Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Pre-release onboarding test via Chrome browser automation. Tests the full new-user flow — provider selection, workflow picker, and streaming all three starter workflows. Use when asked to test onboarding, first-run experience, or starter workflows.
Test Scope locally in Livepeer mode end to end using a prebuilt `go-livepeer` artifact from the `ja/serverless` PR, `uv run --extra livepeer livepeer-runner`, and Scope. Use when the user mentions Livepeer mode, `livepeer-runner`, or local serverless testing. Pair with `testing-scope-mcp` when the test path should be driven through Scope's MCP server.
Test Daydream Scope through its stdio MCP server, including disconnected startup, `connect_to_scope`, direct Python stdio client fallback, and lightweight smoke tests. Use when testing Scope via MCP, debugging MCP registration, or when a workflow depends on `connect_to_scope`, `load_pipeline`, `start_stream`, or `capture_frame`.
Ensures Azure REST API and CLI consistency across a document. Use when asked to check API calls, CLI parameters, or REST consistency.
Validates portal navigation paths, detects contradictions against Microsoft Learn documentation, and checks alignment with current Azure implementation standards. Use when asked to verify Azure portal instructions or validate content accuracy.
Identifies definite errors in code samples including syntax errors, missing imports, and deprecated APIs. Use when asked to review code samples for correctness.
Verifies code samples against official Microsoft/Azure examples and syntax rules. Use when asked to verify code correctness or validate API usage.
Checks if DEPENDENCIES.md is out of date by comparing it against gradle/libs.versions.toml and each module's build.gradle. Reports any version mismatches, missing dependencies, or removed dependencies.
Identifies severe factual errors in content. Use when asked to fact-check documentation for major inaccuracies.