Caliper

Evaluation harness that measures whether an AI agent skill actually works, across Claude Code, Codex, Pi, Hermes.

Desktopfreeglobal

This is an evaluation harness for AI agent skills that runs against Claude Code, Codex, Pi, or Hermes. Users write a specification describing what a working skill looks like, run it repeatedly to get a trackable success rate, and can remove a skill and re-run the same tasks to prove it is actually contributing. It suits developers building and maintaining AI agent skills who want to catch regressions.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Caliper - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Caliper to unlock →

Something wrong with this listing — dead link, not a real product, wrong info?

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Caliper (or something else) actually fits.

Try a problem