94 packages found
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfa
Claude Code skill for autonomous, goal-directed iteration. /autoresearch <goal> builds a real-data benchmark harness, ca
A minimal CLAUDE.md template that turns any LLM CLI into a personal knowledge base. Drop in one file, start ingesting ar
借鉴 Karpathy LLM Wiki 的求职文档 Agent skill,把零散经历沉淀成经历库,一键生成简历和面试逐字稿,支持 Obsidian 和飞书
Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+ best pract
An autonomous research agent built on Karpathy's LLM Wiki— give it a topic, it researches the internet and builds a stru
Claude Code plugin — generate a complete project knowledge base from a single brief. Wiki, skills, guardrails, handoff p
Andrej Karpathy's LLM Wiki pattern as a Claude Code plugin — turn accumulated sources into a self-maintaining, scalable
Cross-CLI skill for Obsidian: turn your vault into a living AI-first second brain across Claude Code, Codex, Gemini, and
Turn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge grows with
🎨 Picasso Orchestrator: 1. Gate-scored bidirectional loop: Claude Code ↔ Claude Design. Brief → DESIGN.md → Generate →
Run a Karpathy-style planner/generator/evaluator agent loop in your repo: a manager negotiates a testable contract, then
Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built
Full-stack AI collaboration codex (CLAUDE.md / AGENTS.md / Cursor rules) distilled from Karpathy's four principles, GoMa
A cross-platform, file-based persistent memory and prompt bridge for Claude Code, claude.ai, and Antigravity IDE. Synchr
Governed shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audi
SIGNAL — Agent Skills: terse structured output (tiers, templates, checkpoints), git workflow skills (commit, push, PR, r
达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Eva
The Karpathy LLM Wiki pattern, productionized. MCP server that gives Claude a librarian for your Obsidian vault — graph
Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it wr
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops
The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills, 42 commands, 176+ plugins, 20 hooks, 15
A CLAUDE.md Generator and Maintenance tool for for Claude Code to create high-quality CLAUDE.md instruction files — alig
Skill for Claude, Cursor & Copilot that automates the Karpathy LLM Wiki workflow: ingest web, GitHub, and YouTube URLs i
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andr
Multi-agents collaboration plugin for Claude Code - orchestrate multiple AI agents (Codex CLI, Gemini CLI, etc.) for div
An opinionated, agentic life-OS for Claude Code — a markdown vault with daily/weekly/quarterly review skills baked in. I
A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems
Agent skills for Claude Code where every entry ships with receipts: accuracy-gated benchmarks vs baseline AND placebo. R
Multi-agent collaboration plugin for Claude Code - orchestrate multiple AI agents (Codex CLI, Gemini CLI, etc.) for dive
Hypothesis-driven problem solving for AI agents: probe, falsify, escalate — never blind-retry. MCP server + agent skill
AI Agent plugin for Autoresearch with AI (Claude, OpenClaw, etc) to improve anything!
A map of what AI tokens actually cost, and where they're wasted vs. well spent. Tools, research, practices, and copy-pas
your calendar, but yapping. Apple Calendar MCP server for Claude Desktop & Claude Code — 28 voices (Mom, Future-you, Gar
Claude Code skill: Run decisions, code, and plans through a council of 5 AI advisors with anonymous peer review. Based o
Claude Code skill for building persistent, interlinked knowledge bases from source documents. Knowledge is compiled once
Self-installing personal AI orchestrator. Hand the latest blueprint file to a Claude Code session and it builds a full m
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
A deliberately lite personal brain: Obsidian to browse, Claude Code for everything else. No vector DB, no embeddings, no
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and
A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvem
An "LLM wiki" upgraded to a real database — typed entities, graph relations, HTTP API, and a built-in natural-language a
obra/superpowers extended — 14→24 skills, 6 GadaaLabs engineering improvements, override infrastructure, one-command ins
Free, local, accurate and honest meeting transcription SKILL with speaker diarization for your AI agent or second brain
Transform YouTube videos into a compounding knowledge base with transcripts, vision analysis, and agentic search. Works
162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours!
Source-driven knowledge dossiers for Claude: ingest documents into a compounding wiki with traceable analyses, plans, ac
Your super agent for work: local-first, learn your working context in mins and never forget it.
Installable GitHub library of 1,500+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and mor