Skip to content

Add autoresearch#1060

Closed
luiscantero wants to merge 3 commits into
github:mainfrom
luiscantero:main
Closed

Add autoresearch#1060
luiscantero wants to merge 3 commits into
github:mainfrom
luiscantero:main

Conversation

@luiscantero
Copy link
Copy Markdown
Contributor

Pull Request Checklist

  • I have read and followed the CONTRIBUTING.md guidelines.
  • I have read and followed the Guidance for submissions involving paid services.
  • My contribution adds a new instruction, prompt, agent, skill, or workflow file in the correct directory.
  • The file follows the required naming convention.
  • The content is clearly structured and follows the example format.
  • I have tested my instructions, prompt, agent, skill, or workflow with GitHub Copilot.
  • I have run npm start and verified that README.md is up to date.

Description

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.


Type of Contribution

  • New instruction file.
  • New prompt file.
  • New agent file.
  • New plugin.
  • New skill file.
  • New agentic workflow.
  • Update to existing instruction, prompt, agent, plugin, skill, or workflow.
  • Other (please specify):

Additional Notes

N/A


By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

Copilot AI review requested due to automatic review settings March 18, 2026 07:52
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds a new “autoresearch” Agent Skill to enable an autonomous, metric-driven experimentation loop (baseline → iterative edits → measure → keep/discard) for optimizing programming tasks, and registers it in the skills index.

Changes:

  • Introduce a new skills/autoresearch skill with detailed setup, loop, logging, and reporting instructions.
  • Add the new skill to the skills catalog table in docs/README.skills.md.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.

File Description
skills/autoresearch/SKILL.md New skill content defining the autonomous experimentation workflow and operating rules.
docs/README.skills.md Adds the autoresearch entry to the skills listing.

You can also share your feedback on Copilot code review. Take the survey.

Comment on lines +3 to +5
description: >-
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, autonomous coding loop.
DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.
```
experiment commit metric status description
```
Add `results.tsv` and `run.log` to `.gitignore` (append if not already present) so they stay untracked.
Comment on lines +197 to +202
- IMPROVED: Keep the commit. Update the "best" baseline.
Log status = "keep".
- SAME OR WORSE: Revert. `git reset --hard HEAD~1`.
Log status = "discard".
- CRASH: Attempt a quick fix (typo, import, simple error).
If unfixable after 2 attempts, revert and log status = "crash".
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants