Use Case
Benchmark Store isn't just for solo use β teams can share skills and build consistent AI workflows across the organization. Use it when you need to initialize the benchmark database, compare skill scores with historical baselines, check whether there is dimension regression in the Pareto front, or check the quality grading standards. Not used for candidate scoring (with improvement-discriminator) or automatic improvement (with improvement-learner). This guide covers how to deploy Benchmark Store for your team, standardize prompts, and create shared workflows that everyone can use.
Install Benchmark Store in your project directory: .claude/skills/benchmark-store/
Commit the skill folder to your repository so the whole team has access
Document your team's standard prompts in a shared README
Use Benchmark Store in code reviews, standups, and planning sessions
Iterate: collect feedback from the team and refine your prompts
Copy these prompts and use them with your AI agent after installing Benchmark Store
How can my team use Benchmark Store together?
Set up Benchmark Store for our project so everyone can use it
Create a shared workflow using Benchmark Store for our team
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install benchmark-storeOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install benchmark-storeβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/benchmark-store/π‘Extract and place the folder at the path above, then restart your agent.