game-balance-and-bots
Tunes game difficulty with seeded headless bots: sim reports, balance bands, tuning knobs, a fun-in-seconds test. Use when balancing, tuning pacing or adding…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-29 00:09
Testing & quality
12,875 results
golden-and-snapshot-tests
Guards data and pixel goldens - *.golden.test.ts snapshots, append-only [contract] entries, Skia tolerance, jest -u rules. Use when adding a golden or snapshot…
level-generation-and-solvers
Generates level tables proven winnable by a solver or witness bot: par, stars, pack unlocks, a daily level. Use when adding levels, a solver, par, stars, packs…
performance-budgets
Measures cold start, hitches, draw calls, storage writes, bundle and memory against budgets on iOS and Android. Use when adding animation, Skia, lists,…
run-goldens-rebaseline
Runs the golden rebaseline ritual - assertions green first, triage, one-file jest -u runs, every diff inspected, recorded, orphans deleted, proof without -u.…
spec-traceability
Keeps spec IDs traced in tests, code, commits and reports; flags dangling or untraced IDs. Use when a task cites a spec ID (REQ-4, SCR-2), asks what is…
tdd-workflow
Drives changes test-first (TDD, red-green-refactor) - one behaviour per commit, test names, layer order, no test edited to pass. Use when writing or changing…
unit-and-component-tests
Sets up Jest, checks unit, component and route tests (RNTL 14, renderWithProviders, SDK mocks, fakes, fast-check, Stryker). Use when writing a test or mock, or…
code-review
Review code changes for correctness, security, performance, and code quality. Use when the user asks to review a diff, review code changes, review commits, or…
testing
Creates tests, runs test suites, analyzes coverage, identifies edge cases
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially when the feedback seems unclear or technically problematic - requires technical rigor and verification, not protocol compliance or blind implementation
systematic-debugging
Use when encountering any error, test failure, or unexpected behavior before proposing a fix
test-driven-development
Use when implementing any feature or bug fix before writing implementation code
code-review-excellence
Provide high-signal code review guidance for TypeScript and C#/.NET. Use for PR review, review diff, code walkthrough, post-change verification, establishing review standards, and checking bugs, behavioral regressions, boundary conditions, type safety, async issues, resource management, performance pitfalls, EF Core, ASP.NET Core, LINQ, and missing tests. Suitable for…
k6-load-testing
k6 for load testing, performance testing, and API stress testing. Use when user mentions "k6", "load testing", "stress testing", "performance testing", "API…
playwright
Playwright for end-to-end testing, browser automation, and web scraping. Use when user mentions "playwright", "e2e testing", "end to end test", "browser…
write-tests
Generates comprehensive tests for a given file, function, class, or module. Covers unit tests, integration tests, edge cases, error paths, and mocking. Use…
devdocs-test-run
Execute test suites and generate test reports. Supports full test run, selective run by type (UT/IT/E2E), and traceability validation. Use when users need to…
factory-verify
Independently verify a factory pull request, including fail-closed gates, negative test proof, scope, and load-bearing review.
pgflow
Use when installing, upgrading, configuring, operating, or debugging PgFlow in Elixir/Phoenix; defining flows, jobs, maps, conditional steps, retries,…
agora-testing-guidance
Mocking patterns and testing requirements for Agora SDK integration code. Covers RTC Web, RTC React, RTC iOS, RTC Android, RTC React Native, RTC Flutter, RTM…
debugging
Use when a bug, test failure, build break, regression, flaky test, or unexpected behavior appears — before proposing or attempting fixes. Triggers: "why is…
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
skill-evaluator
Use when asked to review a skill's quality, test whether a skill works correctly, find why a skill behaves inconsistently or fails to trigger, check if a skill…