yetone
Featured
kill-ai-slop
Kill AI Slop is a multilingual field guide and agent skill that catalogues 33 common AI-generated design tells with interactive before-after demos, and provides a tool to scan and fix web projects.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It offers a lightweight, locally runnable solution for systematically evaluating AI conversation outputs with configurable scoring criteria and persistent records.
Who it is for
- Developers testing chatbot response quality
- Product managers evaluating AI assistant performance
- QA or annotation teams scoring AI outputs
- Researchers using custom scoring rubrics
Use cases
- Scoring AI answers from uploaded conversation logs against custom quality dimensions
- Building a historical score database for tracking AI performance over time
- Exporting evaluation tables to CSV or Markdown for reporting or further analysis
- Rapidly setting up a local evaluation interface with custom model API and prompts
Strengths
- Supports txt and docx conversation file uploads
- Allows custom scoring dimensions and prompts
- Automatically saves scoring history with export options
- Simple local setup via pip and Streamlit
Considerations
- Requires manual configuration of model API, key, and model name before use
- Only handles txt/docx file formats
- Described as a simple test page, not a production-grade system
README quick start
这是个简单的测试网页，是个Streamlit 工具：上传对话文件（txt/docx），对每段对话中 AI 的回答按自定义维度评分，并给出评分理由。并且评分之后，会存下历史记录，以及可以导出的csv/markdown表格，便于统计评分。
代码拉到本地后，依次运行下面的命令，即可自动打开浏览器，开始使用。
运行
pip install -r requirements.txt pip install plotly streamlit run app.py
首页上传文件评分；第一次启动需要在，「配置」页设置模型（API 地址/Key/模型名）、提示词、评分维度；「历史」页可以回看往期评分。
Description
a simply test web for a intern
Related repositories
Similar projects matched by category, topics, and programming language.
lopopolo
Featured
harness-engineering
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.