⚖️
AI EngineeringGo

Agent Judge

by alibaba

Agent Judge is an AI Engineering skill for Claude Code, published by alibaba in skill-up.

680 stars45 forkson alibaba/skill-upAdded 2026/08/24+13% in starsRepository updated 2026/08/21
View source on GitHubDownload repo ZIP
agent-skillsaiai-agentsalibabaskills
Install in seconds
Install Agent Judge
Copy Agent Judge into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/alibaba/skill-up/tree/main/proposals ~/.claude/skills/proposals

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/alibaba/skill-up.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
proposals/0002-agent-judge-specific-skill.md in alibaba/skill-up
Installs to
~/.claude/skills/proposals
Collection
One of 23 skills cataloged from this repository
Category
AI Engineering — 2451 skills

What Agent Judge does

Agent Judge adds judge-level skill installation for agent-based evaluation runs. Use it when the evaluator needs reusable rubrics or domain guidance separate from the skill under test.

Agent Judge is cataloged under AI Engineering on DirSkills. Agent Judge comes from a repository tagged agent-skills, ai, ai-agents, alibaba and skills.

Commands Agent Judge provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /toc

Frequently asked about Agent Judge

  • What else does alibaba publish alongside Agent Judge?

    Agent Judge is one of 23 skills that DirSkills catalogs from alibaba/skill-up, the repository it ships in. Its siblings there include Agent Judge Support, Code Quality Analyzer and Code Quality Reviewer. Each one is a separate skill with its own page in this directory, installs the same way Agent Judge does, and is maintained by alibaba in that same repository. The rest of the collection is listed on the alibaba/skill-up page.

  • How does Agent Judge compare to other AI Engineering skills?

    Agent Judge ranks #1775 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Judge against them. Open each page to compare what they document and how they install.

More from alibaba/skill-up

Agent Judge is one of 23 skills cataloged on DirSkills from alibaba/skill-up.

See all 23 skills →
⚖️
1w ago

Agent Judge Support

Agent Judge Support adds judge-side Skills to agent_judge evaluations so the reviewer agent can install and use separate rubric Skills. It is used when you need reusable, isolated review rules and audit data for scoring.
AI Engineering
68045
🔍
1w ago

Code Quality Analyzer

Code Quality Analyzer reviews code for correctness, maintainability, performance, and security. Use it when you want a static quality assessment, issue list, and actionable fix suggestions.
Quality
68045
🔍
1w ago

Code Quality Reviewer

Code Quality Reviewer reviews code changes and provides a detailed quality assessment with bug findings and actionable recommendations. Use it when you need a second pass on changes before merging or shipping.
Quality
68045
🔎
1w ago

Code Review Assistant

Code Review Assistant analyzes submitted code for bugs, security issues, performance problems, and error handling gaps. Use it when you want a structured review with specific findings and fix suggestions.
Quality
68045
🔍
1w ago

Code Review Helper

Code Review Helper analyzes code snippets or diffs for common issues like null pointer risks, unhandled exceptions, resource leaks, naming, and style. Use it when you want a review report with problems, suggestions, and a summary.
Quality
68045
📊
1w ago

Code Stats

Code Stats analyzes a codebase and reports file counts, line counts, largest files, and size by extension. Use it when you need a quick audit of project structure or want to know how much code is in a directory.
Data
68045

More AI Engineering skills

Agent Judge is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #1775 by stars among them.

Browse all AI Engineering skills →
📐
3w ago

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
3w ago

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
3w ago

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K