Skip to content

Flowy

All Plugins Skills Commands Agents Hooks MCP

Loading creator

All Plugins Skills Commands Agents Hooks MCP

flowy/plugins/@agentscope-ai

Unclaimed·Claim with GitHub

Post on X Share on LinkedIn

@agentscope-ai

agentscope-ai

@agentscope-ai

GitHub

Run @agentscope-ai's plugins in your agent.

Install one, then just prompt in plain English. The FLOW.md fires the right skill at the right moment. No re-orchestration, no babysitting.

Browse @agentscope-ai's plugins See the full library

An opinionated library of Flows. Free. Open source. V1.

Product

Plugins
Skills

Skills

21

skills

853

Stars earned

1

View

Sep 2026

Last ship

Plugins

1

Featured

Plugin

Testing Python Bash+5+6

openjudge

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

21 skills853

@agentscope-ai

View Plugin→

openjudge

Loading skills

21 skills

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Built with

PythonBashGitHubLaTeXAnthropicLangChainHugging Face

853 stars2w updated

Open this plugin→

Skills

21See all 21 →

00-academic-router

Skill

Testing Python Bash+5+6

00-academic-router

Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for…

fromopenjudge2w853

@agentscope-ai

View Skill→

00-arena-router

Skill

Testing Python Bash+5+6

00-arena-router

Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate…

fromopenjudge2w853

@agentscope-ai

View Skill→

Skill

Testing Python Bash+5+6

00-meta-eval

Use when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines,…

fromopenjudge2w853

@agentscope-ai

View Skill→

Skill

Testing Python Bash+5+6

01-auto-arena

Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects…

fromopenjudge2w853

@agentscope-ai

View Skill→

Skill

Testing Python Bash+5+6

01-eval-design

Use when the user needs to design evaluation datasets, create test cases, stratify samples, generate adversarial examples, extract eval dimensions from…

fromopenjudge2w853

@agentscope-ai

View Skill→

01-graders-and-pipeline

Skill

Testing Python Bash+5+6

01-graders-and-pipelin…

Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running…

fromopenjudge2w853

@agentscope-ai

View Skill→

Submit a plugin

Plugin validator

Learn

What is a plugin
What is a Flow
Skill routing
Best directories
Best skills
Glossary
Blog
Skill activation data
Claude ignores CLAUDE.md
Compare
Flowy vs crossaitools

Company

About
Sign in
Privacy
Terms
License
Support
GitHub

© 2026 Flowy · Free and open source

Built for Claude Code · Not affiliated with Anthropic