Agent Skills Hub

auto-skill-generator

Research technical documentation and automatically generate ready-to-use software agent skills in markdown format.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

git-commit-formatter

Standardize git commits with conventional formatting, signatures, and automated context gathering for better project history.

documentation-standards

Standards for organizing, structuring, and maintaining project documentation to ensure consistency across user guides, development docs, and AI-assisted workflows.

mcp-client

Universal MCP client for connecting to any MCP server with progressive disclosure. Wraps MCP servers as skills to prevent context window bloat from tool definitions. Use for Zapier, GitHub, sequential thinking, and file operations.

memory

Manage project SSOT, memory, and cross-tool search. Guardian of decisions.md and patterns.md for Claude Code. Use for context retention, memory synchronization, and decision tracking.

anthropic-api

Expert guidance for building production-ready applications with Anthropic's Claude API. Covers SDKs, prompt caching, batch processing, streaming, tool use, and cost optimization strategies.

linear

Linear issue management and synchronization for LobeHub, featuring automated PR referencing, sub-issue tree decomposition, and status tracking.

context-cascade

A nested plugin architecture for Claude Code that optimizes context by dynamically loading playbooks, skills, and agents to save over 90% in token usage.

phase-5-validator

Automates finalization validation for project workflows by enforcing git compliance, documentation standards, and deployment readiness.

create-skill

Standardizes the process of creating and maintaining reusable Claude Code skills for packaging developer workflows and domain expertise.

goal-tracking

Cascading goal tracking system connecting 3-year vision to daily tasks. Automates progress calculation, stalled goal detection, and project-to-goal alignment for Obsidian vaults.