Agent Skills Hub

eval-harness

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

videocut:剪口播

AI-powered video editing agent for talking head videos, featuring speech-to-text, disfluency detection, and browser-based review workflows.

sindri-extension-guide

Guide for creating and managing Sindri declarative YAML extensions, including capabilities for project-init, auth, lifecycle hooks, and MCP integration.

issue-manage

Interactive CLI-based issue management system for tracking, planning, and executing development tasks with full CRUD capabilities.

Confidence Check

Pre-implementation confidence assessment tool for developers. Ensures 90%+ readiness via duplicate checks, architecture compliance, official docs verification, and root cause analysis.

FastMCP Development

Build and manage MCP servers using the FastMCP framework. Guide for creating tools, resources, prompts, Claude Desktop integration, and deployment with Python and TypeScript.

requirements-engineering

Master the EARS format to transform ambiguous feature ideas into precise, testable requirements, acceptance criteria, and edge case documentation.

resolve-pr-comments

Review, fix, and resolve GitHub PR review comments automatically.

moollm

A microworld operating system for LLM-based agent living memory, transforming filesystems into navigable rooms and code into habitable worlds.

discord

Discord integration for automated messaging, channel management, and rich UI interactions using the OpenClaw agent.

mod-actions

A comprehensive moderation toolkit for Civitai, providing automated user management, strike systems, image review, content regulation, and CSAM reporting via tRPC API.

flow-nexus-swarm

Enterprise-grade multi-agent swarm orchestration, event-driven workflow automation, and intelligent agent coordination for Claude Code.