Testing skills

Development workflows for the playwright-cli repository. Use when the user asks about rolling dependencies, releasing, or other repo maintenance tasks.

OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.

Build, run, and validate evaluators for AI/LLM applications with Phoenix, in Python or TypeScript (including Vercel AI SDK apps) — code-based checks and LLM-as-a-judge, run over exported traces or dataframes or as…

Debug LLM applications using the Phoenix CLI (`px`, from @arizeai/phoenix-cli). Fetch traces, spans, and sessions, annotate them, analyze errors, measure how often a failure or pattern occurs across traces, inspect…

Multi-Agent Harness for Production AI

Multi-Agent Harness for Production AI

Run Playwright smoke tests, debug failures, and verify fixes

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not…

Design and evaluate paid-ad experiments with hypotheses, randomization units, sample-size and duration assumptions, guardrails, platform experiment tools, analysis, and decision rules. Use for A/B test, split test,…

在实现任何功能或修复 bug 时使用,在编写实现代码之前

Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, log into sites, or automate browser…

A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test)

Generate comprehensive tests for specified code

Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop

Existing task skill that should remain after job-level skill injection.

Scaffold a new Harbor benchmark adapter by running `harbor adapter init` and then guide implementation using the Adapters Agent Guide as the authoritative spec.

Create a new Harbor task for evaluating agents. Use when the user wants to

Generate a greeting message and write it to a file.

Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.

Write Harbor task verifiers using Reward Kit. Use when creating or editing a

Write the proof file for the Harbor runtime skill injection example.

Create or reuse Hugging Face dataset PRs for `harborframework/parity-experiments` and upload Harbor parity/oracle result folders efficiently with sparse checkout, raw git pushes, and Git LFS.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.