review-wizard
Review wizard implementation. Use when asked to "review wizard", "check wizard", "audit wizard implementation", or "/review-wizard".
293 repo starsObserved in 1 repos
Testing & Quality
Testing & Quality skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
run-ops-mlir-snippets
Compile and optionally execute every func.func in an ops.mlir-style snippet file (or every .mlir file in a directory) using `run_ops_mlir_snippets.py`. Use when the user wants to compile or run TTIR op snippets on device, test ops.mlir files, or check which ops compile/execute successfully.
293 repo starsObserved in 1 repos
Testing & Quality
sts-feedback-diagnosis
Analyze SlayTheAmethyst feedback report bundles such as `sts-feedback-report-*.zip` or extracted `sts/` directories by prioritizing `sts/feedback/issue_body.md` and `request.json`, then `sts/jvm_logs/latest.log`, archived `jvm_log_*.log`, `launcher_settings.txt`, logcat, and optional crash artifacts to diagnose whether a problem is caused by the launcher, a mod, or the device/driver. Use when Codex needs to inspect a feedback package, interpret the project's diagnostics files, or write a concrete evidence-backed diagnosis and next step.
293 repo starsObserved in 1 repos
Testing & Quality
test-wizard
Test wizard locally. Use when asked to "test wizard", "try wizard", "run wizard", or "/test-wizard".
293 repo starsObserved in 1 repos
Testing & Quality
validate-tt-mlir-against-tt-xla
Validate a tt-mlir PR against tt-xla by creating a cherry-picked branch and triggering CI. Invoked as: /validate-tt-mlir-against-tt-xla <PR number or URL>. Use this skill whenever the user wants to test, validate, qualify, or check a tt-mlir PR in tt-xla, or mentions running uplift qualification test suite, or asks to trigger tt-xla CI for a tt-mlir change. Also triggers when the user mentions "xla validate", "xla test", or "validate in xla".
293 repo starsObserved in 1 repos
Testing & Quality
test-development
Tauri 项目测试开发技能，覆盖 Rust 单元测试和 React 组件测试。 触发场景： - 需要为 Rust Command 编写测试 - 需要为 React 组件编写测试 - 需要设计测试策略 - 需要运行和调试测试 触发词：测试、test、单元测试、集成测试、TDD、测试用例
292 repo starsObserved in 2 repos
Testing & Quality
bug-detective
排查已发生的问题、定位 Bug 原因。 触发场景： - 代码运行报错，需要定位原因 - 功能不正常，需要排查 - Tauri Command 返回错误，需要分析 - 日志分析、调试代码 触发词：Bug、报错、不工作、调试、排查、为什么、出问题、失败、不生效、无效、找不到原因、定位问题
292 repo starsObserved in 1 repos
Testing & Quality
check-model
Check model compatibility with xinfer before loading. Validates config.json, weight tensor shapes and naming, quantization format correctness, and multi-rank (tensor-parallel) divisibility. Use when the user asks to check, validate, audit, or verify a model will load correctly — from a HuggingFace URL/config, local path, or pasted tensor info.
292 repo starsObserved in 1 repos
Testing & Quality
code-review-analysis
Perform comprehensive code reviews with best practices, security checks, and constructive feedback. Use when reviewing pull requests, analyzing code quality, checking for security vulnerabilities, or providing code improvement suggestions.
292 repo starsObserved in 1 repos
Testing & Quality