OpenAgentSkill Registry Manifest
Skill: karpathy
Slug: gaasher-karpathy
Category: research
Description: Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor.

Agent fit:
- Decision: 62/100 Prototype first
- Primary fit: Research agents
- Role: Fallback candidate

Supply profile:
- Track: Research and knowledge work
- Scenario: Research agents
- Applicable agents: Claude Code, CLI, Codex, Cursor
- Maintenance: 2mo since push
- Risk: Needs review

Trust:
- Trust score: 73/100 Strong shortlist
- Audit: 75/100 Needs review

Attribution:
- Status: Registry indexed
- Source: github fast track
- Creator: gaasher
- Claim URL: https://www.openagentskill.com/skills/gaasher-karpathy#claim-this-skill

Install:
npx skills add gaasher/Agent-Loop-Skills --skill karpathy

URLs:
- Web: https://www.openagentskill.com/skills/gaasher-karpathy
- API: https://www.openagentskill.com/api/agent/skills/gaasher-karpathy
- Install API: https://www.openagentskill.com/api/skills/gaasher-karpathy/install
- Repository: https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy