AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Add a Product E2E Eval

A rulebook for adding or extending Paperclip's full-stack Product E2E eval workflows, fixtures, matchers, and evidence paths for local or Daytona runs.

Dev & CodingAdvanced★ 108,442⑂ 17,963AI score 7/10Last updated: Oct 29, 2026

What it does

  • Governs how to add or extend a Product E2E Eval in the Paperclip monorepo: real Chromium, Paperclip server, database, runner, provider, and optionally Daytona.
  • Resolves the repo root via PAPERCLIP_ROOT or git rev-parse --show-toplevel and verifies tests/runner-e2e and packages/paperclip-runner exist.
  • Registers the workflow in catalog.ts, fixture-registry.ts, everyday-cases.ts, and everyday-flow.ts, wiring profile/environment/case IDs through selector and matcher tables.
  • Enforces security rules: no credentials in catalog data, screenshots, logs, or tracked files; Daytona images must be immutable digests; no publishing of raw traces, videos, databases, or provider session IDs.
  • Requires evidence-based failure attribution (product bug vs. model/provider behavior vs. infrastructure) and forbids claiming qualification from partial or manual selections.

Who it's for

  • Engineers contributing eval cases to the paperclipai/paperclip repository.
  • QA/platform engineers maintaining the runner E2E and Everyday Workflows suites.
  • Teams that must keep paid live E2E campaigns scoped to the smallest explicit selector.

Examples

  1. "Add a new Everyday Workflow case" → author it in everyday-cases.ts/everyday-flow.ts, register it in catalog.ts, then confirm discovery with pnpm test:e2e:runner -- --list --suite everyday-workflows.
  2. "Calibrate a new grading assertion" → validate against both a correct outcome and a plausible wrong outcome so missing evidence can never pass.
  3. "Triage a timed-out run" → attribute the symptom from packaged attempt evidence and the dashboard, preserving observed failure and cause separately.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/paperclipai/paperclip/HEAD/.agents/skills/add-product-e2e-eval/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the .agents/skills/add-product-e2e-eval folder from the GitHub repo paperclipai/paperclip into my ~/.claude/skills/add-product-e2e-eval/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/paperclipai/paperclip.git && mkdir -p ~/.claude/skills && cp -r paperclip/.agents/skills/add-product-e2e-eval ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/paperclipai/paperclip.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r paperclip/.agents/skills/add-product-e2e-eval ~/.claude/skills/
  5. Restart Claude Code and confirm add-product-e2e-eval shows up in your skill list.
  6. This skill only works inside the Paperclip checkout — run from the cloned repo root or set PAPERCLIP_ROOT to that path.
  7. Run pnpm install, then pnpm test:e2e:runner -- --list to verify suites are discoverable before making changes.
View source on GitHub ↗License: MIT