autoresearch
This skill runs an autonomous optimization loop to improve a measurable metric through systematic experimentation.
Identity proven by GitHub's verified organisation badge (Factory-AI)
- Agents
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode
- License
- No license stated
- Pin
- 7166a07pinned Oct 9, 2026
- Context cost
- about 4,000 tokenswhen the skill loads
- GitHub stars
- 110on factory-ai/factory-plugins
- Scripts
- 1 script
What it does
“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.”
Generated summary from the skill's own text
This skill runs an autonomous optimization loop to improve a measurable metric through systematic experimentation. It manages git branches, maintains experiment logs, and decides whether to keep or discard changes based on metric improvements. The agent repeatedly makes hypothesized changes, runs a benchmark script, evaluates results, and iterates until a termination condition is reached.
When to use it
- Optimizing a specific measurable metric like training loss, test speed, or build size
- Setting up long-running autonomous experiments with structured logging and resumability
- Systematically exploring code changes with automatic rollback of failed attempts
- Running multi-session optimization work that must survive context resets
When not to
- When the optimization target cannot be measured with a simple script
- Exploratory work without a clear, quantifiable success metric
- One-off quick experiments that do not need session continuity
Install
No license stated: install from the publisher's repository, and ask the author before you reuse or share it.
These commands install from the publisher's repository and need no account.
skills CLI
npx skills add factory-ai/factory-plugins --skill autoresearchInstalls from the repository's default branch, which may have changed since the commit we checked.
GitHub CLI 2.90 or later
gh skill install factory-ai/factory-plugins autoresearch@7166a0799e3dd39184068160b9caaa1e6469028aInstalls the commit we checked (7166a07).
Copy by hand
Download the folder at 7166a07 and put it in .claude/skills/autoresearch for Claude Code and in .agents/skills/autoresearch for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
Copy for your agent
A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.
Prompt
Install the agent skill "autoresearch" by Factory. Source, pinned to commit 7166a0799e3dd39184068160b9caaa1e6469028a: https://github.com/factory-ai/factory-plugins/tree/7166a0799e3dd39184068160b9caaa1e6469028a/plugins/autoresearch/skills/autoresearch 1. Download that folder at exactly this commit. Do not use the default branch. 2. Copy every file unchanged, keeping the folder structure, into .claude/skills/autoresearch/ for Claude Code and .agents/skills/autoresearch/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist. 3. Do not edit the files, and do not run any script in the folder unless I ask you to. 4. When you are done, list the files you copied and where you put them. Its license is restricted or not stated. Show me the license terms from the repository before you copy anything. Listing and checks: https://www.agentnative.dev/skills/factory/autoresearch
SKILL.md at the pin
The license of this skill does not let us show its files here.
Files
- SKILL.md17 KB · 91a1cc0943eb
- autoresearch_helper.py14 KB · 0b1b03872089
2 files, 31 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.
Skill folder on GitHub at 7166a07More from Factory
ban-type-assertions
This skill enables the TypeScript ESLint rule that bans `as` type assertions in a package, replacing them with compiler-verified alternatives like Zod…
Claude Code, Codex, Cursor +4 · about 1.6K tokens · pinned 6 days ago
browser-navigation
This skill enables agents to automate browser interactions including navigation, form filling, element clicking, screenshots, and data extraction from web…
Claude Code, Codex, Cursor +3 · about 2.5K tokens · pinned 6 days ago
create-pr
Creates a pull request with Conventional Commits formatting, templated body, and optional ticket linking.
Claude Code, Codex, Cursor +4 · about 2.2K tokens · pinned 6 days ago
droid-control
Automate terminals, browsers, and desktop applications by routing to specialized drivers for recording, testing, and generating visual demonstrations.
Claude Code · about 3.5K tokens · pinned 6 days ago
fix-knip-unused-exports
Fixes knip unused export violations by identifying their type (test-only, dead barrel re-export, or internally-only-used) and applying the appropriate fix…
Claude Code, Codex, Cursor +4 · about 2.4K tokens · pinned 6 days ago
follow-up-on-pr
This skill takes over an existing pull request, rebases it on the latest base branch, addresses reviewer feedback with code changes, runs local CI checks, and…
Claude Code, Codex, Cursor +4 · about 1.4K tokens · pinned 6 days ago
Related in Coding workflow
planning
This skill orchestrates multi-workflow projects with dependencies and shared data tables by creating a task graph in the orchestrator via the create-tasks tool.
by n8nOfficial publisher
Claude Code, Codex, Cursor +3 · about 2.4K tokens · pinned 6 days ago
progressive-building
This skill implements incremental workflow development for agents building or extending workflows.
by n8nOfficial publisher
Claude Code, Codex, Cursor +3 · about 1.4K tokens · pinned 6 days ago
workflow-builder
Builds and edits n8n workflows using the TypeScript SDK.
by n8nOfficial publisher
Claude Code, Codex, Cursor +3 · about 14.2K tokens · pinned 6 days ago
remotion-upgrade
This skill upgrades Remotion and its related packages to the latest stable version.
by RemotionOfficial publisher
Claude Code, Codex, Cursor +3 · about 460 tokens · pinned 6 days ago
remotion-upgrade
This skill upgrades Remotion and related packages across a project, automatically detecting the package manager and workspaces.
by RemotionOfficial publisher
Claude Code, Codex, Cursor +3 · about 460 tokens · pinned 6 days ago
final-release-review
Audits Python SDK release candidates or plans against the previous release, comparing diffs for regressions, API changes, and version compatibility.
by OpenAIOfficial publisher
Contains scripts
Claude Code, Codex, Cursor +3 · about 5.4K tokens · pinned 6 days ago
Open roles at Factory
5 of 7 open roles on the jobs board
- Solutions Engineer, Enterprise, West
San Francisco, CA, USA (On-site)
- Member of Deployed Staff
San Francisco, CA, United States (On-site)
- Software Engineer, Platform
San Francisco, CA, USA (On-site)
- Research Engineer
San Francisco, CA, USA (On-site)
- Software Engineer, Deployed
San Francisco, CA, USA (On-site)