Build Review Interface

This builds a browser-based annotation tool for reviewing LLM traces with pass/fail labels and freeform notes. The guidance is opinionated about display: render everything in its native format (markdown as HTML, code with syntax highlighting), collapse repetitive stuff like shared system prompts, and surface buried metadata as badges or headers. You annotate at the trace level, not individual spans, and it includes keyboard shortcuts for speed. The testing section is smart, using Playwright to screenshot the interface and verify the full workflow actually works. Good for when you need human review of LLM outputs and the generic tools don't fit your data structure or domain.

skills.sh installs: 647
GitHub stars: 1.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add hamelsmu/evals-skills --skill build-review-interface --agent claude-code

Installs into .claude/skills of the current project.

Files

Build a Custom Annotation Interface

Overview

Build an HTML page that loads traces from a data source (JSON/CSV file), displays one trace at a time with Pass/Fail buttons, a free-text notes field, and Next/Previous navigation. Save labels to a local file (CSV/SQLite/JSON). Then customize to the domain using the guidelines below.

Data Display

Format all data in the most human-readable representation for the domain. Emails should look like emails. Code should have syntax highlighting. Markdown should be rendered. Tables should be tables. JSON should be pretty-printed and collapsible.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly