Research & Data

Enhance academic workflows by auditing papers, verifying citations, and analyzing experiments with a research integrity plugin for Claude Code.

Local-first persistent memory for AI coding agents via MCP. Semantic search and session context for Claude Code, Cursor, and Codex.

Discover TokRepo assets from GitHub for AI coding agents and MCP tools with cross-platform search support

Manage, share, and safely publish Codex skills with automated sanitization, validation, and streamlined installation workflows for team use.

Explore Claude Code workflow notes, plugin patterns, and multi-agent orchestration research for clear insight into its architecture and skill system

Automate trading analysis for Vietnamese stock markets using AI-driven tools and the vnstock data layer to improve investment decision-making.

Personal pi agent configuration — prompts, extensions, skills, themes, and settings managed in version control with symlink-based bootstrap.

An AI-powered job hunting assistant. Set up your profile once, let the agent find and score jobs from Adzuna against your actual skills, research companies before you apply, and track everything on a dashboard.

Automate literature reviews with research skills for fetching arXiv papers, extracting technical details, and tracking citations for agent workflows.

Apply Warren Buffett’s investment framework to your financial analysis using this collection of Claude Code skills.

Production-grade scaffold for reproducible computational research — 10-stage DAG pipelines, ≥90% test coverage, cryptographic provenance (SHA-256 + steganographic PDF watermarking), multi-project workspace, AI-agent-ready with AGENTS.md / SKILL.md throughout.

Sammlung kleiner, kombinierbarer Claude-Skills im SKILL.md-Format (CC BY 4.0).

Multi-agent AI job search assistant deterministic FastAPI pipeline (search, TF-IDF/skill scoring, feedback learning) plus Claude Agent SDK/MCP agents for discovery, match explanations, resume tailoring, and a conversational assistant.

Provide standard AI/ML task definitions as portable skills for use with major coding agents like OpenAI Codex and Claude Code.

Personal Claude Code dotfiles — custom slash commands, skills, agents, and hooks, symlinked into ~/.claude/

Static analysis scanner for SKILL.md LLM agent skills with deterministic security findings.

Public MCP servers and Codex skills for practical agent workflows

Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.

VS Code Extension for searching, installing and managing Agent Skills (SKILL.md) for GitHub Copilot, Claude Code and AI coding assistants

Open-source agent skills for live sports data and prediction markets. Football, F1, Kalshi, Polymarket. Zero API keys. SKILL.md format.

A Unified Virtual Filesystem For AI Agents

LLM驱动的 A/H/美股智能分析：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US markets.

Installable Hive Intelligence agent skills for crypto MCP setup, discovery, and research workflows.

Unified Claude Code, Desktop, and Web skills storage