Research & Data

AgentClaw turns one-sentence ideas into reusable Claw capabilities. Build less boilerplate with declarative workflows, computer browser code file control, MCP, Skills, memory, knowledge bases, tracing, scheduling, and API/MCP publishing.

Pre-merge cross-model review skill for Claude Code. Runs 3 Codex (GPT-5) passes — standard review, adversarial chaos, test-coverage gaps — to surface bugs single-model reviews miss.

Claude Agent Skill: answer NHL questions with live data via the free public NHL API (stats, standings, scores, rosters, nationality filtering).

a claude code skill that runs a council of models on your question. each member gets its own personality, they critique each other anonymously, and a chairman picks the best-argued answer (not a yes-man average). ported from karpathy/llm-council.

AI Agent skills and workflows for a research-driven solo AI company.

Governance skill for Codex and Claude Code: search before writing, reuse existing architecture, control dependencies, and verify AI code changes.

Pattern Cards + SKILL.md auto-generated dal sistema Knowledge Intake (Agent Professor). Distill di 100+ contenuti AI/social analizzati. Letti automaticamente dagli agent Studios + Claude Code via SessionStart hook.

Self-implemented Harness architecture multi-agent system based on LangGraph & self-designed MCP protocol, with pluggable skills, resilience governance, RAG & conversation memory.

Reusable Codex/Claude-style AI skill folders for safe publishing, research briefs, case studies, outreach workflows, Etsy listings, web scraping, copy cleanup, and release automation.

Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing.

Persistent, resumable specs for AI coding agents. Deep research, iterative interviews, phased implementation, resume context. Claude Code plugin + universal skill (Codex, Cursor, Windsurf, Cline, Gemini CLI, Devin, Antigravity).

Exa web search as standalone Agent Skills — no MCP server, just an EXA_API_KEY. Company, people, papers, code, finance, personal-site & X search + lead generation for Claude Code, Codex, Cursor, OpenCode, Gemini CLI, and any SKILL.md agent.

V-model systems engineering rigor playbook and Codex skills

Codex skill for first-party Douyin creator analytics

Reusable Codex skill for recruiter-grade job search, ATS resume tailoring, market intelligence, outcome learning, and OSINT interview prep.

An agent-to-UI Claude skill that generates editable, screenshot-safe HTML slides and photos — fix wrong values and avoid text overlap before exporting to Canva, Figma, or Notion.

A Codex skill for engineering-oriented reading of RF, microwave, and antenna research papers, with focus on parameter extraction, simulation reproduction, and design insights.

Perplexity AI Deep Research Claude Skill

Free Claude skills from Great Question.

Official agent skills for Outbox (out-box.dev) — Claude/Cursor/Codex/+ skill for publishing HTMLs from your AI agent

紫苏叶方法 Perilla-Leaf Method · 通用「证据→推断」判断法 Claude skill — judge anything (good/bad, A vs B) by chaining evidence→inference, with a minimal HTML reasoning-path diagram

oracle 🔮 — a fortune-cookie-style Claude Skill that draws a playful, encouraging answer of the day (bilingual zh/en)

A hand-picked, personally tested collection of Claude Skills & MCPs — curated, not aggregated. Creative, design & marketing focus, with an opinionated verdict and install guide for each.

Claude skill that teaches Claude to analyze Python code quality using CRAPQuants — CRAP scores, complexity metrics, and diagnostics from 6 software engineering books. Works in Claude.ai, Claude Code, and the API. #claude #claude-skill #agent-skills #anthropic #code-quality #python #static-analysis #crap-metric #codescanner #Codereview