output-scoring-enlisted

Scores the quality of an AI legal output before it goes out, in two layers: objective (mechanically checkable - do the citations exist, are the provisions and dockets real) and subjective (LLM-as-judge on a 1-5 rubric: legal correctness, completeness, clarity, jurisdiction fit, grounding/anti-hallucination). Returns a scorecard and a decision: send / revise / full verification. A layer above the deliverable - it does not write, it scores. Jurisdiction-neutral. Pairs with reviewer-en, adversarial-legal-review-en and legal-syllogism-en. Use when: "score this output", "is this ready to send", "quality of this legal answer", "scorecard for the deliverable", "rubric check" - before sending an opinion, memo, or brief.
matematicsolutions/awesome-matematic-skills-en · ★ 0 · AI & Automation · score 76

Install: claude install-skill matematicsolutions/awesome-matematic-skills-en

# Output scoring - a scorecard before you send ## Philosophy **Before you send it, score it - and keep what is checkable apart from what must be judged.** An AI output can read smoothly and still be wrong. This skill scores it in two layers: objective (facts you can verify mechanically) and subjective (quality you have to judge against an explicit rubric). Mixing the two is where false confidence comes from - "sounds right" is not "the citations check out". It **scores**; it does not write or send. The decision is the lawyer's; the scorecard is the basis. ## Layer 1 - objective (mechanically checkable) Delegate, do not guess: - **Citations and provisions** - do they exist in the source verbatim; were they all caught. - **Dockets / identifiers** - real and correctly written. - **Completeness** - did any RED finding drop out of the summary. The objective result is binary per item: matches / does not. Even one mismatched citation means the output is not ready, whatever the subjective score. ## Layer 2 - subjective (1-5 rubric, LLM-as-judge) Score each dimension 1-5 with a one-sentence reason: | Dimension | 1 | 5 | |---|---|---| | Legal correctness | thesis wrong or unsupported | thesis sound and grounded in the rule | | Completeness | omits material issues | covers everything material to the question | | Clarity | muddled, inconsistent | precise, readable for the reader | | Jurisdiction fit | confuses systems/rules | correct for the governing law | | Grounding (anti-hal