发现 Skills

Playwright E2E testing framework. Covers browser automation, assertions, and test generation. Use for end-to-end testing. USE WHEN: user mentions "playwright", "e2e test", "browser test", "end-to-end", asks about "page.goto", "page.click", "locators", "cross-browser testing", "visual regression" DO NOT USE FOR: Unit tests - use `vitest` or `jest`; Component tests - use `testing-library`; API-only tests - use framework HTTP clients; Mobile apps - use specific mobile testing tools

Classify germline variants from VCF/BCF files according to the ACMG/AMP 2015 28-criteria evidence framework and generate clinical-grade interpretation reports with per-variant evidence audit trails and ACMG SF v3.2 secondary findings screening.

Search the web for images (photos, logos, graphics) and download them with Typst embedding code. Use when the user needs real-world images, company logos, or existing graphics for documents.

Use when a product safety incident is detected, a customer reports injury, a quality defect is found, a market surveillance authority contacts you, you need to assess recall obligations, or you need to notify authorities (CPSC, Safety Gate, OPSS) about a product safety issue

Connect BI tools and database clients to ClickZetta Lakehouse. Covers full connection configurations for mainstream tools such as Apache Superset, Tableau, Metabase, DBeaver, DataGrip, FanRuan FineBI, etc., including JDBC connection string formats, SQLAlchemy URL formats, and driver installation steps. Triggered when the user says "connect Superset", "Tableau connect Lakehouse", "Metabase", "DBeaver", "DataGrip", "BI tool", "JDBC connection", "SQLAlchemy connection", "FanRuan", "FineBI", "database client", "visualization tool connection", "BI report", "PowerBI", "Navicat", "MySQL protocol connection". Keywords: BI, Superset, Tableau, Metabase, DBeaver, DataGrip, FineBI, JDBC, connection

Deploy your own Open-Inspect instance. Use when the user wants to set up, deploy, or onboard to Open-Inspect. Guides through repository setup, credential collection, Terraform deployment, and verification with user handoffs.

Create XYZ hypotheses and design pretotype experiments to validate a new product concept with minimal effort.

Automate Vestaboard tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Ambient Weather tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Serpapi tasks via Rube MCP (Composio). Always search tools first for current schemas.

Use when coordinating OpenClaw platform operations, managing infrastructure incidents, assigning tasks to infrastructure agents, or conducting weekly reviews of VPS health and platform status.

Diagnoses common Linux service issues using logs, systemd/PM2, file permissions, Nginx reverse proxy checks, and DNS sanity checks. Use when a server app is failing, unreachable, or misconfigured.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Create distinctive, production-grade frontend interfaces with strong visual direction. Use for design systems, components, pages, dashboards, landing pages, accessibility, and polished UI work that should avoid generic AI aesthetics.

Guides developer education leadership—audience and skills-gap analysis, learning paths and curriculum design, workshops and cohort programs, hands-on labs, certification or badging, instructor enablement, feedback loops, and success metrics (completion, confidence, time-to-first-success). Use when building or scaling a developer training program, onboarding engineers to a platform, designing certification, planning launch enablement for developers, or aligning docs/tutorials with learning outcomes—not for writing single API pages (tech-writer-researcher), customer support macros (product-support-specialist), generic exec comms (communication-lead), or shipping product code (senior-software-engineer).

PDF processing. USE WHEN dealing with PDFs or .pdf files. Use SkillSearch('pdf') for docs.

Add or repair an iOS or iPadOS app target in a JUCE-Plugin-Starter project. Use when a project needs the portable equivalent of `setup-ios`: deciding between plain JUCE and Visage modes, creating app entrypoint files, wiring the CMake app target, and validating safe-area, touch, and simulator/device build details.

Datadog docs lookup using docs.datadoghq.com/llms.txt and linked Markdown pages.

Analyze two llmo experiements in a comparative manner. Use when user says "analyze two experiments", "comparative experiment analysis", "evaluate experiments" "analyze against baseline". Requires two experiment_id as arguments to perform a comparative analysis, first is the baseline, second the candidate.

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.

Implement Series-style batch indicators with mathematical precision. Use for new StaticSeries implementations or optimization. Series results are the canonical reference—all other styles must match exactly. Focus on cross-cutting requirements and performance optimization decisions.

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).