

Purpose

Use local Gemini CLI as an external advisor for brainstorming, design feedback, or focused reviews. The workflow is local-first and always leaves a Markdown artifact.

When to Use

  • Need a Gemini second opinion from Codex App or another shell-capable agent.
  • Want reviewable output from gemini -p saved for later.
  • Do not use when Gemini CLI is missing or unauthenticated.
  • Do not use as an MCP fallback.

For multi-turn advisory sessions (persistent context across follow-ups), use relay-gemini instead — apx relay start <name> --provider gemini keeps context across turns.

Inputs

  • A specific prompt or task.
  • Local gemini command available in PATH.
  • Optional artifact directory.

Workflow

Run through APX:

apx ask-gemini "Brainstorm edge cases for this CLI"

Equivalent nested APX and direct CLI calls:

apx ask gemini "Brainstorm edge cases for this CLI"
gemini -p "Brainstorm edge cases for this CLI"

If gemini is missing, stop and ask the user to install/configure Gemini CLI. Verify with:

gemini --version

Output

APX writes:

.apx/artifacts/gemini-<slug>-<timestamp>.md

Artifact sections:

  • Original user task
  • Final prompt sent to Gemini CLI
  • Gemini output (raw)
  • Concise summary
  • Action items / next steps

Verification

apx check ask-gemini
apx ask-gemini "Return OK only" --json

Confirm JSON includes provider, artifactPath, promptLength, and raw output in stdout. Open the artifact before applying advice.

Failure Modes

  • Missing CLI: do not use MCP; ask user to install/configure gemini.
  • Auth failure: keep artifact if APX created one, report CLI stderr.
  • Broad prompt: narrow the question before running to avoid noisy advice.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.