Skip to content

Search is only available in production builds. Try building and previewing the site to test it out locally.

Prompt Grade

Prompt Grade scores each prompt you send against a seven-point rubric. The judge runs after the prompt is captured and produces a single letter grade from A+ down to F.

Each prompt is checked against seven habits, each rooted in Anthropic’s Claude Code prompting guide. Not every check applies to every prompt — the judge marks which checks are applicable based on intent (fix, plan, explore, etc.).

The seven checks roll up into four pillars (Clarity · Context · Verification · Workflow) — see the Skill page for the full list.

Each letter maps to a numeric score, rescaled to a 0–100 scale (A+ = 100, F = 0) so it lines up with the PRISM Score. APG is the mean across all scored prompts in the selected range.

APG = mean(prompt_score_0_100) across prompts where judge_status = "ok"

The headline number is APG; the badge next to it is the closest letter grade.

Weak · Fair · Good · Great.

  • Skill summarizes APG as a 0–10 score and breaks it down by pillar.
  • This page is the per-prompt drill-down — see which prompts pulled the average down and why.