Your prompt (optional) - for reference while you score. It stays on your machine; this page makes no network calls with your text.
Methodology: one point per check, equal weights; verdict bands 0–2 / 3–7 / 8–11 / 12, calibrated against sample prompts. OBSERVATIONALHeuristic weights are equal by design and not empirically derived; this measures specification completeness, not code quality. Calibration set: publishing in the companion repository.. This is a self-assessment heuristic from Delta: Closing the Specification Gap by Sandeep Dhuri (Acuity Press, 2026) — it measures specification completeness, not code quality. Scores are not stored, logged, or transmitted.
@misc{dhuri2026score,
author = {Dhuri, Sandeep}, title = {Delta: Closing the Specification Gap — score},
year = {2026}, url = {https://acuity.press/score/}
}