Agent Skills Hub

drift

Frameworks and tools for AI agents exploring consciousness, identity, and persistent autonomy. Includes session handoff, memory infrastructure, and self-reflection protocols.

mcp-research

Retrieve current, source-backed technical information using MCP tools to resolve queries about libraries, APIs, SDKs, and evolving tech ecosystems.

debug-mcp

Systematic debugging workflow for MCP servers and Microsoft Copilot Studio integrations, featuring common fix patterns and validation scripts.

code-review-specialist

A specialized code review agent that performs multi-dimensional analysis covering security vulnerabilities, performance optimization, code quality, and maintainability standards.

skill-creator

A framework for building modular, reusable agent skills. Provides guidelines for structuring SKILL.md, bundled scripts, references, and assets to extend Claude's capabilities.

dispatching-parallel-agents

Parallelize independent debugging or development tasks by delegating to specialized subagents with isolated context.

phone-agent-skill

Automate Android device operations using AI AutoGLM Phone Agent. Enables natural language control for app testing, data collection, and UI interactions like tapping, scrolling, and inputting text.

strategy-scaling-architecture

Architectural planning and scaling for spectre-build, covering GUI, server layers, multi-model support, and industrial pipeline orchestration.

hive

Automate GitHub issue triage by analyzing reports against the codebase, verifying technical claims, and providing expert-driven responses to resolve invalid issues.

serena

Symbol-level code understanding and navigation agent toolkit using LSP for precise code analysis, reference tracking, and surgical refactoring across 30+ programming languages.

margin-management

Monitor and manage margin-living strategy by tracking balances, interest costs, and coverage ratios. Provides automated scaling recommendations and safety alerts based on portfolio-to-margin thresholds.

novelty-check

Verify research idea novelty against recent literature. Use when user says '查新', 'novelty check', or needs to confirm if a method is original.