dag-confidence-scorer

Official

Calibrates agent confidence with factor scoring.

Authorcuriositech
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a structured approach to quantify and calibrate the confidence of DAG outputs by evaluating multiple contributing factors such as reasoning quality, source reliability, internal consistency, completeness, and explicit uncertainty.

Core Features & Use Cases

  • Multi-Factor Scoring: compute scores across reasoning, sources, consistency, completeness, and uncertainty.
  • Confidence Calibration & Thresholding: calibrate raw scores using historical accuracy, task difficulty, and model bias; determine actions (accept/review/iterate/reject) via thresholds.
  • Use Cases: DAG decision gating, iterative refinement, and risk-aware routing of outputs.

Quick Start

Run the scorer on a DAG output to obtain a calibrated confidence and a recommended action.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: dag-confidence-scorer
Download link: https://github.com/curiositech/windags-skills/archive/main.zip#dag-confidence-scorer

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.