# run-evals

The run-evals skill launches iPolloWork and runs coded E2E flows through CDP. Use it to check a feature and produce run artifacts for a PR.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 7523 repo stars
- Author: Devin-AXIS
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Devin-AXIS/iPolloWork/tree/HEAD/.opencode/skills/run-evals/SKILL.md
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/run-evals

## What it does

The skill starts iPolloWork in a Daytona sandbox or locally with Electron, then runs eval flows. Daytona use requires an installed, logged-in CLI, a selected organization, and the repository’s `.devcontainer/` files. Runs produce machine-checkable assertions, screenshots, and reports under `evals/results/<run-id>/`.

Use `pnpm evals` to list flows, run one by ID, or start all flows with the `den` stack. A missing flow can be added as `evals/flows/<id>.flow.mjs`. The `fraimz` skill owns the proof and verdict loop, so load it too when the task needs a verdict.

Local Electron is the fallback when Daytona is down or quota-limited. A local run does not validate Daytona, so report which environment produced the result. Video recording is for cases where motion matters; frame evidence is the standard output.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill run-evals -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/run-evals/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/run-evals/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill run-evals -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/run-evals/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill run-evals -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/run-evals/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install Devin-AXIS/iPolloWork .opencode/skills/run-evals
```

2. **Manually: put the files in place**
- File: `.github/skills/run-evals/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill run-evals -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/Devin-AXIS/iPolloWork --path .opencode/skills/run-evals
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/run-evals/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Devin-AXIS/iPolloWork/tree/HEAD/.opencode/skills/run-evals/SKILL.md

## When to use it
- launch iPolloWork in Daytona for an E2E run
- list available eval flows and select one by ID
- check app behavior through CDP
- save screenshots and run reports
- add a coded flow for a feature

## Example prompts
- Launch iPolloWork in Daytona and run the `<flow-id>` flow through CDP.
- List the eval flows, then run them with the `den` stack.
- Check this feature locally and save the run report under `evals/results/<run-id>/`.

## Similar
- [flow-next-drive](https://affpapa.org/en/nevibecode/skills/flow-next-drive.md) — skill · ★ 730 repo stars
- [rag-observability-evals](https://affpapa.org/en/nevibecode/skills/rag-observability-evals.md) — skill · 353 installs
- [aiconfig-online-evals](https://affpapa.org/en/nevibecode/skills/aiconfig-online-evals.md) — skill · 2700 installs
- [online-evals](https://affpapa.org/en/nevibecode/skills/online-evals.md) — skill · 1900 installs
- [adk-evals](https://affpapa.org/en/nevibecode/skills/adk-evals.md) — skill · 1700 installs
- [evals-start](https://affpapa.org/en/nevibecode/skills/evals-start.md) — skill · 959 installs

From the same set: [devin-axis/ipollowork](https://affpapa.org/en/nevibecode/by/devin-axis/ipollowork.md) — 42 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
