rai-discover-validate

Validate discovery analysis components using confidence-tier batching and export.

Updated Feb 4, 2026

Search Tags:#automation #workflow #validation #discovery #confidence #ai-review #module-batching

Ready to run

npx skills add https://github.com/fcastrillo/carbtrack-ai --skill rai-discover-validate

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rai-discover-validate
Source: https://github.com/fcastrillo/carbtrack-ai/tree/main/.claude/skills/rai-discover-validate
Command: npx skills add https://github.com/fcastrillo/carbtrack-ai --skill rai-discover-validate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Discovery validation often requires manual review of components after a discovery scan, which is time-consuming and error-prone. This skill automates the validation workflow using a confidence-tier model to auto-validate high-confidence components, batch-review medium-confidence modules, and flag low-confidence items for individual human review.

Core Features & Use Cases

Auto-validate high-confidence components based on analysis data (confidence >= 70).
Batch-review medium-confidence components by module to synthesize purposes and categories.
Individual review for low-confidence components with detailed signals.
Save updates to work/discovery/components-draft.yaml and export to components-validated.json.
Support audit trails and prepare data for graph integration via rai discover build.

Quick Start

Run /rai-discover-scan to generate analysis results, then run /rai-discover-validate to begin auto-validation

Frequently Asked Questions about rai-discover-validate

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

FAQPage Schema

How do I automate validation of discovery analysis results to reduce manual component review?▼

Automate discovery analysis validation using a confidence-tier workflow that auto-validates high-confidence components, batch-reviews medium-confidence modules, and flags low-confidence items for individual human review. This reduces manual checks from individual components to module-level batching.

What is confidence-tier workflow validation for component drafts?▼

Confidence-tier validation is a process that categorizes analysis artifacts by score, auto-validating entries with confidence >= 70, batching medium-confidence items by module to synthesize purposes and categories, and isolating low-confidence items for detailed manual review.

How do I finalize a components-draft with validated entries and export to JSON?▼

Finalize a components-draft by running the validation workflow to auto-populate auto_purpose, auto_category, and validation flags, saving updates to work/discovery/components-draft.yaml and exporting the validated data to components-validated.json.

Does discovery validation preserve audit trails for batch-processed modules?▼

Discovery validation preserves audit trails throughout the per-module batch processing workflow. It maintains validation flags and detailed signals for low-confidence components while preparing the validated data for subsequent graph integration.

Do I need to run a discovery scan before validating components?▼

You need to run a discovery scan first to produce analysis artifacts. The validation workflow applies to outputs where a scan generated the initial data, requiring these artifacts to begin auto-validating and batch-reviewing the components-draft.