Research & Data

Bias detection skill for PM, strategy, prompt, and LLM reasoning audits

OpenClaw skill for internet reading and signal gathering so agents can retrieve web context quickly.

Agent Skill for Claude: Build, query, validate, and reason over knowledge graphs. Adversarial fact validation, deterministic reasoning, JSON-LD schema.

44 open-source financial skills for AI agents — P&L, budgeting, tax prep, debt payoff, and more. Works with Claude Code, Wilson, Cursor, Codex, and Paperclip.

OpenClaw Skill for AWS China region pricing query, cost calculation, and quote generation

Open AI-agent skill pack for equity research and fundamental analysis.

A manager-led Codex skill pack for research-grade engineering, scientific workflows, and role-based subagent orchestration.

Claude Code Skill: 自动从 Boss 直聘发现、筛选、记录合适岗位，定时运行，开箱即用。

TODO: Messy Virgo Specific Agents & Skills

A package manager for Claude Code skills. Install once, use anywhere, pay only for what you use.

一款轻量非 RAG 架构的Agent 记忆框架。支持跨客户端记忆共享，并发协作，记忆治理等功能，适用于Vibe coding 项目经验总结，踩坑复盘沉淀。

Agent Skill that maps course learning outcomes to ABET EAC Student Outcomes for engineering accreditation documentation.

Extract accurate YouTube video transcripts quickly and easily with a reliable API built for fast, scalable access and integration.

Xueqiu stock data CLI for AI agents — 30 commands for A-shares, HK, US stocks and funds.

Agent skills for EVM Copilot — competitive intelligence for the EVM ecosystem including smart contract analysis.

北京花粉实时监测与预报 Agent Skill — supports Claude Code, Codex to query live pollen data, trends, and allergy risk for all 16 Beijing districts.

Autonomous research loop skill for LLM agents — inspired by Karpathy's autoresearch. Define a goal, let the agent iterate.

Autonomous research agent with auto-improving skills

The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions.

utonomous AI research loop skill - modify, verify, keep or discard, repeat. PIVOT/REFINE escalation, cross-run learning, works with Codex, Claude Code, OpenClaw, and any agent.

Open-source Claude Code skills, agents, and slash commands for AI-powered penetration testing, bug bounty hunting, and security research

Colosseum Copilot — AI agent skill for Solana/crypto startup research

Paperzilla Agent skills for OpenClaw, Claude Cowork/Code, Codex, ...

AI Agent Skills for Computer Vision Engineers, Researchers