Skip to content
Back to skills

Confidence Scoring

ASecurity

SOP for assigning calibrated confidence scores to causal claims based

  • 417 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 5, 2026
research

Security analysis

A100/100

Scanned September 5, 2026

npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill confidence-scoring --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Confidence Scoring?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Confidence Scoring
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yogsoth-ai-confidence-scoring/badge)](https://www.skillsdirectory.com/skills/yogsoth-ai-confidence-scoring)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: confidence-scoring
description: SOP for assigning calibrated confidence scores to causal claims based
  on evidence quality and quantity.
execution: sop
---

# Confidence Scoring

Assign calibrated confidence scores to causal claims.

## Tool

CC file edit

## Protocol

1. Count supporting evidence (weighted by evidence hierarchy)
2. Count contradicting evidence (weighted similarly)
3. Calculate net confidence: support_weight / (support_weight + contradict_weight)
4. Adjust for mechanism plausibility (+0.1 if strong mechanism, -0.1 if no mechanism)
5. Update claim page frontmatter confidence field

## HARD-GATE

<HARD-GATE>
Confidence must be between 0.0 and 1.0. Must cite the evidence used in calculation.
</HARD-GATE>

## Yield

Returns: `{ claim: string, confidence: number, evidence_count: number }`

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…