SkillsLLM
CategoriesBlogAI NewsAbout
HomeAI Agentsautoresearch

autoresearch

by uditgoenka

Pending

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

372stars
34forks
Added 3/14/2026
View on GitHubDownload ZIP
AI Agentsaiautonomous-agentautoresearchclaudeclaude-codeiterationkarpathyproductivityskill
Installation
# Add to your Claude Code skills
git clone https://github.com/uditgoenka/autoresearch
README.md

Claude Autoresearch Skill

Turn Claude Code into a relentless improvement engine.

Based on Karpathy's autoresearch — the principle that constraint + mechanical metric + autonomous iteration = compounding gains.

Claude Code Skill Version License: MIT Based on


Commands Reference

| Command | Description | Since | |---------|-------------|-------| | /autoresearch | Run the autonomous iteration loop (unlimited) | v1.0.0 | | /loop N /autoresearch | Run exactly N iterations then stop | v1.0.1 | | /autoresearch:plan | Interactive wizard: Goal → Scope, Metric, Verify config | v1.0.2 | | /autoresearch:security | Autonomous STRIDE + OWASP + red-team security audit | v1.0.3 | | /autoresearch:security --diff | Delta mode — only audit files changed since last audit | v1.0.3 | | /autoresearch:security --fix | Auto-fix confirmed Critical/High findings after audit | v1.0.3 | | /autoresearch:security --fail-on critical | Exit non-zero if severity threshold met (CI/CD gate) | v1.0.3 | | /loop N /autoresearch:security | Bounded security audit (N iterations) | v1.0.3 |

Security audit includes: STRIDE threat model, OWASP Top 10 (70+ checks), 4 red-team adversarial personas (Security Adversary, Supply Chain Attacker, Insider Threat, Infrastructure Attacker), proof-of-concept validation, structured report folder, historical comparison.

Flag Combinations

# Full combo: delta + auto-fix + CI gate
/loop 15 /autoresearch:security --diff --fix --fail-on critical

# CI/CD: quick delta check, block on criticals
/loop 5 /autoresearch:security --diff --fail-on critical

# Overnight: comprehensive audit with auto-remediation
/autoresearch:security --fix

# Plan then run: wizard builds config, launches immediately
/autoresearch:plan

Quick Decision Guide

| I want to... | Use | |--------------|-----| | Improve test coverage / reduce bundle size / any metric | /autoresearch or /loop N /autoresearch | | Don't know what metric to use | /autoresearch:plan | | Run a security audit | /autoresearch:security or /loop 10 /autoresearch:security | | Red-team my codebase | /autoresearch:security (includes 4 adversarial personas) | | Audit only changed files (PR review) | /autoresearch:security --diff | | Auto-fix security issues | /autoresearch:security --fix | | Block CI pipeline on vulnerabilities | /autoresearch:security --fail-on critical |


What Is This?

A [Claude Code skill](https://d...

Comments (0)
to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

n8n

by n8n-io

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
179,165
55,789
TypeScript
MCP Serversaiapis
View details
gemini-cli

by google-gemini

An open-source AI agent that brings the power of Gemini directly into your terminal.
97,754
12,257
TypeScript
AI Agentsaiai-agents
View details
everything-claude-code

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
76,097
9,506
JavaScript
AI Agentsai-agentsanthropic
View details
TrendRadar

by sansan0

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。
48,947
22,642
Python
MCP Serversaibark
View details
awesome-claude-skills

by ComposioHQ

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
44,141
4,446
Python
AI Agentsagent-skillsai-agents
View details
chatgpt-on-wechat

by zhayujie

CowAgent是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长。同时支持飞书、钉钉、企业微信应用、微信公众号、网页等接入,可选择OpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI,能处理文本、语音、图片和文件,可快速搭建个人AI助手和企业数字员工。
42,209
9,826
Python
AI Agentsaiai-agent
View details