generating-ralph-charts
Generates RALPH charts (factor-level analysis diagrams) for HAYST method test design. Use when designing combination tests, identifying test coverage gaps, or analyzing system behavior factors.
Discover Tools skills, compare source repositories and read the instructions for each workflow.
Generates RALPH charts (factor-level analysis diagrams) for HAYST method test design. Use when designing combination tests, identifying test coverage gaps, or analyzing system behavior factors.
Retrieves project knowledge resources by browsing categories, searching tags, or filtering by keywords. Use when exploring existing knowledge or finding specific documentation entries.
Detects test flakiness patterns including timing issues, environmental dependencies, state pollution, and non-deterministic behaviors. Use as part of parallel test review execution.
Reviews UI test scenarios for RALPH chart and AC coverage. Detects uncovered constraints and acceptance criteria. Use as part of parallel UI test scenario review.
Reviews UI test scenarios for consolidation opportunities. Identifies scenarios that can be merged to reduce operation counts. Use as part of parallel UI test scenario review.
Systematic documentation review following document-writer principles. Use when user requests documentation review, quality check, or principle compliance verification.
Comment quality review. Detects LLM generation traces, implementation history, conversational tone, HOW vs WHY patterns, and redundant comments.
Generic code review for production code. Use as part of parallel code review execution.
TDD workflow executor using Canon TDD (Red-Green-Refactor). Supports test list creation, failing test writing, minimal implementation, and refactoring with test verification. Use when implementing features with...
Manages project tickets - list, show, create, update, and move. Use when listing tickets, showing ticket details, creating new tickets, updating ticket content, or moving tickets between statuses.
Reviews UI test scenarios for wording accuracy. Detects variables and dynamic values that cannot be verified from actual UI. Use as part of parallel UI test scenario review.
Reviews test code for assertion quality including precision levels, property coverage, and validation patterns. Use as part of parallel test review execution.
Reviews UI test scenarios for behavioral appropriateness. Detects design tests (colors, fonts, layout) that should not be in scenario tests. Use as part of parallel UI test scenario review.
Generic code review for test code. Use as part of parallel test review execution.
A template skill that demonstrates the SKILL.md format. Use this as a starting point for creating new skills.
Verifies software compliance with the C2PA specification. Invoke during planning or code review to check implementations against the spec. Provide code/design context and optionally a target version.
Specializes in ONNX model import failures, unsupported operators, opset version mismatches, and dynamic shape issues. Use when burn-import fails or produces incorrect results.
This skill should be used when the user asks about "ONNX import", "PyTorch to Burn", "safetensors", "model conversion", "burn-import", "unsupported operator", "opset version", or importing external models into...
This skill should be used when the user asks about "Burn tensors", "tensor operations", "Module derive", "burn config", "autodiff", "backward pass", "gradient", "record serialization", "model weights", or core...
Diagnoses Burn deep learning errors including tensor shape mismatches, backend panics, autodiff issues, and training failures. Use when encountering runtime errors, compilation failures, or unexpected behavior...
This skill should be used when the user mentions "burn", "tensor", "module", "backend", "training", "ONNX", "autodiff", "deep learning in Rust", or any Burn framework related query. Routes to appropriate domain...
This skill should be used when the user asks about "training loop", "Learner", "metrics", "dataset", "dataloader", "checkpointing", "optimizer", "learning rate scheduler", "custom training", or Burn training wo...
This skill should be used when the user asks about "Burn backend", "WGPU", "NdArray", "Candle", "LibTorch", "custom kernel", "CubeCL", "quantization", "WebAssembly", "no_std", or backend selection and extension...
This skill should be used when the user asks about "contributing to Burn", "adding an operation", "burn internals", "burn-tensor", "burn-autodiff", "ONNX converter", "NodeProcessor", or Burn framework developme...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.