Homework Grader Skill for Openclaw

An automated educational tool that fetches student assignments from QQ Mail, evaluates them using AI, and compiles grades into an Excel report.

yaouuu
v1.0.0
Mar 28, 2026
0
864
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install homework-gader-skill

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install homework-gader-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Homework Grader Skill?

The Homework Grader Skill is a specialized automation tool designed for educators and teaching assistants who manage large volumes of digital submissions. By integrating directly with mail servers, it eliminates the manual overhead of downloading, organizing, and preliminary grading of student work. This skill is a powerful addition to the Openclaw Skills ecosystem, providing a bridge between traditional email-based submission workflows and modern AI evaluation techniques.

At its core, the skill uses pattern recognition to identify specific student submissions based on naming conventions like Name-StudentID-AssignmentID. It then applies intelligent grading logic based on predefined templates to ensure consistent, objective feedback across all submissions, ultimately outputting a structured dataset ready for academic record-keeping.

Homework Grader Skill Use Cases

  • Teachers managing large classes who receive student assignments via QQ Mail as zip archives.
  • Automated screening and preliminary grading of coding assignments or structured text reports.
  • Generation of standardized academic performance spreadsheets from unstructured email attachments.
  • Reducing manual file handling and directory organization for educational administrators.

How Homework Grader Skill Works

  1. Establishes a secure connection to the QQ Mail server using the IMAP protocol and provided authorization codes.
  2. Scans for unread emails and identifies relevant zip attachments matching the assignment criteria.
  3. Extracts metadata from filenames, including student names and identification numbers.
  4. Decompresses the archives and loads the specific grading rubric or assignment template.
  5. Processes the content through an AI scoring engine to generate grades and qualitative feedback.
  6. Aggregates all processed data into a final Excel (.xlsx) file for the user.

Homework Grader Skill Setup

To deploy this skill within the Openclaw Skills framework, ensure you have your QQ Mail IMAP authorization code ready:

# Example of initiating the skill via CLI
openclaw run homework-grader --assignment_id 1 --email_user "[email protected]" --email_auth_code "your_imap_auth_code"

Ensure that students follow the naming convention: Name-StudentID-AssignmentNumber.zip for successful parsing.

Homework Grader Skill Data Schema & Taxonomy

The skill organizes processed data into a structured Excel format with the following data points:

Column Description
Student Name Extracted from the zip filename
Student ID Extracted from the zip filename
Score Numerical value generated by the AI based on the template
Feedback AI-generated qualitative comments
Status Processing status (e.g., Success, Unzipped, Error)

All generated reports are saved to the path specified in the excel_path output variable.

Homework Grader Skill Advanced Features

  • Multi-stage archival extraction to handle nested zip folders.
  • Template-based scoring allows for custom rubrics for different subjects (coding, essays, math).
  • Seamless integration with the Openclaw Skills environment for chainable AI workflows.
  • Automated read-status management in QQ Mail to prevent duplicate processing.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*