skills.rest
ttmouse
ttmouseCOMMUNITY
Explore all skills by this author →
𝕏@ttmouseGitHub

interactive-feedback-evaluator

Collect and summarize feedback via sidebar web forms with Flask and JSON storage.

35|10|Updated Dec 29, 2025
Search Tags:#automation#feedback#evaluation#reporting#data collection#forms
One-click install
npx skills add https://github.com/ttmouse/skills --skill interactive-feedback-evaluator
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: interactive-feedback-evaluator
Source: https://github.com/ttmouse/skills/tree/main/interactive-feedback-evaluator
Command: npx skills add https://github.com/ttmouse/skills --skill interactive-feedback-evaluator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires flask, requests, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a standardized, interactive system for collecting and summarizing feedback directly within the Alma sidebar, eliminating manual data collection and analysis.

Core Features & Use Cases

  • Interactive Forms: Users can fill out evaluation forms directly in the sidebar.
  • Automated Data Collection: Feedback is automatically captured and stored.
  • AI-Powered Summaries: Generates structured summaries from collected feedback.
  • Use Case: Evaluate analysis reports, skill effectiveness, or product features using pre-defined or custom templates, with AI providing a concise summary of the feedback.

Quick Start

Use the interactive-feedback-evaluator skill to evaluate the latest analysis report.

Frequently Asked Questions about interactive-feedback-evaluator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I collect and summarize user feedback using an interactive web form?▼

To collect and summarize user feedback, this system provides interactive web forms integrated into the AI sidebar, automatically capturing submissions and generating AI-powered structured summaries from the data.

How do I set up a Flask backend to automate feedback collection and reporting?▼

You need to run the provided scripts to start a Flask-based backend server that handles web form generation and submission, persisting all collected feedback data locally in JSON format.

Can I evaluate skill effectiveness and product features directly within the AI assistant sidebar?▼

Yes, you can evaluate skill effectiveness, product features, and analysis reports directly within the sidebar using pre-defined or custom evaluation templates without requiring external interfaces.

Does the automated feedback evaluation system require an external database?▼

No, the automated feedback evaluation system does not require an external database; all submitted form data is persisted locally on your server in a lightweight JSON file format.

What is the best way to generate AI summaries from collected evaluation data?▼

The best way to generate AI summaries is to use this built-in system, which automatically processes the locally stored JSON feedback data to produce concise, structured summaries.

What are the limitations of using JSON for persistent feedback data storage?▼

Using JSON for persistent feedback data storage limits scalability and concurrent write performance compared to relational databases, making it less suitable for high-traffic, enterprise-level data collection.

Related Skills

Explore More Product & Management Skills→
datasciencemonkeydatasciencemonkey
27

databricks-app-python

Build Python-based Databricks applications using Dash, Streamlit, or Flask.

Community
Advanced
zocomputerzocomputer
45

generate-pdf

Convert Markdown files into PDF documents using pandoc and LaTeX.

Official
Intermediate
lxp119lxp119

baidu-search

Search the web via the Baidu AI Search Engine using Python requests.

Community
Basic
zhuangbiaoweizhuangbiaowei
2

nemo-evaluator-sdk

Evaluate LLMs across 100+ benchmarks from 18+ harnesses.

Community
Advanced