jaktestowac

Testing LLM features, guardrails, groundedness and agent skills.

API test automation with Playwright and contract testing.

Creating skills, custom agents, commands and prompt files, instructions and rules, hooks, plugins and orchestration packs for GitHub Copilot, Claude Code and OpenAI Codex, plus auditing a whole collection. Each covers this repository's single-source format and your own project's native files.

Accessibility, performance and load, and application security testing.

A minimal orchestrator with three read-mostly helpers (planner, explorer, analyst) that shows how to split analysis and planning across subagents to save context, with stop gates for the user. Start here to learn the pattern; it does not implement code. For a pipeline that also implements, reviews and commits, use plan-explore-review-commit.

A full delivery pipeline: a planner and an orchestrator drive architect, researcher, explorer, implementer, QA strategy, security, code review and docs subagents through small test-first phases, with a review and a user-approved commit after each. Pick it for multi-phase feature or refactoring work; for analysis and planning only, use orchestration-basics.

Test design, planning, exploratory testing, requirements traceability and bug reporting.

Quality contracts, change gates, waivers, release readiness, metrics and debt.

Unit tests, TDD, Playwright, mocking, visual regression, migration and test code review.

Explores an application (frontend through Playwright MCP, backend through its OpenAPI spec), plans coverage, implements UI and API tests, reviews them and runs them to a verified result. Pick it for a full suite with a review and verification stage; for a small first batch of tests, or a project that still needs a test framework set up, use ui-api-automation-minimal.

A compact UI + API pack with four helpers: explore (OpenAPI and/or Playwright MCP), plan, set up a test framework if none exists, and implement tests, each returning the same handoff packet. Pick it for a small first batch of tests or a project without a test framework; for a full suite with review and verification stages, use ui-api-automation.