# Ask

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-szarkans-multi-ask`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [szarkans](https://agentstack.voostack.com/s/szarkans)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [szarkans](https://github.com/szarkans)
- **Source:** https://github.com/szarkans/multi/tree/main/skills/ask

## Install

```sh
agentstack add skill-szarkans-multi-ask
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Ask several models

!`sh -c 'for p in "$CLAUDE_PLUGIN_ROOT/scripts" "$HOME/.claude/skills/multi/scripts" "./.claude/skills/multi/scripts"; do [ -x "$p/probe.sh" ] && { "$p/probe.sh"; echo "scripts-dir: $p"; exit 0; }; done; echo "probe: NOT FOUND — locate scripts/probe.sh in this plugin and run it yourself"'`

One model's answer is one model's priors. Three answers from different families
show you where the question is actually settled and where it only looked
settled.

This is not a review and not a vote. **You do not pick a winner and you do not
merge them into one answer** — that throws away the only thing the user came
for. Show what each said, then say where they differ.

`$SCRIPTS` is whatever the probe printed as `scripts-dir:`.

## Run it

Start the external models first — they take 30–90 seconds and OpenCode spends
most of a minute just waking up. Answer the question yourself while they run.

```bash
$SCRIPTS/ask.sh --question "" \
                --out-prefix /tmp/multi-ask \
                --model  [--fallback ] [--effort ]
```

Pass the question **as the user asked it**. Do not rewrite it into a better
prompt: the point is what different models do with the same words. Add context
they would need and could not see — the file you are both looking at, what was
already ruled out — but leave the question itself alone.

Effort defaults to `medium`. Raise it for a hard design question, drop it to
`low` for something factual.

If neither external model is available, say so and just answer normally. This
skill has nothing to add without them, and pretending otherwise is worse than
a plain answer.

## Report

Your own answer is one of the three, not the frame around the other two. Write
it before you read theirs — otherwise it is not an independent answer.

```
## 

**Claude** — 

**Codex** — 

**OpenCode ()** —    ← or one line saying it did not run

### Where they differ

```

Keep each answer recognisably its own. Trim padding and repetition, but do not
paraphrase a model into agreeing with the others — a disagreement flattened in
the retelling is the one thing this skill exists to prevent.

If all three said the same thing, say that in one line. It is a useful answer:
the question was not as open as it looked.

Then stop. Offer to dig into one of the answers; do not act on any of them
unprompted.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [szarkans](https://github.com/szarkans)
- **Source:** [szarkans/multi](https://github.com/szarkans/multi)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-szarkans-multi-ask
- Seller: https://agentstack.voostack.com/s/szarkans
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.