bmad-qa-generate-e2e-tests Skill: Add End-to-End and API Tests for Working Features

Has Claude write end-to-end and API tests for features that already work, following the test setup your project already uses.

Installs: 12.9K; on skills.sh
Stars: 54.9K; on GitHub
Files: 3; besides SKILL.md
Updated: Nov 2026; last repo commit

bmad-qa-generate-e2e-tests is a BMad Method skill for adding test coverage after the feature works. Claude finds the feature to cover, lists the scenarios and waits for your OK, learns how your project already runs end-to-end tests, writes one test per scenario, runs them twice and reports. Its description says it is not for unit tests on work in flight.

SKILL.md is a short shim. It runs one command, uv run --no-cache "{project-root}/_bmad/scripts/render_skill.py", and follows the workflow that command prints, so it needs the BMad setup from the bmad skill. The workflow lives in workflow.md in the same folder.

Good for

Developers who shipped a feature and now want regression tests for it
QA engineers adding end-to-end or API tests inside an existing test harness
Teams using the BMad ticket tree who want coverage for tickets in review
Anyone who wants failing tests reported as bugs and not weakened

Install bmad-qa-generate-e2e-tests

Claude Code

Copy this prompt.

Install the bmad-qa-generate-e2e-tests skill in Claude Code. Run this command:

npx skills add bmad-code-org/BMAD-METHOD --skill bmad --skill bmod-method --skill bmad-qa-generate-e2e-tests

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js, Git, uv.

bmad-qa-generate-e2e-tests belongs to the bmod-method module and needs the bmad skill, which sets up the _bmad folder in your project. The README needs uv for BMad setup and Python scripts. These are the v7 preview alpha skills from the main branch, which the README says change often. There is no Claude app upload route, because the skill runs uv scripts inside a project folder. The plugin marketplace repo lists the plugins as bmad-method and bmad-toolbox, while the main README calls the second one bmad-core-tools. The plugin tree holds skills only, with no hooks or MCP files.

Built from the package data we hold. Not yet tested by us.

What's in the skill

When it loads

Add end-to-end and API tests for features that already work, following the project's existing test harness. Use when the user asks for e2e tests, API tests, or automated coverage of an existing feature, or says "create qa automated tests for [feature]". Not for unit tests on work in flight, which the build writes.

Key facts

Author: BMad Code (bmad-code-org)
Repository: bmad-code-org/bmad-method
Installs on skills.sh: 12,876 as of 2026-11-02
GitHub stars: 54,859 for the whole repo, 2026-11-02
Last commit to the repo: 2026-11-01
Files: 4 files including SKILL.md (workflow.md, bmod.toml, customize.toml)
License: MIT per the repo LICENSE file and README (GitHub license detection reports NOASSERTION)
Module: Part of bmod-method; needs the bmad skill and uv
Status: README calls these v7 skills a preview alpha
Runs: uv run render_skill.py, then the project's own test runner

What it includes

SKILL.md runs one uv command and follows the workflow it prints
Claude runs render_skill.py once, without changing the working directory. If the script is missing, BMad is not set up and Claude offers the bmad setup. A HALT message is reported and the run stops.
Runs code · render_skill.py shim
Finds the feature or ticket and lists scenarios for your approval
Checks your request, then the BMad ticket tree, then the current git branch, then asks. Each scenario is one plain sentence. It never writes to ticket files.
Try: “Create QA automated tests for the checkout flow.”
Runs code · Phase 1: Scope
Reads how the project runs e2e tests, then runs the existing suite once
Looks at the runner, test layout, how the app starts, authentication and CI. A failing suite is a finding, not something to fix. With no harness, it proposes one and waits for your confirmation before adding a dependency or configuration.
Runs code · Phase 2: Learn the harness
One test per scenario, through the UI or public API
Tests use locators by role, label or text, assert visible outcomes, wait on conditions, create their own data and pass alone and in any order. No page-object layer is built.
Write · Phase 3: Write the tests
Runs the new tests twice and sorts failures
A wrong test is fixed. A wrong harness setup is fixed. A real application bug is kept, marked as an expected failure with the bug as the reason, and reported. It never weakens an assertion and never changes product code to pass.
Runs code · Phase 4: Run them
Lists covered and uncovered scenarios, bugs found and the run command
The report appears in chat and no summary file is written. Any product code touched for the harness, such as a test id, is listed.
Phase 5: Report

From the official docs

Permissions

Medium risk

The skill runs your end-to-end tests and writes new test files in your project. Use a branch and a test environment.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It runs your test suite
Phase 2 runs the existing end-to-end suite once, and Phase 4 runs new tests twice. If tests touch real databases or services, use a test environment. github.com
It can add a dependency or config
If there is no harness, it proposes one and waits for your confirmation before adding a dependency or configuration. github.com
It runs a script from your project
SKILL.md runs uv run render_skill.py from _bmad/scripts, put there by the bmad skill. github.com

Technical details

Scopes	Runs uv run render_skill.py from the project's _bmad/scripts folder Runs your existing end-to-end suite and the new tests Writes new test files, and may touch product code for test ids or add harness configuration after you confirm

Questions

What does bmad-qa-generate-e2e-tests do?

It writes end-to-end and API tests for features that already work, using your project's existing test runner and layout.

How do I install it in Claude Code or Codex?

Use the install box at the top of this page. It installs the skill with the bmad hub skill and its module record. Then ask bmad to run bmad setup in your project.

Does it fix bugs it finds?

No. workflow.md says to keep the test as written, mark it as an expected failure with the bug as the reason, and report it. It never changes product code to make a test pass.

Will it change my product code?

Only what the test harness needs to reach an element, such as a test id. Any such change is listed in the report.

Is it safe?

It runs your existing end-to-end suite, creates new test files and runs them twice. Run it against a test environment, not production data, and use a git branch.

Does it need an API key?

No key is named in SKILL.md or workflow.md. It needs uv and the BMad setup.

Does it work in the Claude app?

The install box leaves out a Claude app upload route, because the skill runs uv scripts and your test runner inside your project folder. Use Claude Code, Codex or another coding tool that supports skills.

Information

updated Nov 2, 2026

Repository: bmad-code-org/bmad-method
Folder: skills/bmad-qa-generate-e2e-tests

bmad-code-org/bmad-method skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

BMAD-METHOD README · github.com
bmad-plugins README · github.com
bmad-plugins marketplace.json · github.com
bmad-qa-generate-e2e-tests SKILL.md · github.com
workflow.md · github.com