Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy''s autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Autoresearch: Autonomous Iterative Experimentation
An autonomous experimentation loop for any programming task. You define the goal and how to measure it; the agent iterates autonomously -- modifying code, running experiments, measuring results, and keeping or discarding changes -- until interrupted.
This skill is inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch), generalized from ML training to **any programming task with a measurable outcome**.
---
## Agent Behavior Rules
1. **DO** guide the user through the Setup phase interactively before starting the loop.
2. **DO** establish a baseline measurement before making any changes.
3. **DO** commit every experiment attempt before running it (so it can be reverted cleanly).
4. **DO** keep a results log (TSV) tracking every experiment.
5. **DO** revert changes that do not improve the metric (git reset to last known good).
6. **DO** run autonomously once the loop starts -- never pause to ask "should I continue?".
7. **DO NOT** modify files the user marked as out-of-scope.
8. **DO NOT** skip the measurement step -- every experiment must be measured.
…
The line at the top of this page pins the label git:20260825.81319f4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_i3lmktxhcddndvw2
GET https://markdownregistry.com/api/v1/resolve?ref=sebastiendegodez/skraft-plugin/autoresearch
GET https://markdownregistry.com/api/v1/blob/754179e987519dac86e01f79c1e015345d9b07c09f4bc34c324d89165d10fbd5
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
sebastiendegodez/skraft-plugin · .agents/skills/create-skraft-eval/SKILL.md · Use when creating, refreshing, expanding, or reviewing a SKRAFT Vally skill evaluation at…
sebastiendegodez/skraft-plugin · .agents/skills/genesis/SKILL.md · Use this skill BEFORE drafting any agentic primitive module (skill, persona scoping file, scope-attached rule file…
sebastiendegodez/skraft-plugin · .github/skills/agentic-workflows/SKILL.md · Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.
sebastiendegodez/skraft-plugin · plugins/skraft-backlog/skills/backlog-review-lenses/SKILL.md · Use when a triage report, a sprint proposal, refined stories or a refinement proposal for one issue must pass an…
sebastiendegodez/skraft-plugin · plugins/skraft-backlog/skills/github-issue-search/SKILL.md · Use when finding GitHub issues to work on, exploring a backlog by labels, milestones or assignees, finding issues…
sebastiendegodez/skraft-plugin · plugins/skraft-backlog/skills/issue-refinement/SKILL.md · Use when transforming raw issues or feature requests into well-structured user stories with acceptance criteria. Covers…
sebastiendegodez/skraft-plugin · plugins/skraft-backlog/skills/issue-triage/SKILL.md · Use when triaging GitHub issues by assigning labels, priority, effort estimates, or detecting duplicates. Covers triage…
sebastiendegodez/skraft-plugin · plugins/skraft-backlog/skills/refinement-proposal/SKILL.md · Use when reviewing one GitHub issue and proposing its refinement as a comment: Definition of Ready check, Fibonacci…
sebastiendegodez/skraft-plugin · plugins/skraft-backlog/skills/sprint-planning/SKILL.md · Use when planning sprint content, prioritizing stories within milestones, estimating capacity, or analyzing dependency…
github/awesome-copilot · skills/autoresearch/SKILL.md · Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable…
orchestra-research/ai-research-skills · 0-autoresearch-skill/SKILL.md · Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid…
ericosiu/ai-marketing-skills · autoresearch/SKILL.md · Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated…
yeachan-heo/gajae-code · packages/coding-agent/src/defaults/gjc/skills/autoresearch/SKILL.md · Goal-directed research missions that interleave web research with data experimentation and end on a structured…
