Research & Data

Daily Claude Code + Codex usage aggregates, powering maxghenis.com/usage

Sistema diario para crear contenido viral · 29 agentes · 15 commands · 32 knowledge files · 12 estructuras virales · 7 gatillos · 8 elementos notable · adaptado del Método Audience de Elias Mamã por Joseph Moreno · Zenith

A .NET 11 MCP server exposing Roslyn compiler analysis (16 tools: diagnostics, hover, references, code fixes) to AI coding agents. Works with Reasonix, Claude, Cursor.

A Claude Code plugin marketplace that codifies engineering craft: disciplined Python and data-engineering practice alongside deliberate session-knowledge workflows, packaged as reusable skills.

A native codebase awareness extension for the Pi coding agent that delivers analysis tools and hooks for AI agents, and also enables non‑Pi agents (via MCP, e.g., Cursor, Claude Code, Kimi‑code, Trae, Qoder, Codebuddy) to achieve full tool support like pi‑shazam.

Dockerfile and compose.yml for Claude Code with LiteLLM proxy

Personal Agent OS for Claude Code — 46 hooks, 3501 skills, 97 agents. Blocks rm -rf, prompt injection, pipe-to-shell at runtime. Apache 2.0.

AI-friendly CLI for turning HTML/Markdown drafts into Japanese PDF/PNG deliverables

Shield your terminal from AI agents. Aegis intercepts every shell command, auto-snapshots your data before dangerous operations, and asks before anything destructive runs. Works with Claude Code, Codex, Cursor, and any agent that uses $SHELL.

🚀 Deploy and manage vLLM with ready-made skills for modular automation, adhering to the Anthropics template for seamless integration.

A knowledge cycle for AI agents — one that grows with the people who shape it. Centered on the scarcity of human attention and judgment as agent capability grows; six phases keep behavior aligned with operator intent across sessions. ADRs, JSON schemas, and a dependency-free Python reference.

A modular LLM skill for epistemic operations and noetic analysis: a cognitive-security framework (SOC) for classifying discourse and diagnosing orientation, deformation, and concealment; routing engagements through matched case modules and tactics, techniques, and procedures (TTPs), grounded in sound reason and normative disposition.

Open-source Claude Code plugins for knowledge work — consulting, B2B sales, marketing, and strategic foresight.

Applied reasoning, persistent agent memory, context engineering, and human-governed trust for AI coding agents — Claude Code, Claude Cowork, Codex, Cursor, Antigravity. Compatible with Obsidian.

Codex skill for Hong Kong stock flow, southbound, ADR and short-position tape analysis

Codex skill for generating Xiaohongshu 9:16 text motion HTML demos

Codex skill for high-quality public internet research review without paid APIs.

paperGo-skill is a Codex skill for reviewer-grade research paper reproduction. It helps an agent move from a paper and optional author repository to a source-grounded reproduction plan, dataset manifest, missing-code audit, protocol coverage check, and evidence-backed result report.

draw.io compatible xml (bpmn2) claude skill

A Claude skill that turns your Strava data into coaching insight - analyzes runs, rides, swims, training load, and zones via the Strava MCP.

Claude Code skill: turn any folder of files into a navigable knowledge graph — clustered communities, interactive HTML, GraphRAG JSON + an honest audit report.

Claude Code skill: clear, evaluable academic prose — plain-empirical voice, no-hype rules, and evaluability rules that make every claim checkable in seconds

Codex skill for GitHub open-source commercialization analysis and HTML opportunity reports

Claude Code custom slash commands for Datadog TSE workflows