Plan and validate tests to prevent stdlib-focused pitfalls.
npx skills add https://github.com/ponylang/llm-skills --skill pony-test-design
Please help me install this Agent Skill. Skill: pony-test-design Source: https://github.com/ponylang/llm-skills/tree/main/pony-test-design Command: npx skills add https://github.com/ponylang/llm-skills --skill pony-test-design
Two-stage ensemble for planning meaningful tests. Load when writing tests for new features or reviewing test quality. Counters the tendency to write tests that exercise the stdlib instead of your code. Has full (8-persona) and lightweight (5-persona) modes.
Run the two-stage ensemble workflow to begin planning tests for a feature or bug fix.
High-intent search queries and answers about installing and using this skill.
Test design planning prevents stdlib-focused test pitfalls by using a two-stage ensemble workflow to produce a structured candidate test strategy. This approach guides test creation to ensure your code is validated rather than just standard library functions.
Full mode uses an 8-persona ensemble for comprehensive test planning, while lightweight mode uses 5 personas to fit smaller project scopes. Both modes execute the two-stage planning and evaluation workflow to generate candidate test strategies.
Evaluate and iterate on a candidate test strategy by running the two-stage ensemble workflow. It produces evaluation feedback artifacts that guide iteration and convergence decisions, ensuring your bug fix tests are robust and meaningful.
Use an ensemble workflow for test design when writing tests for new features or reviewing test quality. It is specifically designed to counter the tendency to write tests that exercise the stdlib instead of your actual code.
Yes, the test planning and validation scope explicitly includes both feature development and bug fixes. The ensemble workflow generates structured candidate test strategies and evaluation artifacts to guide iteration across both scenarios.
Tony363Facilitate requirements discovery through Socratic dialogue and multi-persona analysis.
Sheldon-92Execute test suites and report failures with coverage metrics.
gaiastudio-aiAutomate test quality review and flakiness identification in automated tests.
coreyjaWrite behavior-focused unit, integration, and end-to-end tests with mocked dependencies.
