discover-confidence

Name: discover-confidence
Availability: InStock
Author: Theo

Score blueprint markdown files against a deterministic rubric and output JSON reports.

Updated May 13, 2026

Search Tags:#evaluation #blueprint #deterministic #rubric #quality-assurance #score

Ready to run

npx skills add https://github.com/usetheodev/theo-ui --skill discover-confidence

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: discover-confidence
Source: https://github.com/usetheodev/theo-ui/tree/main/.claude/skills/discover-confidence
Command: npx skills add https://github.com/usetheodev/theo-ui --skill discover-confidence

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) components.

What problem does it solve?

Score blueprints against a deterministic rubric to ensure consistent, auditable quality judgments in AI discovery workflows.

Core Features & Use Cases

Deterministic evaluation of blueprint structure: coverage, references, completeness, and smells.
Reproducible scoring with transparent outputs for audits and reviews.
Use Case: Run /discover-execute to generate a blueprint score report used to guide merges and improvements.

Quick Start

Invoke the /discover-execute process with a blueprint slug or path to generate a score report.

Frequently Asked Questions about discover-confidence

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I score a blueprint against a deterministic rubric for quality assurance?▼

To score a blueprint for quality assurance, you need a Python runtime, a rubric loaded from project templates, and the blueprint markdown file on disk. The process evaluates research coverage, reference citations, completeness, and structural smells to produce a reproducible score.

Can I evaluate blueprint completeness without making model calls?▼

Yes, you can evaluate blueprint completeness without model calls. This deterministic scoring mechanism operates independently of model inference, using a fixed rubric loaded from templates to assess structural smells and coverage, ensuring a reproducible score report every time.

What does deterministic blueprint evaluation include in the JSON score report?▼

Deterministic blueprint evaluation outputs a JSON score report containing per-dimension scores, a final score, a verdict, and hard-cap details. It assesses research coverage, reference citations, blueprint completeness, and structural smells to provide transparent quality judgments.

Does blueprint scoring require any specific dependencies or runtime environments?▼

Blueprint scoring requires a Python runtime and the pyyaml dependency to load the rubric configuration. You also need the blueprint markdown file saved on disk, allowing the deterministic evaluation scripts to parse and score the document locally.

Why use a deterministic rubric instead of model-based evaluation for blueprint reviews?▼

A deterministic rubric ensures consistent, auditable quality judgments for blueprint reviews. Unlike model-based evaluation, it provides a reproducible score by applying fixed criteria to research coverage and structural smells, eliminating variance in quality assurance workflows.

How do I integrate deterministic blueprint scoring into an AI discovery workflow?▼

You integrate deterministic blueprint scoring by running it within the discovery workflow after generating a blueprint. It assesses the blueprint against a rubric to produce a score report, which guides merges and improvements during the discovery process.