Agent Skills Hub

prompt-improver

Enriches vague prompts by performing codebase research and asking targeted questions to clarify user intent before execution.

changelog

Automated runtime observability changelog for Claude Code development sessions, tracking file changes, test results, and git commits.

git

Safe, protocol-driven Git operations for committing, pushing, and PR management using the GitHub CLI (gh).

tanstack-integration-best-practices

Integration patterns and best practices for TanStack Query, Router, and Start. Ensures type-safe data flow, efficient SSR, and unified caching.

simple-skill

A testing skill designed to verify the functionality of the Skillet CLI by performing basic tasks and confirming completion.

speckit-workflow

A constitution-driven, spec-first development workflow for Claude Code and Codex, automating feature planning, implementation, and quality assurance through structured agentic loops.

dev-cycle

Interactive development workflow manager. Coordinates discovery, planning, review, and build phases using a specialized team of AI agents (Scout, Bob, Garry, Arlo) for consistent project delivery.

claude-oracle

Automated tool and MCP server discovery for Claude Code. Searches 17+ registries to find relevant skills, plugins, and tools before planning or when errors occur.

test-skill

A testing fixture for validating AI agent skill configurations and detecting rule violations.

english-text-editor

Provides targeted, concise English language editing and stylistic improvements for text without performing full rewrites.

multi-llm-advisor

Fetches expert perspectives from OpenAI Codex and Google Gemini for architecture, code reviews, and debugging, with transparent LLM synthesis.

lsp-setup

Automated LSP detection, installation, and configuration for intelligent code analysis, navigation, and diagnostics.