autoresearch-agent
Skill1 starsChanged 4 months agoNo licenceView on GitHub
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
- Deletes or force-pushes
7 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- darkweb19/skillsedited, first seen Nov 8, 2026
- Hassaan146/claude-skillsword for word, first seen Jul 25, 2026
- Hussain-Elfalah/Agentic-Skillsedited, first seen Jun 4, 2026
- csiddhant796-blip/claude-skills-collectionword for word, first seen May 10, 2026
- Arnav-0/claude-code-setupword for word, first seen Mar 28, 2026
- tumf/skillstheir own version, first seen Mar 24, 2026
Other versions7 projects use a version of this.
Word for word · 4
- Hassaan146/claude-skills★ 18100% same
- csiddhant796-blip/claude-skills-collection★ 2100% same
- Arnav-0/claude-code-setup★ 0100% same
- vbrevik/claude_code_skills★ 0100% same
Edited · 2
- Hussain-Elfalah/Agentic-Skills★ 283% same
- darkweb19/skills★ 0100% same
Wrote their own version · 1
- tumf/skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository429 other files it gives its agents.
- gstack/AGENTS.mdAGENTS.md
- gstack/CLAUDE.mdCLAUDE.md
- a11y-auditSkill
- ab-testingSkill
- ab-test-setupSkill
- ad-creativeSkill
- adversarial-reviewerSkill
- agent-decision-receiptsSkill
- agent-designerSkill
- agenthubSkill
- agent-protocolSkill
- agent-workflow-designerSkill
- agile-product-ownerSkill
- ai-act-readinessSkill
- aims-auditSkill
- ai-second-brainSkill
- ai-securitySkill
- analytics-dashboardSkill
- analyticsSkill
- analytics-trackingSkill
- andreessenSkill
- api-design-reviewerSkill
- api-test-suite-builderSkill
- apple-hig-expertSkill
- app-store-optimizationSkill
- arquiteto-de-empresaSkill
- atlassian-adminSkill
- atlassian-templatesSkill
- autoplanSkill
- aws-solution-architectSkill
- azure-cloud-architectSkill
- behumanSkill
- benchmark-modelsSkill
- benchmarkSkill
- board-deck-builderSkill
- board-meetingSkill
- board-prepSkill
- boardroomSkill
- boardSkill
- brand-guidelinesSkill
- brandkitSkill
- briefSkill
- browser-automationSkill
- browserstackSkill
- browseSkill
- business-growth-skillsSkill
- business-investment-advisorSkill
- business-operations-skillsSkill
- caio-reviewSkill
- campaign-analyticsSkill
- canarySkill
- capacity-plannerSkill
- capa-officerSkill
- captureSkill
- carefulSkill
- cavemanSkill
- cco-reviewSkill
- cdo-reviewSkill
- cfo-reviewSkill
- challengeSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
16 rules. 12 are common, 0 are distinctive, and 4 are very specific to this project.
12
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.