Setting up an autoresearch experiment helps you optimize a file by collecting the right details. You choose a domain, a target file, an eval command, a metric, and a direction. You can also pick a built-in evaluator or use your own.
The /ar:setup command works in two ways. You can provide all details at once or use interactive mode to answer one question at a time. After setup, the tool checks your eval command and reports the baseline metric. Then you can run the optimization loop.
Global
mkdir -p ~/.claude/skills/setupProject
mkdir -p .claude/skills/setupSource Repository
Lark Drivelarksuite/cli
Organize Lark cloud files import export manage permissions and versions
Lark Eventlarksuite/cli
Stream Lark events in real time with simple CLI commands
Lark Workflow Meeting Summarylarksuite/cli
Turn your Lark meeting notes into organized weekly summaries with ease
Lark Approvallarksuite/cli
Easily manage Lark approval instances and tasks from your command line
Implementmattpocock/skills
Implement PRD or issue tasks with TDD tests typechecking and review
Executing Plansobra/superpowers
Load a plan review critically then execute each task with verifications
Subagent Driven Developmentobra/superpowers
Execute plans with fresh subagents per task and thorough reviews for fast iteration
Churn Preventioncoreyhaines31/marketingskills
Reduce customer churn with smart cancel flows and failed payment recovery