create-qa-test

create-qa-test is a skill for Claude Code from jpoutrin/product-forge. It costs 14 tokens per session (2,098 once invoked), scanned A, original, MIT.

A guided tool for creating a QA test procedure for a software feature. It collects details such as the feature, URL, acceptance criteria, prerequisites, and test data, then saves a draft test file.

In plain words
What is it for?
Use it to write manual test cases and, optionally, explore the feature with Playwright, a browser-testing tool.
Why use it?
It provides a repeatable structure for deciding how a feature should be checked before release.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code.

Part of the product-design plugin — 43 skills, 8 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/jpoutrin/product-forge/create-qa-test
Any agent
npx skills add jpoutrin/product-forge --skill create-qa-test
Clone the repo
git clone --depth 1 https://github.com/jpoutrin/product-forge

Made for: Claude Code.

Or install product-design, the plugin that ships this one along with the rest of its 43 skills, 8 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for create-qa-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpoutrin/product-forge/create-qa-test.svg)](https://agentmods.dev/skills/jpoutrin/product-forge/create-qa-test)
Your own site
<a href="https://agentmods.dev/skills/jpoutrin/product-forge/create-qa-test"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/create-qa-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,098 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.02098
Opus 5 $0.00007 $0.01049
Sonnet 5 $0.00003 $0.00420
Haiku 4.5 $0.00001 $0.00210

Measured 2d ago against content hash 2025994d345e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

create-qa-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/product-design/skills/create-qa-test/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

create-qa-test

Category: Quality Assurance

Usage

create-qa-test <feature-name> [--url <url>] [--priority <priority>] [--explore]

Arguments

  • <feature-name>: Required - Name of the feature to test (kebab-case)
  • --url: Optional - Test environment URL for the feature
  • --priority: Optional - Test priority (critical, high, medium, low). Default: medium
  • --explore: Optional - Launch qa-tester agent to explore the feature via Playwright

Execution Instructions for Claude Code

When this command is run, Claude Code should:

  1. Generate Test ID

    • Format: QA-YYYYMMDD-###-feature-name.md
    • Use today's date
    • Find next sequential number for today
  2. Create Directory Structure (if not exists)

    qa-tests/
    ├── draft/
    ├── active/
    ├── executed/
    ├── archived/
    └── screenshots/
    
  3. Prompt for Details (if not provided)

    • Feature description
    • Test URL (if --url not specified)
    • Acceptance criteria
    • Prerequisites
    • Test data requirements
  4. Create QA Test File

    • Place in qa-tests/draft/ with status DRAFT
    • Include all required metadata
    • Generate test case placeholders based on feature
  5. Optional: Invoke qa-tester Agent

    • If --explore flag is set, launch the qa-tester agent
    • Agent will navigate to URL and document test steps
    • Agent will take screenshots of key states

File Template

# QA Test Procedure: [Feature Name]

## Metadata
- **Test ID**: QA-YYYYMMDD-###
- **Feature**: [Feature name]
- **Application**: [App name]
- **URL**: [Test environment URL]
- **Created**: [YYYY-MM-DD]
- **Author**: [Name]
- **Status**: DRAFT
- **Priority**: [Critical|High|Medium|Low]
- **Estimated Time**: [X minutes]
- **PRD Reference**: [Link if applicable]

## Prerequisites
- [ ] [Required setup step 1]
- [ ] [Test account with appropriate permissions]
- [ ] [Test data prepared]

## Test Environment
- **URL**: [Test environment URL]
- **Browser**: Chrome (latest)
- **Credentials**: See password manager

---

## Test Cases

### TC-001: [Happy Path - Main Success Scenario]

**Objective**: Verify the main success flow for [feature]

**Preconditions**:
- User is logged in
- [Feature-specific preconditions]

#### Steps

| Step | Action | Expected Result | Pass/Fail | Notes |
|------|--------|-----------------|-----------|-------|
| 1 | Navigate to [URL] | [Page loads correctly] | ☐ | |
| 2 | [Action] | [Expected outcome] | ☐ | |
| 3 | [Action] | [Expected outcome] | ☐ | |

**Postconditions**: [Expected state after test]

---

### TC-002: [Validation Test]

**Objective**: Verify input validation for [feature]

| Step | Action | Expected Result | Pass/Fail | Notes |
|------|--------|-----------------|-----------|-------|
| 1 | [Submit with empty required field] | [Error message appears] | ☐ | |
| 2 | [Enter invalid format] | [Validation error shown] | ☐ | |

---

## Edge Cases & Error Scenarios

### EC-001: [Edge Case Description]

| Step | Action | Expected Result | Pass/Fail | Notes |
|------|--------|-----------------|-----------|-------|
| 1 | [Edge case action] | [Expected behavior] | ☐ | |

---

## Summary Checklist

### Critical Path
- [ ] TC-001: [Title]

### Validation
- [ ] TC-002: [Title]

### Edge Cases
- [ ] EC-001: [Title]

---

## Test Execution Log

| Date | Tester | Environment | Build | Result | Issues |
|------|--------|-------------|-------|--------|--------|
| | | | | | |

## Notes
- [Additional observations]
- [Known limitations]

Read the full file on GitHub · 301 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 301 lines · 14 tokens per session scan A 2025994d345e

Subscribe to this mod's changes

create-qa-test is a skill published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 2,098 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.