Skill UI

This skill simulates a Chief Data Officer's deep interrogation, pressure-testing any plan touching core data strategy. Use it before approving ML model training runs, selecting data infrastructure (warehouse vs. mesh), productizing data assets, or making major team hires. It ensures that all data decisions are grounded in clear business decisions, compliance, and structural necessity.

This skill simulates a rigorous review by a Chief Financial Officer (CFO) to stress-test any major plan that involves spending or fundraising. It forces consideration of critical financial metrics such as burn rate, unit economics, dilution path, and capital allocation alternatives. Use this when evaluating new expenditures, hiring waves, or funding decisions to ensure financial viability and sustainable growth.

This expert framework guides users through the systematic process of conducting rigorous A/B tests and growth experiments. It covers all stages: formulating strong hypotheses, selecting appropriate metrics (primary, secondary, guardrail), calculating necessary sample sizes, and choosing the best implementation method (client-side vs. server-side). Use this when planning to compare two versions or build a systematic growth experimentation program.

Expert skill for building Model Context Protocol (MCP) servers and tools from scratch. Covers the full development lifecycle—from defining tool schemas and resources to implementation, testing, and publishing to registries. Supports robust patterns using TypeScript and Python for integrating custom capabilities into AI agents.

This skill automatically routes subtasks to the most cost-effective Claude model (Haiku, Sonnet, or Opus) based on complexity. It logs real token usage and cost per session, and includes an A/B testing feature to validate model tier savings against your actual workload, ensuring accurate cost control.

A comprehensive skill orchestrator designed for AI coding agents working with Go/Golang. Instead of relying on single skills, this tool analyzes the entire task context—be it designing an API, debugging a panic, or auditing security—and dynamically loads all necessary, relevant skills (e.g., concurrency, testing, error handling, and security) simultaneously. It ensures a holistic approach to Go development.

This skill helps manage and execute steps within a Test-Driven Development (TDD) workflow cycle. Note that this skill serves as an alias for `tdd-workflows-tdd-cycle`, maintaining discoverability. It guides users through the complete TDD development cycle, ensuring structured testing and validation steps.

This deployment skill is designed to be integrated into the Playwright testing workflow. Its primary function is to validate the loading process of shared skills across the entire environment during the startup phase. It ensures that all necessary components and modules are correctly registered and available for reliable End-to-End (E2E) testing execution.

This meta-skill runs three essential quality gates (ruff, mypy, and pytest) concurrently against the staged changes. It provides a comprehensive, CI-like check locally, offering a single BLOCK or APPROVE verdict to ensure code readiness before committing. It combines static analysis, type checking, and unit testing into one workflow.

Unship is a dedicated local workflow for front-end developers to compare multiple AI-generated UI alternatives (such as layouts, copy, or flows) directly within a running application environment. Instead of committing to one generated version, it adds temporary source-level variants, allowing for visual comparison. After the user selects the final version, the skill automatically cleans up all unused temporary code and attributes, ensuring a clean, production-ready codebase. Note: This tool is for local iteration only, not for production A/B testing or analytics.

This Main Agent acts as a central orchestrator for a specialized squad of AI agents, managing complex software development lifecycles. It guides projects through defined phases—from requirements gathering and planning to architecture, implementation, testing, and deployment. It maintains strict context discipline by summarizing agent outputs and referencing full artifacts, ensuring efficient, structured, and non-overwhelming communication to the user.

Dep handles the entire journey from local code to production deployment. This skill automates containerization using Docker and docker-compose, establishes robust CI/CD pipelines (linting, testing, security scanning, deployment), manages environment variables and secrets, and generates Infrastructure as Code (Terraform/Pulumi) configurations. It ensures observability and provides rollback procedures.