Scenario Test Builder

Turns one focused Markdown behavior scenario into a deterministic test written in the repository's own test stack.

Dev & CodingIntermediate★ 168⑂ 6AI score 9/10Last updated: Aug 16, 2026

What it does

Enforces a repository-understanding gate: reads AGENTS.md, README, contribution guide, manifests, test config and neighboring tests, then states product surface, run command, test runner, fixture strategy and validation commands before touching code.
Normalizes prose requirements into a strict Given/When/Then scenario contract — one behavior, one reason to fail.
Maps preconditions, actions, oracles and cleanup onto the repo's actual fixtures, public APIs, CLI runners or browser runners.
Picks the narrowest harness that can prove the behavior (web, API, CLI, desktop, mobile, library) instead of defaulting to browser tests.
Preserves traceability: scenario ID in the test name/metadata and a link back to the Markdown spec.
Proves the compilation by running the test alone, the nearest suite, and required lint/type/build commands, then hands off evidence.

Who it's for

Developers and QA engineers converting acceptance criteria into automated coverage
Teams that reproduce user-visible regressions with a failing test before fixing
Contributors adding tests to an unfamiliar codebase

Examples

Compile "running a CLI command with an expired session prints re-login guidance" into a pytest subprocess test using the project's existing runner.
Turn "accepting a workspace invite shows the user in the member list" into a Playwright spec using the project's stable test IDs.
From a bug report, produce an API integration test that fails before the fix and passes after, locking in the regression.

Note: the skill deliberately rejects or splits broad exploratory journeys, subjective visual checks, and anything requiring real payments or human authorization.

· · · 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/tamdogood/builder-essential-skills/HEAD/skills/build-scenario-tests/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)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
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 Claude Skill Mart.
Copy the skills/build-scenario-tests folder from the GitHub repo tamdogood/builder-essential-skills into my ~/.claude/skills/build-scenario-tests/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/tamdogood/builder-essential-skills.git && mkdir -p ~/.claude/skills && cp -r builder-essential-skills/skills/build-scenario-tests ~/.claude/skills/

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

Open a terminal and go to your home directory: cd ~
Clone the repository: git clone https://github.com/tamdogood/builder-essential-skills.git
Create the skills directory if needed: mkdir -p ~/.claude/skills
Copy just this skill: cp -r builder-essential-skills/skills/build-scenario-tests ~/.claude/skills/
Verify the references/ and examples/ subfolders came along: ls ~/.claude/skills/build-scenario-tests
Restart Claude Code, then ask something like "turn these acceptance criteria into a scenario test".
Run it from the root of a project that already has a test runner configured for best results.

View source on GitHub ↗License: MIT