playwright-triage
Triage a Playwright bug report by reproducing it from the information in the issue. Use when asked to triage, reproduce, or verify a GitHub issue (a new bug report, or an existing report with a new comment).
⌘ K
Newest skills
3209 skills
playwright-test-results
Query Playwright CI test results from the aggregated DuckDB database. Answers questions about flaky tests, failure rates, slow tests, and per-run/SHA/PR results without hunting through GitHub artifacts.
playwright-devops
DevOps workflows for Playwright - CI failure analysis, workflow debugging, and release operations.
playwright-dev
Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.
playwright-roll
Roll Playwright Python to a new driver version. Walks the upstream `docs/src/api/` commit range, ports each public-API change, suppresses the rest in `expected_api_mismatch.txt`, regenerates the typed surface, and adds tests.
playwright-java-release
Prepare a Playwright Java release after the rolling PR has merged — cut the release branch, mark the Maven version, draft the GitHub release, and tick the Java boxes in the internal checklist.
openvmm-ci-investigation
Investigate CI failures on OpenVMM PRs. Load when a PR has failing CI checks, you need to download and analyze test artifacts, or you need to diagnose build, fmt, clippy, or VMM test failures.
guide-maintenance
Maintain the OpenVMM Guide and its code-sync mapping. Load when: (1) adding, removing, or moving Guide pages, (2) adding new device crates or CLI args that need doc coverage, (3) updating the doc-code-sync mapping table, or (4) auditing Guide freshness against code changes.
fuzzing
Run, optimize, and debug OpenVMM fuzzers. Covers cargo-fuzz targets, crash reproduction, lldb debugging, code coverage analysis, entropy optimization, and multi-target parallel campaigns.
openclaw-dev
Deploy, operate, and troubleshoot the openclaw-dev template: a secure, hosted OpenClaw AI assistant on Azure (Azure Container Apps + Azure OpenAI in Foundry Models, passwordless via Managed Identity, Entra ID Easy Auth, ephemeral sandbox execution, optional Microsoft Teams channel) using the repo's `devclaw` wrapper around the Azure Developer CLI (azd). USE FOR: deploy openclaw-dev / OpenClaw to Azure in one prompt, "devclaw up" / "azd up" failing, set the model or region, switch tool execution to ephemeral sandboxes (EXECUTION_MODE=sandbox / devclaw exec-mode), clone another sandbox, connect
theme-authoring
Add a new color theme to the Ontology Playground. Use when someone wants to create, author, or plug in a theme, palette, color scheme, dark mode, or light mode, or add an entry to the theme picker. Covers the appStore registration plus the CSS token block.
ontology-school-path-generator
Generate Ontology School course paths/labs with progressive step ontologies from source ontology material. Use when user asks to tutorialize an ontology into school lessons and per-step builds.
ontology-catalog-import
Import customer or external RDF/OWL into this repo's catalogue format. Use when user drops an RDF/OWL file and wants it catalogue-ready (metadata, category, validation, compile).
name-generator
Generate approved person names for examples, demos, quests, tests, docs, and sample data. Use when a task needs fictional person names, customer names, employee names, patient names, student names, instructor names, or other human names.
community-ontology-contribution
Add a contributor ontology to catalogue/community/. Use when a community member submits an RDF/OWL file and wants it listed in the Playground catalogue under their GitHub username.
workspace-estimation-shared-header
Use when editing a boundary-safe shared header meant to be included by both in-tree and shared-provider/plugin-bridge code (e.g. include/onnxruntime/core/framework/workspace_requirement.h, or any future header supporting OrtKernelWorkspaceEstimateFunc / DeclareWorkspaceRequirements per issue #29775's Phase-A workspace-estimation roadmap), or when a workspace-estimation math helper needs to be callable from a future plugin EP DLL. Covers a Node forward-declaration ODR trap and the math-helper vs. graph-parsing-wrapper reuse boundary discovered while implementing PR #29811 (MatMulNBits pilot).
webgpu-local-testing
Build and run ONNX Runtime WebGPU provider tests on Linux WITHOUT a real GPU, using a software Vulkan adapter (Mesa lavapipe). Use when you need to exercise WebGPU EP kernels off-Mac — the Linux webgpu CI leg is build-only, so software Vulkan is how you actually run WebGPU correctness tests locally. SCOPE - lavapipe only validates host-side enforce/shape bugs and MatMul-free kernels; any graph containing MatMul (including the expanded-Attention node tests) crashes lavapipe and runs ONLY on macOS-arm64 Metal, which is the source of truth for those. Covers install (dnf on Azure Linux), the --use
python-kwargs-setattr-security
When reviewing or fixing Python code that uses setattr() with user-controlled kwargs to configure C++ extension objects (SessionOptions, RunOptions, etc.) in ONNX Runtime. Use this to apply the allowlist pattern that prevents arbitrary file writes and other attacks via reflected property access.
ort-transformers-gpu-pytest
Run the ONNX Runtime transformers Python tests (onnxruntime/test/python/transformers) against a GPU wheel, and confirm real cuDNN/flash SDPA dispatch. Use when a transformers pytest fails with ModuleNotFoundError onnxruntime.capi, when torch's bundled CUDA/cuDNN libs shadow the ORT-built ones (wrong-version dispatch or load errors), or when you must PROVE a test exercised the cuDNN SDPA decode tier instead of silently skipping/falling back to MATH.