Loading...
Loading...
Found 5 Skills
Automates benchmark test creation for C++ projects using Google Benchmark with consistent software testing patterns. Use when creating performance benchmarks, profiling tests, or when the user mentions benchmarking, Google Benchmark, or performance testing.
A skill to improve test code quality based on the test principles from Google's "Software Engineering at Google". It supports creating new tests, reviewing and refactoring existing tests. Must be used when users make requests such as: "Write tests", "Add tests", "Review test code", "Refactor tests", "Improve test quality", "Check if test principles are followed", "Use good test writing practices", "I want tests for this method", "Insufficient test cases", "Review tests", "Increase coverage". Actively trigger this skill for any test-related work even if the skill name is not explicitly mentioned. It has three subcommands: review (test code review), refactor (refactoring existing tests), write (creating new tests).
Systematically add test coverage for all local code changes using specialized review and development agents. Add tests for uncommitted changes (including untracked files), or if everything is commited, then will cover latest commit.
Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions to configuring-experiment-rollout and metric setup to configuring-experiment-analytics. TRIGGER when: user asks to create a new experiment or A/B test, OR when you are about to call experiment-create. DO NOT TRIGGER when: user is updating an existing experiment, managing lifecycle, or only browsing experiments.
Write unit and integration tests for a reproduced bug based on issue-analysis-<issue_number>.md.