Agent Skills Hub

jean-claude-dev

Expert development guide for the Jean Claude orchestration framework. Use for source code changes, architecture, testing, and debugging.

positron-qa-verify

Automates the creation of QA verification guides for Positron bug fixes and features by analyzing GitHub issues and PRs.

design

Collaborative UI design, wireframing, and Tailwind-first code polish to build distinctive, high-quality interfaces without AI slop.

update-llm-model-list

Audit and synchronize the supported LLM model list in assets.py against the authoritative litellm registry.

text-to-sql

Convert natural language queries to safe, optimized SQL. Automates database interactions with schema awareness and parameterized query generation.

BDD-prompts-with-eval

An AI-driven active listening framework to extract, clarify, and structure requirements, business values, and scope from ambiguous user stories.

hs

Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.

react-email

Build and send responsive HTML email templates using React components. Features a visual editor, rendering engine, and compatibility with major email clients.

nav-task

Manage Navigator task documentation: create implementation plans, archive completed features, and maintain the task index for Claude Code workflows.

spec

Create structured specifications for platform changes including GitHub issues, SDD templates, and automated type inference for infrastructure and security.

agno

Framework for building multi-agent systems, AgentOS runtimes, and MCP-integrated AI agents.

rivetkit-client-react

Official React client for RivetKit. Provides hooks like useActor and createRivetKit to build realtime React applications connected to Rivet Actors.