Know if your agency skills are actually effective
Know if your agent skill actually works. A lightweight evaluation harness that tracks a success rate across Claude Code, Codex, Pi, and Hermes.
Project overview
Caliper: Know if your agent skill actually works
Caliper is a lightweight evaluation harness for agent skills. Write a short spec of what "good" looks like, run it, and get a success rate you can track. Works with the agent you already use: Claude Code, Codex, Pi, or Hermes. Caliper installs the skill where the agent looks for skills and lets the agent choose. Teach your agent to evaluate: Or run it yourself:
You write a spec, a YAML file describing what "working" means. Either hand-write it or have /grill-skill generate it for you. --ablate runs the same tasks with that skill removed, and caliper compare diffs the two runs task by task: