Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Run a phased scheduler audit from modules/sd_samplers_diffusers.py and scheduler UI definitions: verify class loadability first, then config validity against scheduler capabilities, then SamplerData correctness and UI option alignment.
Run a phased scripts audit in scripts/*.py: validate Script overrides (init/title/show) first, then verify ui() output compatibility with run() or process() parameters.
Debug a broken SD.Next or Diffusers model integration. Use when a newly added or ported model fails to load, misdetects, crashes during prompt encoding or sampling, or produces incorrect outputs.
Comprehensive E2E test development guidance for Eclipse Che / Red Hat OpenShift Dev Spaces. Use this skill when writing, modifying, or reviewing TypeScript Mocha Selenium tests, page objects, utilities, or test infrastructure. Provides code style rules, patterns, dependency injection setup, and best practices.
Explore a web page with new functionality using Playwright, record UI interactions, develop a test plan, and generate E2E Mocha/Selenium test code following the project's code style and patterns.
Review a FlashList PR or branch, run unit tests, test on iOS simulator, and verify RTL/LTR behavior. Shared context with fix-github-issue skill.
How to test and debug Feast — running targeted tests, writing unit tests for new components, debugging registry and online store issues, and inspecting live feature store state. Use when writing tests for a new feature, debugging a failing test, investigating a runtime error, or verifying that a change works correctly end-to-end.
Qt6/C++ deep code review for Serial Studio. Use when asked to "review", "audit", "check", "look over", or "sanity check" C++ — or before committing. Runs the repo linter (scripts/code-verify.py) as Phase 1, then six parallel read-only analysis agents covering Qt model contracts, ownership/lifecycle, thread-safety + the data hotpath, API/C++ correctness, error handling, and performance. Reports only high-confidence findings (>=80/100) with prose mitigations. Never modifies code.