Agent Skills Hub

handoff

Create structured session handoff documents to ensure continuity when switching contexts, taking breaks, or ending your workday.

react

React component development guide for LobeHub, including styling with antd-style, layout building with @lobehub/ui, and routing management.

webapp-testing

Toolkit for testing local web applications using Playwright, featuring server lifecycle management, automated DOM inspection, and browser automation workflows.

conversation-log

Systematic technical conversation logging for developers and engineers. Captures decisions, implementation details, and session outcomes with factual precision.

cosense

A comprehensive automation skill for Cosense (formerly Scrapbox) enabling page reading, searching, creating, and safe editing via API.

doc-sync

Synchronizes and maintains CLAUDE.md and README.md documentation hierarchy across a repository to ensure consistent, just-in-time context for AI agents.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

dlt-skill

Create, manage, and debug dlt (data load tool) pipelines for ingesting data from APIs, databases, and custom sources into destinations like DuckDB, BigQuery, and Snowflake.

mcp-rails

Implement a full Model Context Protocol (MCP) stack in Rails. Connect to external servers, expose your Rails app as an MCP server, or manage subprocess MCP containers via Docker with OAuth 2.1 PKCE support.

debugging-strategies

Language-agnostic debugging framework: scientific method, stack trace analysis, logging strategies, and advanced techniques like Git bisect and rubber ducking.

paper-write

Drafts LaTeX research papers section-by-section using paper plans and research narratives with multi-model reviewer validation.

recursive-decomposition

Handles large-scale tasks by automatically breaking them down into manageable, recursive sub-tasks to overcome context window limits and improve reasoning accuracy on large codebases and document sets.