Research & Data

面向 OpenClaw / Codex Agent 的决策导向 deep research skill，强调任务路由、证据可追溯、current-state verification、反证约束与可审计交付。

Visible AI-driven robotics demos powered by VLM policies, MCP skills, and AI coding agents. Reviewable HTML reports — frames, maps, tool traces, scores — instead of buried terminal logs.

Catches AI prose before it ships. Density-based slop detector for Claude Code: 45 patterns + 150 vocab tells + 33 structure tells, calibrated against PubMed/arXiv data, with model fingerprinting for GPT/Claude/Gemini. Passes its own test.

Claude Code skills for medical research — literature search, reporting guidelines, statistical analysis, publication figures. Built by a physician-researcher, tested on real publications. MIT licensed.

Personal collection of agent skills for Claude Code and the open agent skills ecosystem (skills.sh)

APS Framework project template: agents, skills, commands and scripts for creating .NET Azure Functions and ASP.NET Core Web Apps with APS packages.

Unified audit logging, policy enforcement, and sanitization for VMware MCP skills

Методист-наставник по самостоятельному изучению иностранных языков — скилл для Claude Code. Строит и пересматривает доказательный (SLA) план обучения по дням: setup / review / adjust.

Catch your AI agent lying about "done" A one-file proof-gate for Claude Code, Cursor & Codex. it must verify before it can finish

170+ Claude Code / Codex skills. Production-grade skills system for web apps & mobile architecture, APIs, databases, web, mobile, AI, security, UX, SaaS, and ERP engineering. Encodes reusable engineering judgment through layered baseline and specialist skills to help generate secure, scalable, maintainable, high-performance software systems.

Agent skills - Fundamental Research of Listed Companies and other utilities

Codex skill for disciplined evidence-driven research exploration loops

Claude Code skill that enables Claude to extract, analyze, reverse engineer iOS apps

Hermes Agent skill for Chinese mutual fund portfolio management — analysis, DCA optimization, rebalancing, daily reports

Binance historical data hosted on Github Pages with TypeScript and Python libraries, comes with Claude Skill. Updates every day via Github Actions.

Curated collection of Claude Code skills for automation, data extraction, code generation, and productivity. Drop-in skills for Claude AI to enhance your workflow.

This package ports the useful parts of Hermes-style self-improvement into native Codex skills,It does not modify model weights. It builds an auditable external learning loop using Codex skills, local memory files, rollout summaries, session search, and optional automations.

Type a market category -> an auto-built, cited, structured competitive landscape. Built on the context.dev API. Includes a pricing tracker, an honest extraction report-card, and a Claude-Code agent-skill.

paper-md-zh-translator is a Codex skill for translating extractable-text English life-science papers into searchable Simplified Chinese PDF deliverables.

Hardening skill for Solana cross-program invocations (CPI), with first-class coverage of the return-data spoofing exploit class. Claude Code / Codex skill for the Solana AI Kit.

Codex skill for SVG floorplan ontology extraction and renovation proposal reports

A Claude Code/Codex skill for filling Word and Excel forms from reusable, source-backed reference data.

Codex skill for AI product PM brainstorming, architecture, prompt discipline, and GitHub prototype research

A Claude skill that teaches AI the structure of a real Rojo Roblox project: filesystem layout, Wally packages, Knit services and controllers, ProfileService data, and live Roblox Studio (MCP) workflows. Open source.