
Test Scenario Writer
Turns user stories into structured QA test scenarios with steps and expected outcomes
- Repository
- phuryn/pm-skills
- Stars
- 27,616
- Licence
- MIT
- Files
- 1 file
What it does
Once installed, the agent can take a user story and its acceptance criteria and produce detailed test scenarios. Each scenario includes a test objective, starting conditions, the user role performing it, numbered steps with expected results, and edge cases such as invalid inputs and boundary conditions. It follows a fixed template so the output is consistent and ready for a QA team to run. The skill is written as instructions only; it does not run any code or access outside systems.
Great for
- QA engineers who need a first draft of test cases from a feature spec
- Product managers who want to check that acceptance criteria are testable
- Developers preparing acceptance tests before or after building a feature
Skip it if
- Automated test code generation: the skill produces written scenarios, not runnable test scripts, so it will not replace a test framework
- Safety-critical or regulated testing where scenarios must be validated by a qualified human; the output is unreviewed AI text and can miss cases
Try asking
- “Write test scenarios for this user story: As a shopper, I want to reset my password by email, with these acceptance criteria...”
- “Create a test plan for our checkout flow, including edge cases for invalid payment details”
- “Turn these acceptance criteria for the search filter feature into QA test cases”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
test-scenarios.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip test-scenarios.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip test-scenarios.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Paste the full user story with all acceptance criteria and any constraints in $CONTEXT, such as browsers, roles, or data limits, so scenarios are specific.
- Review the generated expected outcomes against the real system behaviour, since the agent cannot know your actual product details beyond what you provide.
- Ask for edge cases explicitly if the default output seems light on negative or boundary tests.
What's inside
- SKILL.md
Redistributed unmodified from phuryn/pm-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.