Rebuild Branch
platformplatform/PlatformPlatform
Rebuild a stale branch by cherry-picking each commit onto a fresh branch off main, using a ralph-loop to validate each commit (build, test, format, lint, optional e2e) before moving on.
Autonomous experiment loop for optimization research. An agent skill from Factory-AI/factory-plugins.
Install Autoresearch
$ npx skills add Factory-AI/factory-plugins --skill autoresearch -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Factory-AI/factory-plugins autoresearch --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Factory-AI/factory-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/autoresearch/skills/autoresearch .claude/skills/autoresearch && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "autoresearch" agent skill from https://github.com/Factory-AI/factory-plugins/tree/master/plugins/autoresearch/skills/autoresearch into .claude/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Factory-AI/factory-plugins/tree/master/plugins/autoresearch/skills/autoresearchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Factory-AI/factory-plugins --skill autoresearch -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Factory-AI/factory-plugins autoresearch --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Factory-AI/factory-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/autoresearch/skills/autoresearch .agents/skills/autoresearch && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "autoresearch" agent skill from https://github.com/Factory-AI/factory-plugins/tree/master/plugins/autoresearch/skills/autoresearch into .agents/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Factory-AI/factory-plugins --skill autoresearch -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Factory-AI/factory-plugins autoresearch --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Factory-AI/factory-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/autoresearch/skills/autoresearch .cursor/skills/autoresearch && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "autoresearch" agent skill from https://github.com/Factory-AI/factory-plugins/tree/master/plugins/autoresearch/skills/autoresearch into .cursor/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Factory-AI/factory-plugins.git --path plugins/autoresearch/skills/autoresearch--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Factory-AI/factory-plugins --skill autoresearch -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Factory-AI/factory-plugins autoresearch --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Factory-AI/factory-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/autoresearch/skills/autoresearch .gemini/skills/autoresearch && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "autoresearch" agent skill from https://github.com/Factory-AI/factory-plugins/tree/master/plugins/autoresearch/skills/autoresearch into .gemini/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Factory-AI/factory-plugins autoresearchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Factory-AI/factory-plugins --skill autoresearch -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Factory-AI/factory-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/autoresearch/skills/autoresearch .github/skills/autoresearch && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "autoresearch" agent skill from https://github.com/Factory-AI/factory-plugins/tree/master/plugins/autoresearch/skills/autoresearch into .github/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Factory-AI/factory-plugins --skill autoresearch -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Factory-AI/factory-plugins autoresearch --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Factory-AI/factory-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/autoresearch/skills/autoresearch .opencode/skills/autoresearch && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "autoresearch" agent skill from https://github.com/Factory-AI/factory-plugins/tree/master/plugins/autoresearch/skills/autoresearch into .opencode/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
autoresearch- GitHub stars
- 111
- Token cost
- ~4.2k tokens
- SKILL.md length
- 1,511 words
- Files
- 2
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- None found
At a glance
Autonomous experiment loop for optimization research. An agent skill from Factory-AI/factory-plugins.
- Works in 9 steps: Gather Information → Create Branch and State Files → Initialize JSONL and Commit State Files → …
- The user wants to: - Optimize a metric through systematic experimentation (ML training loss
- SKILL.md covers Overview, Setup, The Experiment Loop and State Files Reference, plus 5 more sections
- Runs Python scripts from its folder; calls git, python3 and pnpm
What it does
Autoresearch is an agent skill from Factory-AI/factory-plugins. Autonomous experiment loop for optimization research. Use when the user wants to: - Optimize a metric through systematic experimentation (ML training loss, test speed, bundle size, build time, etc.) - Run an automated research loop: try an idea, measure it, keep improvements, revert regressions, repeat - Set up autoresearch for any codebase with a measurable optimization target Implements the autoresearch pattern with MAD-based confidence scoring, git branch isolation, and structured experiment logging.
Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `autoresearch_helper.py`).
It sits in Agent Workflows, covering Autonomous loops, Git workflow and Web performance. The repository describes itself as: Official Factory plugins marketplace.
When your agent uses it
- The user wants to: - Optimize a metric through systematic experimentation (ML training loss
- Etc.) - Run an automated research loop: try an idea
- Keep improvements
- Revert regressions
Example prompts
- “/autoresearch”
Requirements
- Python 3
Workflow steps
9 steps, taken from the step headings in SKILL.md.
- Gather Information
- Create Branch and State Files
- Initialize JSONL and Commit State Files
- Run Baseline
- Summarize Results
- Group Changes
- Resolve File Conflicts
- Create Clean Branches
- Verify and Report
What it can do on your machine
Read from SKILL.md and the folder at commit 7166a07. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
gitpython3pnpmuvbash
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, pnpm and uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Autoresearch loads about 4.2k tokens when it runs. Until then it costs about 130 tokens; SKILL.md has 1,511 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 1,511 words (~4,188 tokens).
“Autonomous experiment loop: try ideas, keep what works, discard what doesn't, never stop.”
- name
- autoresearch
- version
- 1.0.0
Files
SKILL.md and 1 other file in plugins/autoresearch/skills/autoresearch of Factory-AI/factory-plugins.
- SKILL.md
- autoresearch_helper.py
Open the folder on GitHubat commit 7166a07
Compare with similar skills
Autoresearch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Autoresearch this skillFactory-AI/factory-plugins | 111 | — | ~4.2k | Automated safety check: Pass | None | |
| Rebuild Branchplatformplatform/PlatformPlatform | 441 | — | ~2.1k | Automated safety check: Notes | MIT | |
| Darwin SkillHHU3637kr/skills | 145 | 1 repos | ~2.2k | Automated safety check: Pass | None | |
| AutoResearch LoopLearnPrompt/andrej-karpathy-skills | 110 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Karpathygaasher/Agent-Loop-Skills | 174 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Slate Ar Recipeudecode/plate | 17k | — | ~658 | Automated safety check: Pass | Custom licence |
Similar skills
Darwin Skill
HHU3637kr/skills
Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch.
AutoResearch Loop
LearnPrompt/andrej-karpathy-skills
Sets up an autonomous research loop where an agent runs experiments on git branches, logs results and proposes the next iteration while you approve each hypothesis change.
Karpathy
gaasher/Agent-Loop-Skills
A skill your agent uses 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.
Slate Ar Recipe
udecode/plate
Slate v2 Autoresearch recipe picker. An agent skill from udecode/plate.
- Official
Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
More from Factory-AI/factory-plugins
All 13 skills in this repoBan Type Assertions
Factory-AI/factory-plugins
Ban as type assertions in a package via the @typescript-eslint/consistent-type-assertions lint rule, replacing them with compiler-verified type-safe alternatives.
Browser Navigation
Factory-AI/factory-plugins
Automate browser interactions for web testing, form filling, screenshots, and data extraction.
Commit Security Scan
Factory-AI/factory-plugins
Analyze code changes for security vulnerabilities using LLM reasoning and threat model patterns.
Create PR
Factory-AI/factory-plugins
Create a pull request with Conventional Commits formatting, a templated body, and local verification.
Droid Control
Factory-AI/factory-plugins
Control terminal TUIs, browsers, and native desktop apps for testing, demos, QA, and computer-use tasks.
Fix Knip Unused Exports
Factory-AI/factory-plugins
Fix knip "Unused exports" violations. An agent skill from Factory-AI/factory-plugins.
Related
Categories
Questions about Autoresearch
What does Autoresearch do?
Autonomous experiment loop for optimization research. An agent skill from Factory-AI/factory-plugins. Autoresearch is an agent skill from Factory-AI/factory-plugins. Autonomous experiment loop for optimization research.
When should I use Autoresearch?
Autoresearch fits situations like: the user wants to: - Optimize a metric through systematic experimentation (ML training loss; etc.) - Run an automated research loop: try an idea; keep improvements; revert regressions.
How do I install Autoresearch in Claude Code?
Run `npx skills add Factory-AI/factory-plugins --skill autoresearch -a claude-code`. Or copy the skill folder (plugins/autoresearch/skills/autoresearch in Factory-AI/factory-plugins) into .claude/skills/autoresearch in your project. Claude Code loads it when a task matches its description.
How do I install Autoresearch in Codex?
Run `npx skills add Factory-AI/factory-plugins --skill autoresearch -a codex`. Or copy the skill folder (plugins/autoresearch/skills/autoresearch in Factory-AI/factory-plugins) into .agents/skills/autoresearch in your project. Codex loads it when a task matches its description.
Can I use Autoresearch in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Factory-AI/factory-plugins --skill autoresearch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autoresearch, .gemini/skills/autoresearch, .github/skills/autoresearch and .opencode/skills/autoresearch in your project.
What does Autoresearch need to run?
Going by SKILL.md and its folder, Autoresearch needs Python for the scripts in its folder and the command-line tools its instructions call (git, python3, pnpm, uv and bash). Our summary lists: Python 3.
Does Autoresearch access the network?
SKILL.md contains no URLs. Its commands use git and uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Autoresearch safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Autoresearch use?
No licence was found for Autoresearch or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Autoresearch use?
About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Autoresearch?
Skills that share tags, products or a category with Autoresearch: Rebuild Branch (platformplatform/PlatformPlatform, 441 stars), Darwin Skill (HHU3637kr/skills, 145 stars), AutoResearch Loop (LearnPrompt/andrej-karpathy-skills, 110 stars) and Karpathy (gaasher/Agent-Loop-Skills, 174 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Autoresearch?
Factory-AI (a GitHub organization) maintains it in Factory-AI/factory-plugins, which has 111 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 7, 2026.
Source: Factory-AI/factory-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.