---
title: "Promptfoo Evaluation - Air Market"
description: "You changed a prompt and you are not sure whether it got better or worse. This sets up prompt testing with the Promptfoo framework so you can run your prompts against test cases, compare models, and…"
canonical: "https://airmarket.ai/app/promptfoo-evaluation"
---

[Air Market](/) / [Developer Tools](/category/devtools) / Promptfoo Evaluation

Skill by [daymade](/@daymade)

# Promptfoo Evaluation

Test your prompts against real cases instead of guessing

## What this does

You changed a prompt and you are not sure whether it got better or worse. This sets up prompt testing with the Promptfoo framework so you can run your prompts against test cases, compare models, and check results with your own assertions or a model acting as judge.

### Top 3 things it does for you

- Set up a prompt test config
- Compare how different models answer
- Write your own pass/fail checks

## Information

**Promptfoo Evaluation at a glance**

|  |  |
| --- | --- |
| Kind | Skill |
| Publisher | [daymade](/@daymade) |
| Category | [Developer Tools](/category/devtools) |
| Works with | Agent Skills - an open standard supported by 40+ agents |
| Size | 22 KB |
| Licence | MIT |
| Repository | [daymade/claude-code-skills](https://github.com/daymade/claude-code-skills/tree/b2003d6f31764a7a37e08cc76ded206810f70ae4/promptfoo-evaluation) |
| GitHub stars | 1,348 (as of Nov 2026) |
| Installs | 1,597, counted by skills.sh (Nov 2026) |

## Security report

**Verified.** AIR scanned this exact version of Promptfoo Evaluation and flagged nothing. AIR's verdict: **safe**.

**What Promptfoo Evaluation's check was run against**

|  |  |
| --- | --- |
| Commit | b2003d6f31764a7a37e08cc76ded206810f70ae4 |
| Content hash | 2aa3a7c4b6ef88cfa086b0620a1e9ce8ff595723ba218ecb99df0dd608fcfbc1 |
| Files read | [Browse the files at this exact commit](https://github.com/daymade/claude-code-skills/blob/b2003d6f31764a7a37e08cc76ded206810f70ae4/promptfoo-evaluation/SKILL.md) |

A scan is named by the exact content it read, not by a version number. A different version is a different artifact, and nothing here applies to a version AIR has not scanned.

[Read the full security report for Promptfoo Evaluation](/security/promptfoo-evaluation)

## About Promptfoo Evaluation

This configures and runs LLM evaluation using the Promptfoo framework. It handles the evaluation config, so setting up prompt testing does not start from a blank file.

It covers custom assertions written in Python, llm-rubric for using an LLM as a judge, and managing few-shot examples inside your prompts. It also fits model comparison work, where the same prompts need to run against more than one model.

## What's inside

- SKILL.md - instructions
- .security-scan-passed
- references/promptfoo_api.md - reference
- scripts/metrics.py - script

## Questions

### Is Promptfoo Evaluation safe to install?

AIR scanned this exact version of Promptfoo Evaluation and flagged nothing. AIR's verdict: safe. The verdict is named by the content that was read, at commit b2003d6f3176, so it cannot drift onto a version nobody scanned. The full report is at https://airmarket.ai/security/promptfoo-evaluation.

### How do I install Promptfoo Evaluation?

Open https://airmarket.ai/app/promptfoo-evaluation on Air Market and use the install action: Air Market hands Claude a prompt naming this exact skill, and Claude sets it up. Source, pinned to the exact commit this listing describes: https://github.com/daymade/claude-code-skills/tree/b2003d6f31764a7a37e08cc76ded206810f70ae4/promptfoo-evaluation. Install from that link, not the branch.

## Related on Air Market

- [More Developer Tools listings](/category/devtools)
- [Everything by daymade](/@daymade)

---

Canonical URL: <https://airmarket.ai/app/promptfoo-evaluation>