Autoresearch Skill Andrej Karpathy — Data skill for Claude Code
Claude Code skill for autonomous, goal-directed iteration.
How to install Autoresearch Skill Andrej Karpathy
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Muminur/autoresearch-skill-Andrej-Karpathy and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Autoresearch Skill Andrej Karpathy does
Claude Code skill for autonomous, goal-directed iteration. /autoresearch builds a real-data benchmark harness, captures a baseline, and iterates with a regression gate until the goal is hit. Inspired by Andrej Karpathy's autoresearch.
Alternatives in Data
- Context Mode — Benchmark Results — Benchmarked against real outputs from popular Claude Code MCP servers, Skills, and dev tools 5.6k ★
- Deepdive — Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, clai 297 ★
- NERV UI V2 — Operations Console Component Library — Build web interfaces that feel like NERV designed them 194 ★
README
🔬 Autoresearch Skill
Autonomous, Goal-Directed Iteration for Claude Code
*Inspired by [Andrej Karpathy's autoresearch](https://github.com/karpathy/autoresearch) — extended into a universal, real-data benchmark-driven workflow for any engineering task.*
[](./SKILL.md) [](https://docs.claude.com/en/docs/claude-code) [](./LICENSE) [](https://github.com/karpathy/autoresearch) [](#)
╔════════════════════════════════════════════════════╗
║ MODIFY → VERIFY → REGRESS → KEEP / DISCARD → ∞ ║
╚════════════════════════════════════════════════════╝
✨ What is this?
**Autoresearch** is a Claude Code skill that turns a free-form goal like
/autoresearch reduce API p95 latency to 200msinto an **autonomous, self-correcting optimization loop** that:
- 🧠 Parses the goal into seven machine-readable slots
- 📦 Ingests real data (refusing synthetic corpora)
- 🛠️ Builds a single-file benchmark harness
- 📐 Captures a baseline + regression test count
- 🔁 Iterates — one atomic change at a time
- ✅ Keeps wins, 🗑️ auto-discards regressions, logs everything
- 🏁 Stops when the target metric is hit
No hand-holding. No "should I continue?" Just mechanical iteration until the goal is reached.
