Scripting

Run Python scripts with inline dependencies using uv and PEP 723.

Browser automation using Puppeteer or Playwright. Use for web testing, screenshots, form filling, and automated browser interactions.

Python coding standards, conventions, and best practices. Use when writing, reviewing, or testing Python code.

Create and manage Databricks notebooks programmatically. Use when generating ingestion code, creating ETL notebooks, executing Databricks workflows, or when user mentions notebook creation, job automation, or data pipeline implementation in Databricks. Handles notebook generation, execution, and results retrieval.

TypeScript-first schema validation library with static type inference and runtime validation

CVE vulnerability checker for software dependencies and components. Includes KEV (Known Exploited Vulnerabilities) analysis, exploit verification, and white hat security assessment. Use when checking for known vulnerabilities, scanning dependencies, analyzing SBOM for CVEs, verifying security of packages/libraries, identifying actively exploited vulnerabilities, or performing KEV-based security assessments. Triggers on: CVE check, vulnerability scan, dependency security, SBOM analysis, security audit, package vulnerability, KEV check, exploited vulnerability, ransomware CVE, CISA KEV, exploit verification, white hat, attack vector analysis.

Self-improving skill library for programming workflows. Mines transcripts and patternsto propose and scaffold new skills. Use when you hear:- "turn this workflow into a skill"- "make a skill for our PR review process"- "generate a new skill"- "automate this repeated process"- "create a skill for X"- "what skills could I create?"- "propose some skills"

Identify and remove unused code, commented blocks, unreachable code, and unused imports. This skill should be used during Phase 1 cleanup tasks to improve codebase maintainability.

Efficiently compose multiple MCP tool operations by launching a subagent that writes and executes TypeScript or Python code. Use when you need to compose 3+ MCP tool calls, process their results together, implement complex logic, or avoid token overhead from loading many MCP tool schemas into main context. The subagent has MCP servers configured and writes code that calls tools dynamically.

Execute agentic coding tools directly via bash commands with output capture. Use this when the user requests to run AI agents (Gemini, Claude Code, etc.) and get their results directly.

Write minimal, strategic tests focused on core user flows and critical paths during feature development, deferring comprehensive edge case testing. Use this skill when writing unit tests, integration tests, or end-to-end tests, creating test files (*.test.ts, *.spec.js, __tests__/*), testing critical user workflows, focusing on behavior rather than implementation details, using descriptive test names, mocking external dependencies (databases, APIs, file systems), ensuring tests run quickly, testing business-critical functionality, or determining which tests to write during development versus dedicated testing phases. Apply this skill when completing features at logical milestones, writing tests for primary user flows, or balancing feature development speed with adequate test coverage.

Generate comprehensive pull request descriptions with summaries and test plans. Use when creating PR descriptions or documenting code changes.

TypeScript best practices and patterns

Safe refactoring of Jupyter notebook code into Python modules

Automate Chrome browser via DevTools Protocol. Use when user asks to scrape websites, take screenshots, generate PDFs, interact with web pages, extract content, fill forms, or automate browser tasks.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Python library for programmatic PDF generation and creation. Use when user wants to generate PDFs from scratch, create invoices, reports, certificates, labels, or custom documents with precise control over layout, fonts, graphics, tables, and charts. Supports both low-level drawing (Canvas) and high-level documents (Platypus).

Automates browser interactions using Playwright CLI and templates - takes screenshots, generates PDFs, clicks elements, fills forms, monitors console/network. Use when testing web pages, automating browser tasks, or when user mentions screenshots, web testing, form automation, or Playwright

This skill should be used when the user asks to "explore the codebase", "understand the architecture", "find similar features", or as Phase 2 of the /dev workflow. Launches explore agents to map codebase and returns key files list.

Write strategic, focused tests for critical user flows and core functionality using modern testing frameworks, focusing on behavior over implementation. Use this skill when creating test files, writing unit tests, integration tests, or end-to-end tests in test directories (tests/, __tests__, spec/, *.test.js, *.spec.py). Apply this skill when testing core user workflows and business-critical features, implementing test-driven development (TDD) with red-green-refactor cycles, mocking external dependencies for isolated unit tests, using clear descriptive test names that explain expected behavior, following arrange-act-assert patterns, and ensuring tests run fast and independently. This skill prioritizes testing what matters most (primary user flows) while deferring edge cases and non-critical paths until later, emphasizes behavior testing over implementation details to reduce brittleness, and uses modern frameworks like Jest, Playwright, Cypress, pytest, RSpec, or Testing Library for reliable, maintainable test