review-interface

Generate self-contained HTML annotation interfaces for reviewing JSONL data.

Updated Apr 29, 2026

Search Tags:#ui #LLM #review #traces #annotation #data-labeling

Ready to run

npx skills add https://github.com/MantisWare/BizForge --skill review-interface-mantisware

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: review-interface
Source: https://github.com/MantisWare/BizForge/tree/main/library/skills/workspace/review-interface
Command: npx skills add https://github.com/MantisWare/BizForge --skill review-interface-mantisware

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate self-contained HTML annotation interfaces for reviewing agent outputs, traces, and labeled data.

Core Features & Use Cases

Self-contained HTML UI that runs entirely in the browser with embedded data
Supports configurable annotation schemas, review modes, and progress tracking
Enables evaluation, auditing, and dataset labeling with exportable results

Quick Start

Launch a customizable, browser-based review UI for a given dataset and annotation task.

Frequently Asked Questions about review-interface

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

FAQPage Schema

How do I build a custom annotation UI for reviewing LLM traces?▼

To build a custom annotation UI for reviewing LLM traces, you can generate a self-contained HTML file with inline data, configurable label schemas, and review modes that runs entirely in the browser without a server.

Can I review agent outputs in a browser without setting up a backend server?▼

Yes, you can review agent outputs in a browser without a backend server by using a self-contained HTML annotation interface that embeds data inline and requires no server setup.

What is the best way to create a data labeling interface from JSONL data?▼

The best way to create a data labeling interface from JSONL data is generating a single self-contained HTML file with inline data, configurable label schemas, and progress tracking for human reviewers.

Does the annotation interface support configurable schemas for auditing tasks?▼

Yes, the annotation interface supports configurable schemas for auditing tasks, allowing teams to design custom review workflows, compare labeled data, and export results directly from the browser.

How do I export results from an HTML annotation review workflow?▼

To export results from an HTML annotation review workflow, you use the interface's built-in export functionality, which allows human reviewers to extract annotated data and comparison results directly from the self-contained file.