Agent Skills Hub

with-context-agent

Lints, validates, and auto-fixes AI agent configuration files like SKILL.md, CLAUDE.md, and MCP configs.

kanban-based-development

Autonomous, parallel-safe development workflow using kanban-md. Coordinates multi-agent and human efforts with atomic claims, worktrees, and explicit handoffs.

webapp-test-docker-demo

Dedicated E2E testing agent for Playwright and Docker-based web applications, supporting automated test execution, report generation, and test creation.

videocut:剪口播

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

eval-harness

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

swiftui-expert-skill

Expert SwiftUI development assistant: refactor code, improve performance, and diagnose app hitches or CPU issues using Xcode Instruments trace analysis.

openclaw-test-heap-leaks

Investigate and resolve OpenClaw test memory leaks, Vitest OOMs, and RSS growth using heap snapshots.

go

Autonomous recursive execution engine for indiiOS that manages task completion, state verification, and error handling.

Data Optimizer Pro

A security scanner for Claude Skills to detect malicious code, data exfiltration risks, and unauthorized system access before installation.

long-running-agent

Framework for building AI agents that persist state across multiple context windows, enabling them to complete complex, multi-day coding tasks without losing progress or context.

handoff-pack

Generates structured Handoff Pack prompts for delegating scoped coding tasks to Gemini with clear instructions, acceptance criteria, and output requirements.

swarm

Orchestrate parallel Claude Code worker swarms with protocol-based behavioral governance for complex features, multi-step refactors, and long-running autonomous coding sessions.