NeVibe · 13
Testing and QA: skills, rules and MCP servers
Testing and QA for Claude Code, Codex and Cursor: skills, subagents, rules and MCP servers, from popular to niche.
skill-creatorskill Creates and refines skills, then tests them with prompts, evaluations, and performance checks.
improve-codebase-architectureskill This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review.
tddskill Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details.
prototypeskill Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase.
codebase-designskill This skill helps design modules with small interfaces and hidden complexity. Use it when refactoring code, choosing a seam, or making tests easier to write.
diagnosing-bugsskill This skill guides an agent through reproducible diagnosis of hard bugs and performance regressions. Use it when code fails, produces wrong results, or becomes slow.
implementskill Implements work from a specification or tickets, following a test-driven flow and ending with review and a commit. Use it when a coding task needs a defined delivery routine.
to-specskill Turns the current conversation and repository context into a spec, then publishes it to the project issue tracker. Use it when a feature discussion is ready to hand off to an agent.
webapp-testingskill This skill tests local web apps with Playwright, helping agents debug UI behavior, capture screenshots, and inspect browser logs.
setup-pre-commitskill This skill configures pre-commit checks for a JavaScript repository, running Prettier, type checking, and tests before each commit.
migrate-to-shoehornskill Replaces `as` type assertions in tests with helpers from `@total-typescript/shoehorn`. Use it when tests need partial objects or deliberately invalid data.
writing-plansskill Creates an implementation plan from a spec before code changes begin. Use it when a task has multiple steps, files, and tests.
implement-specskill Implements a prepared spec from its ticket graph on one integration branch, using parallel subagents. Use it when tickets have blocking dependencies.
Tests are the best way to keep an agent from breaking your project: it sees a red run and fixes things itself. Skills in this topic cover test-first work (TDD), pytest, Jest, Vitest, Playwright and Cypress, coverage, and not bending a test to fit a bug. Check whether a skill runs the tests itself and with which command, because it has to match yours. A PostToolUse hook that runs tests after each edit is more reliable than any instruction.
