run-evals — Claude Code skill: E2E runs and setup
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.
LicenseRef-Proprietary ★ 7,523 updated 2026-10-29
npx skills add Devin-AXIS/iPolloWork --skill run-evals -a claude-codeWhat run-evals 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.
What it helps with
- 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 for the agent
- Launch iPolloWork in Daytona and run the
<flow-id>flow through CDP. - List the eval flows, then run them with the
denstack. - Check this feature locally and save the run report under
evals/results/<run-id>/.
How to install run-evals
1Skills CLI (Vercel)
npx skills add Devin-AXIS/iPolloWork --skill run-evals -a claude-code2Manually: put the files in place
~/.claude/skills/run-evals/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/run-evals/
1Skills CLI (Vercel)
npx skills add Devin-AXIS/iPolloWork --skill run-evals -a codex2Manually: put the files in place
.agents/skills/run-evals/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Devin-AXIS/iPolloWork --skill run-evals -a cursor2Manually: put the files in place
.cursor/skills/run-evals/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Devin-AXIS/iPolloWork .opencode/skills/run-evals2Manually: put the files in place
.github/skills/run-evals/SKILL.md1Skills CLI (Vercel)
npx skills add Devin-AXIS/iPolloWork --skill run-evals -a gemini-cli2Platform CLI
gemini skills install https://github.com/Devin-AXIS/iPolloWork --path .opencode/skills/run-evalsManually: put the files in place
.devin/skills/run-evals/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about run-evals
How do I install run-evals in Claude Code?
Run npx skills add Devin-AXIS/iPolloWork --skill run-evals -a claude-code. The skill file is at ~/.claude/skills/run-evals/SKILL.md.
What does run-evals do?
It launches iPolloWork in Daytona or local Electron and runs coded eval flows through CDP. The run generates screenshots and reports.
What is required to run it in Daytona?
You need the daytona CLI installed and logged in, an active organization selection, and .devcontainer/ files in the repository. If the app opens its Welcome page, use an onboarding flow or create /workspace/hello in the UI before a flow that needs a workspace.