Research & Data

Fail-closed Codex/Claude Code skill for crypto quant alpha research - Stage 0, falsification, provider concordance, promotion gates

A curated collection of OpenClaw AI agent skills — workspace optimization, diagram generation, search, self-improvement, and more.

End-to-end pipeline framework for turning crypto/AI hotspots into shipped GitHub repos backed by ChainStream (or pluggable) on-chain data. 6 console scripts, 8-gate fail-closed publish, twice-daily auto-scan, Claude Code / OpenClaw skill bundle.

Generate interactive AI role-play training activities as self-contained HTML. Agent-first authoring via Agent Skills (Claude Code, Cursor, Gemini CLI, Codex).

AI agent methodology skill for Codex, Claude Code, and OpenCode: dialectical analysis, software architecture reasoning, product strategy, and project retrospection.唯物辩证批判思维 Skill — 基于毛选方法论的 AI 底层思维框架的 coding 框架

Agent skill or AI-agent tooling repository surfaced by cross-model daily skill hunt.

Agent skill or AI-agent tooling repository surfaced by cross-model daily skill hunt.

Agent skill or AI-agent tooling repository surfaced by cross-model daily skill hunt.

Agent skill or AI-agent tooling repository surfaced by cross-model daily skill hunt.

Agent skill repository for AI-assisted workflows.

Claude Code plugin — Vucar operational skills for data architecture and query patterns

TEHIK AI software development skills, available as a Claude Code Plugin Marketplace

Claude Code plugin marketplace with reusable agentic skill patterns for reasoning, decision-making, and AI workflows.

Claude Code plugin marketplace — Specs-Driven development (sdd) and GitHub (gh) plugins

Accelerate Qwen3.5 KVCache with TurboQuant MLX-LM tools for prompt caching, quantized attention, and research-ready evals

Deploy the uncensored Qwen3.6-27B model with lossless abliteration and NVFP4 hardware quantization for optimized performance on Blackwell architecture.

面向中文非编程用户的 AI Coding 学习 Skill（Claude Code / Codex CLI）

Karpathy-style LLM Wiki as a Claude Code skill — persistent markdown knowledge base with ingest/query/lint/compile ops

A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

A comprehensive SEO audit command-line tool with 108 audit rules across 12 categories. Analyze any website for SEO best practices, Core Web Vitals, security headers, structured data, accessibility, and more.

Static linter for AI agent configs (skills, rules, hooks, plugins). Catches vague triggers, unsafe commands, missing metadata, and trust issues. Runs as a read-only MCP server — one command setup, auto-triggers on edit.

STDIO based MCP server to collect and rank job postings data to be used later with skills and agents and save tokens

个人知识库数据 Agent - 学习 Agent 开发核心技术栈（Tool Use / RAG / Skills / MCP / Memory / Multi-Agent）

Agent skill repository for AI-assisted workflows.