autoresearch
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements.
Skill by Lua2147
Chalk Labs
Need help deploying autoresearch?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lua2147-autoresearch
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
autoresearch- Description
- Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
- License
- unknown
- Instructions
- 326 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "autoresearch" does not match folder "autoresearch-optimizer"
- files: referenced but missing: references/eval-guide.md
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from Lua2147/claude-toolkit-catalog
- 0.438score
architect-review
Lua2147
Use when reviewing system architecture or major design changes, evaluating scalability/resilience/maintainability impacts, assessing architecture compliance…
SkillDFreshness: D★ 2Claude Code +9 - 0.438score
automation-mcp
Lua2147
Control your Mac with mouse, keyboard, screen capture, and window management via MCP.
SkillDFreshness: D★ 2Claude Code +9 - 0.434score
agentic-orchestration-patterns
Lua2147
Context forking, parallel sessions, agent escalation/handoff, session state persistence, and hook lifecycle patterns for multi-agent Claude architectures.
SkillDFreshness: D★ 2Claude Code +9 - 0.434score
autoresearch
Lua2147
Karpathy's autonomous research loop — an AI agent iteratively runs experiments, evaluates results, and keeps improvements.
SkillDFreshness: D★ 2Claude Code +9 - 0.433score
create-auth-skill
Lua2147
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth.
SkillDFreshness: D★ 2Claude Code +9 - 0.225score
autoresearch-plugin
Lua2147
No description from the publisher yet.
SkillDFreshness: D★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Mar 20, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.753score
autoresearch
pedronauck
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements.
SkillBFreshness: B★ 641Claude Code +9 - 0.342score
autoresearch
marcioaltoe
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements.
SkillAFreshness: AClaude Code +9 - 0.278score
autoresearch
aresbit
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements.
SkillDFreshness: D★ 45Claude Code +9
More from Lua2147
- 0.438score
architect-review
Lua2147
Use when reviewing system architecture or major design changes, evaluating scalability/resilience/maintainability impacts, assessing architecture compliance…
SkillDFreshness: D★ 2Claude Code +9 - 0.438score
automation-mcp
Lua2147
Control your Mac with mouse, keyboard, screen capture, and window management via MCP.
SkillDFreshness: D★ 2Claude Code +9 - 0.434score
agentic-orchestration-patterns
Lua2147
Context forking, parallel sessions, agent escalation/handoff, session state persistence, and hook lifecycle patterns for multi-agent Claude architectures.
SkillDFreshness: D★ 2Claude Code +9 - 0.434score
autoresearch
Lua2147
Karpathy's autonomous research loop — an AI agent iteratively runs experiments, evaluates results, and keeps improvements.
SkillDFreshness: D★ 2Claude Code +9 - 0.433score
create-auth-skill
Lua2147
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth.
SkillDFreshness: D★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get autoresearch running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
autoresearch skill. Agent Mart. https://agentmart.dev/skills/lua2147-autoresearch (last updated 2026-10-24)