Agent Skills Hub

Create New Skills

A framework for creating reusable Claude Code agent skills, following best practices for directory structure, progressive disclosure, and multi-file patterns.

tpmjs-tool-creator

Development guide for creating and publishing TPMJS tools using the blocks CLI, AI SDK v6, and npm registry patterns.

hello-world

A friendly welcome skill that displays system OS details in ASCII art when triggered by casual greetings like 'hello' or 'hi'.

release

Automates the release workflow for Worktrunk, including version bumping, CHANGELOG generation, contributor crediting, and publishing to crates.io and GitHub.

rule-validation

Validates Skill, Agent, and Command syntax using validate_skills.py, logs errors, and manages the automated QC workflow for agent development.

looped-builder

Scaffold complex, multi-step coding tasks into actionable implementation plans and execute them autonomously using a Claude-driven bash loop.

durable-objects

Create, debug, and optimize Cloudflare Durable Objects. Supports stateful coordination, RPC, SQLite storage, WebSocket handlers, and Vitest testing.

wt

Manage isolated LlamaFarm development environments using git worktrees for parallel agent sessions and service testing.

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.

plugin-best-practices

Validates Claude Code plugins against architectural standards, checking manifest files, frontmatter, and tool invocation patterns to ensure high-quality, compliant plugin development.

playwright-cli

Token-efficient CLI for browser automation, web testing, and agentic workflows using Playwright.

sql-pro

Expert SQL agent for modern database systems, query optimization, HTAP environments, and data architecture patterns. Optimize performance, schema design, and analytical workloads effectively.