superpowers-bench

Can your agent pick the right skill without being told?

You give your agent a set of skills. You describe a task. Does it figure out which skills to use - or does it need hand-holding?

superpowers-bench measures how well coding agents (Claude Code, Codex, OpenCode) discover and invoke skills from [obra/superpowers](https://github.com/obra/superpowers) based on context alone. It tests two conditions: **no hints** (just the task prompt) and **with hints** (task prompt + a natural-language hint that implies the right workflow without naming it).

• Skill selection as the unit of measure - not code quality, not pass/fail on tests. Did the agent reach for the right tools?
• Apples-to-apples comparison - same 20 tasks, same skills, same grading. Just swap the agent.
• Baseline vs triggered - quantifies how much a well-written hint improves skill discovery without explicit instruction.

Quick Start

$ npm install
$ npm run fetch-skills            # download skill definitions
$ npm run bench -- run --condition claude --task explain_code
# ... agent runs, result appended to results/results.jsonl

$ npm run bench -- matrix --parallel 4   # run full benchmark
$ npm run bench -- report                # generate report

Install

**From source** (only method - this is a benchmarking tool, not a published package):

git clone https://github.com/kunche