# AI Trust Scorecard

> Assess the evidence and explainability of database advisor recommendations.

- Skill: `rweisssieker-xp/ai-trust-scorecard` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rweisssieker-xp/ai-trust-scorecard`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rweisssieker-xp/ai-trust-scorecard/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: rweisssieker-xp (https://skillmd.com/u/rweisssieker-xp)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rweisssieker-xp/ai-trust-scorecard

---


# ai_trust_scorecard

Use this skill to score AI recommendations across explainability, safety, reproducibility, and governance.

Governance:
- Analysis-only scoring.
- Low trust requires more evidence before recommendation.
- Trust scores do not authorize production execution.

Output contract:
- `usp: "ai_trust_scorecard"`
- `trustScore`, `decision`
- `evidence`, `confidence`, `source: "analysis"`