Search Skills

Preview and capture screenshots of UI components from local development servers and Storybook for testing and documentation.

Conducts thorough code reviews to identify unused code, duplications, bugs, and optimization opportunities without making changes.

Creates distinctive, production-ready frontend interfaces with high design quality, avoiding generic AI aesthetics for web components and applications.

Generates detailed feature implementation plans with architecture proposals and solution suggestions prior to coding.

Provides Vercel-engineered best practices for optimizing React and Next.js performance, including component design and data fetching strategies.

Generates git commits adhering to the Conventional Commits specification for standardized version control messaging.

Generates a draft GitHub pull request using the project's predefined template for consistent code review submissions.

Generates tool functions for ReinforceNow agent training, supporting @tool decorators and sandbox environments in AI agent development.

Provides CLI for RLHF training workflows including project initialization, training runs, and model management.

Generates training data from teacher models for off-policy distillation, enabling efficient knowledge transfer and SFT dataset creation.

Generates reward functions for Reinforcement Learning (RL) training in ReinforceNow, supporting @reward decorators, precondition rewards, and LLM verification.

Configures ReinforceNow training runs using config.yml and train.jsonl, and converts HuggingFace datasets to required format for model training.

Generates Dockerfiles for sandbox environments, supporting container image creation and deployment workflows.

Enables on-policy distillation training using token-level KL penalty with teacher models like Qwen and Llama.

Formats training data in JSONL for ReinforceNow, handling entry structures, tools, rewards, and sandbox setup.

Manages Open Agent library components (skills, agents, commands, tools, rules, MCPs) via Library API tools for development.

Automates Drizzle ORM setup with Neon database, including dependency installation, credential provisioning, schema generation, and migration execution for immediate database connectivity.

Configures authentication, creates auth routes, and generates UI components for Next.js, React SPA, and Node.js applications.

Adds Neon best practices reference links to project documentation files (CLAUDE.md, AGENTS.md, or Cursor rules) without modifying code or installing packages.

Automates creation and management of temporary Neon databases for testing, CI/CD pipelines, and isolated development environments.

Configures Neon Serverless Driver for Next.js, Vercel, and AWS Lambda with TypeScript examples and environment setup.

Configures a unified Neon JS SDK for authentication and PostgREST-style database access, including type generation for seamless app development.

Guides users in building custom customer support automation, including integration planning, script writing for tools like Zendesk, and triage workflow setup.

Provides AWS CloudFormation templates and patterns for Auto Scaling configurations across EC2, ECS, and Lambda, including best practices for high availability and cost optimization.