Autoresearch Agent
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
Install
/plugin marketplace add ArogyaReddy/alirezarezvani-claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add ArogyaReddy/alirezarezvani-claude-skills --skill autoresearch-agentgit clone --depth 1 https://github.com/ArogyaReddy/alirezarezvani-claude-skills.git /tmp/alirezarezvani-claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/alirezarezvani-claude-skills/engineering/autoresearch-agent ~/.claude/skills/autoresearch-agentPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Autoresearch Agent > You sleep. The agent experiments. You wake up to results. Autonomous experiment loop inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch). The agent edits one file, runs a fixed evaluation, keeps improvements, discards failures, and loops indefinitely. Not one guess — fifty measured attempts, compounding. --- ## Slash Commands | Command | What it does | |---------|-------------| | `/ar:setup` | Set up a new experiment interactively | | `/ar:run` | Run a single experiment iteration | | `/ar:loop` | Start autonomous loop with configurable interval (10m, 1h, daily, weekly, monthly) | | `/ar:status` | Show dashboard and results | | `/ar:resume` | Resume a paused experiment | --- ## When This Skill Activates Recognize these patterns from the user: - "Make this faster / smaller / better" - "Optimize [file] for [metric]" - "Improve my [headlines / copy / prompts]" - "Run experiments overnight" - "I want to get [metric] from X to Y" - Any request involving: optimize, benchmark, improve, experiment loop, autoresearch If the user describes a target file + a way to measure success → this skill applies. --- ## Setup ### First Time — Create the Experiment Run the setup script. The user decides where experiments live: **Project-level** (inside repo, git-tracked, shareable with team):
Details
- Skill name
autoresearch-agent- Repository
- ArogyaReddy/alirezarezvani-claude-skills
- Path
engineering/autoresearch-agent/SKILL.md- License
- MIT
- Repo updated
- 17 March 2026
FAQ
What does the Autoresearch Agent skill do?
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
How do I install the Autoresearch Agent skill?
Claude Code plugin: /plugin marketplace add ArogyaReddy/alirezarezvani-claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Autoresearch Agent popular?
It lives in ArogyaReddy/alirezarezvani-claude-skills, which has 40 GitHub stars and 11 forks.
Related skills
AWS Solution Architect
40ArogyaReddy/alirezarezvani-claude-skills
Design AWS architectures for startups using serverless patterns and IaC templates. Use when asked to design serverless architecture, create CloudFormation templates, optimize AWS costs, set up CI/CD pipelines, or migrate to AWS. Covers Lambda, API Gateway, DynamoDB, ECS, Aurora, and cost optimization.
Ceo Advisor
40ArogyaReddy/alirezarezvani-claude-skills
Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making executive decisions, fundraising, or when user mentions CEO, strategic planning, board meetings, investor updates, organizational leadership, or executive strategy.
Code Reviewer
40ArogyaReddy/alirezarezvani-claude-skills
Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.
Board
40ArogyaReddy/alirezarezvani-claude-skills
Read, write, and browse the AgentHub message board for agent coordination.
Agenthub
40ArogyaReddy/alirezarezvani-claude-skills
Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.
C Level Advisor
40ArogyaReddy/alirezarezvani-claude-skills
10 C-level advisory agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, Executive Mentor. Multi-role board meetings, strategy routing, structured recommendations. For founders needing executive-level decision support.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.