Browse Skills

PR Review fixes review comments on an open pull request by grouping them by impact and applying approved changes. Use it to triage Gemini or human feedback and work through a prioritized fix queue.

PR Review Agent orchestrates full pull request reviews, including comment triage, blast radius checks, and architecture drift checks. Use it when reviewing a PR or deciding whether it is ready to merge.

Standards Kit enforces development and design rules for code quality, naming, imports, and approved UI libraries. Use it when reviewing or building features that must follow strict implementation standards.

Forge convenes an engineering panel to deliberate on architecture, debugging, refactoring, and code review. Use it when you need structured technical evidence and a synthesized verdict on a codebase decision.

RDC CLI analyzes RenderDoc .rdc captures from the command line for frame inspection, shader debugging, and draw call tracing. It also supports exporting render targets and running CI assertions against GPU captures.

Blue Team patches a target against a concrete set of failing cases, one root-cause class at a time, while checking that previously passing cases still pass. Use it for red-team failure catalogues or CI test failures when you want the fix loop to stop only when regressions are closed.

Debug Runtime Integration helps identify why NeMo Relay loads but runtime behavior is missing or incorrect, including scope, event, plugin, and export wiring issues. Use it when integration works partially but the expected callbacks or telemetry do not appear.

Fix Bug guides reproducing a defect, writing a failing test, and making the smallest code change to restore expected behavior. Use it when a feature breaks, behaves unexpectedly, or violates a user's mental model.

Improvement guides making focused enhancements to existing ClaudeBar functionality using TDD. Use it for UX, performance, or code-quality changes when you are not adding a new feature.

Karpathy Guidelines reduce common LLM coding mistakes when writing, reviewing, or refactoring code. It encourages explicit assumptions, minimal changes, and verifiable success criteria.

Building writes production code with test-first discipline using RED-GREEN-REFACTOR, vertical slicing, and safe refactoring. Use it when implementing features or fixes that need reliable tests and code generation patterns.

Code Review runs adversarial diff reviews with confidence-scored findings and file:line evidence. It also supports receiving review by checking external feedback before agreeing or acting on it.