Align Human

by agentscope-ai

Align Human is an AI Engineering skill for Claude Code, published by agentscope-ai in OpenJudge.

797 stars64 forkson agentscope-ai/OpenJudgeAdded 2026/08/23+1% in starsRepository updated 2026/08/03

View source on GitHub Download repo ZIP

agentagent-skillsai-agentalignmentevaluationgraderllmrewardreward-modelrlhfskill-mdskills

Install in seconds

Install Align Human

Copy Align Human 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/agentscope-ai/OpenJudge/tree/main/skills/eval_pipeline/03-align-human ~/.claude/skills/03-align-human

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/agentscope-ai/OpenJudge.git

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

In this catalog

Source file: skills/eval_pipeline/03-align-human/SKILL.md in agentscope-ai/OpenJudge
Installs to: ~/.claude/skills/03-align-human
Collection: One of 18 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Align Human does

Align Human measures how well an automatic judge agrees with human labels, including TPR/TNR, kappa, AC1, and bias checks. Use it to validate a grader, find disagreement patterns, and decide how much human review can be reduced.

Align Human is cataloged under AI Engineering on DirSkills. Align Human comes from a repository tagged agent, agent-skills, ai-agent, alignment and evaluation.

Documentation

README

Excerpt

Align Human

Measure whether your automatic judge agrees with human judgment, detect where and why they disagree, and build a roadmap to reduce human review over time.

When to Activate

You have a working judge/grader and 50+ human-labeled examples
You want to know if the judge is trustworthy enough to replace human review
You've noticed the judge's decisions being overturned by humans
You're preparing to deploy an evaluation as a production gate

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Align Human

What else does agentscope-ai publish alongside Align Human?
Align Human is one of 18 skills that DirSkills catalogs from agentscope-ai/OpenJudge, the repository it ships in. Its siblings there include Auto Arena, BibTeX Verification and Bootstrap. Each one is a separate skill with its own page in this directory, installs the same way Align Human does, and is maintained by agentscope-ai in that same repository. The rest of the collection is listed on the agentscope-ai/OpenJudge page.
How does Align Human compare to other AI Engineering skills?
Align Human ranks #1618 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 Align Human against them. Open each page to compare what they document and how they install.