Skills
.Work. You
Rest

eval-summary

Official

Audit readings.ts summaries against KR originals.

Education & Research#education#markdown#quality-assurance#evaluate#readings.ts#kr-translation
Authorteam-attention
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the validation of readings.ts summaries by comparing them to the original Korean Markdown, identifies gaps, and proposes improvements. It helps maintain translation quality and consistency across reading materials.

Core Features & Use Cases

  • Automated summary validation: Compare tldr, learningGoals, chapterSummaries, motivation, and keyTakeaways between original and KR translations.
  • Issue tracking and suggestions: Generate improvement recommendations per issue and request user confirmation before applying changes to readings.ts.
  • Use Case: A maintainer runs /eval-summary week1 to verify all weekly summaries, then iteratively refines readings.ts based on the report.

Quick Start

Run the eval-summary skill for a whole week or a specific reading:

  • /eval-summary week1
  • /eval-summary week1/deep-dive-llms
  • /eval-summary week1/how-openai-uses-codex

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: eval-summary
Download link: https://github.com/team-attention/stanford-cs146s-kr/archive/main.zip#eval-summary

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 223,000+ vetted skills library on demand.