Self-improving prompt optimization using the Karpathy autoresearch pattern.

No licenceAuto-check: warningsAgent Workflows

Install Autoresearch Universal

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill --skill autoresearch-universal -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill autoresearch-universal --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
autoresearch-universal
GitHub stars
207
Token cost
~5.8k tokens
SKILL.md length
2,771 words
Files
3
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Self-improving prompt optimization using the Karpathy autoresearch pattern.

  • Works in 5 steps: Repo Discovery → Target Selection → Metric Definition → …
  • The user asks to optimize
  • SKILL.md covers Phase 1 — Repo Discovery, Phase 2 — Target Selection, Phase 3 — Metric Definition and Phase 4 — Baseline + Loop Setup, plus 2 more sections
  • Calls pytest, go and npx

What it does

Autoresearch Universal is an agent skill from balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill. Self-improving prompt optimization using the Karpathy autoresearch pattern. Scans any repo, suggests optimization targets, auto-defines binary eval metrics, and runs an autonomous generate-eval-score-mutate loop to improve prompts over time. Use when the user asks to optimize, improve, or run autoresearch on anything in their codebase.

Its SKILL.md is about 5.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `ARTICLE.md` and `README.md`).

It sits in Agent Workflows, covering Autonomous loops.

When your agent uses it

  • The user asks to optimize
  • Run autoresearch on anything in their codebase

Example prompts

  • “/autoresearch-universal”

Requirements

  • Node.js
  • Docker

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Repo Discovery
  2. Target Selection
  3. Metric Definition
  4. Baseline + Loop Setup
  5. Autoresearch Loop

What it can do on your machine

Read from SKILL.md and the folder at commit 4870864. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pytest
    • go
    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Autoresearch Universal loads about 5.8k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 2,771 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~5.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

  • WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:441
    1. **Never ask for permission to continue** once the loop has started. You are autonomous.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 2,771 words (~5,750 tokens).

“You are an autonomous research agent applying the Karpathy autoresearch pattern to optimize prompts and processes. You scan the repo, suggest targets, define binary eval criteria, and run a self-improving loop: generate outputs, evaluate them, keep winners, mutate the prompt…”

— opening of SKILL.md by balukosuri
name
autoresearch-universal

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files in the repository root of balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill.

  • SKILL.md
  • ARTICLE.md
  • README.md

Open the folder on GitHubat commit 4870864

Compare with similar skills

Autoresearch Universal next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Autoresearch Universal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Autoresearch Universal this skillbalukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill207—~5.8kAutomated safety check: WarnNone
Show Me Your Work Decision Logcursor/plugins11k8 repos~1.6kAutomated safety check: PassNone
Autoresearch Iteration Loopuditgoenka/autoresearch6.5k1 repos~2kAutomated safety check: PassMIT
Install Loop Engineeringcobusgreyling/loop-engineering11k1 repos~648Automated safety check: PassMIT
LoopyForward-Future/loopy3.2k—~3.9kAutomated safety check: PassMIT
AI Performance Improvement Plantanweai/pua20k2 repos~6.9kAutomated safety check: PassMIT

Similar skills

  • Official

    Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.

    11k GitHub starsUsed in 8 repos~1.6k tokens
    Agent WorkflowsAuto-check passed
  • Autoresearch Iteration Loop

    uditgoenka/autoresearch

    Runs an autonomous modify, verify, keep-or-discard loop against any metric, with subcommands for planning, debugging, fixing, security audits, shipping and more.

    6.5k GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed
  • Install Loop Engineering

    cobusgreyling/loop-engineering

    Installs Loop Engineering into a project through the single @cobusgreyling/loop CLI, scaffolding a report-only loop and a readiness score.

    11k GitHub starsUsed in 1 repo~648 tokens
    Agent WorkflowsAuto-check passed
  • Loopy

    Forward-Future/loopy

    Discover, find, compare, audit, repair, adapt, craft, run, debrief, save, and prepare repeatable AI-agent loops for publication.

    3.2k GitHub stars~3.9k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Pushes an agent to exhaust every option, investigate before asking and take initiative beyond the literal request, instead of giving up or waiting passively.

    20k GitHub starsUsed in 2 repos~6.9k tokens
    Agent WorkflowsAuto-check passed
  • LoopX Self Repair

    loopx-project/loopx

    Diagnoses surprising LoopX behavior, such as stale recommendations or tiny progress, assigns it to the responsible layer and repairs it at the lowest durable level.

    6.2k GitHub stars~2.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

Categories

Questions about Autoresearch Universal

What does Autoresearch Universal do?

Self-improving prompt optimization using the Karpathy autoresearch pattern. Autoresearch Universal is an agent skill from balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill. Self-improving prompt optimization using the Karpathy autoresearch pattern.

When should I use Autoresearch Universal?

Autoresearch Universal fits situations like: the user asks to optimize; run autoresearch on anything in their codebase.

How do I install Autoresearch Universal in Claude Code?

Run `npx skills add balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill --skill autoresearch-universal -a claude-code`. Or copy the skill folder (the balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill repository) into .claude/skills/autoresearch-universal in your project. Claude Code loads it when a task matches its description.

How do I install Autoresearch Universal in Codex?

Run `npx skills add balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill --skill autoresearch-universal -a codex`. Or copy the skill folder (the balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill repository) into .agents/skills/autoresearch-universal in your project. Codex loads it when a task matches its description.

Can I use Autoresearch Universal in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill --skill autoresearch-universal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autoresearch-universal, .gemini/skills/autoresearch-universal, .github/skills/autoresearch-universal and .opencode/skills/autoresearch-universal in your project.

What does Autoresearch Universal need to run?

Going by SKILL.md and its folder, Autoresearch Universal needs the command-line tools its instructions call (pytest, go and npx). Our summary lists: Node.js; Docker.

Does Autoresearch Universal access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Autoresearch Universal safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Autoresearch Universal use?

No licence was found for Autoresearch Universal or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Autoresearch Universal use?

About 5.8k tokens (SKILL.md is roughly 23k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Autoresearch Universal?

Skills that share tags, products or a category with Autoresearch Universal: Show Me Your Work Decision Log (cursor/plugins, 11k stars), Autoresearch Iteration Loop (uditgoenka/autoresearch, 6.5k stars), Install Loop Engineering (cobusgreyling/loop-engineering, 11k stars) and Loopy (Forward-Future/loopy, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Autoresearch Universal?

balukosuri (a GitHub user) maintains it in balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill, which has 207 GitHub stars. The repository was last updated on March 23, 2026.

Source: balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.