auto-study

Use when handling browser-based study tasks on platforms like Yuketang, Xuexitong, and Pintia, including quiz answering and page actions.

3,891 stars

Best use case

auto-study is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Use when handling browser-based study tasks on platforms like Yuketang, Xuexitong, and Pintia, including quiz answering and page actions.

Teams using auto-study should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/auto-study/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/amiracleta/auto-study/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/auto-study/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How auto-study Compares

Feature / Agentauto-studyStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use when handling browser-based study tasks on platforms like Yuketang, Xuexitong, and Pintia, including quiz answering and page actions.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# auto-study

This skill provides a browser workflow for study platforms during ordinary practice. It can return answers, select options, fill in answers, clear answers, and submit them as needed.

## When to use

- Want to automatically handle answering tasks in a browser on study platforms, such as practice sets, quizzes, and homework.
- Want the answers for questions on the page.
- Wants answers selected, filled, or cleared on an ordinary practice page.

## Workflow

1. Start Chrome with the intended persistent site profile and a CDP port, or connect to an existing Chrome instance that already exposes a CDP port.
2. Verify the active tab and current URL, then snapshot or inspect the current page state before acting.
3. Interact with the page according to the user's request, such as selecting, filling, or clearing answers, or clicking the submit button.

## Core policy

- Treat all pages as ordinary practice by default unless the user explicitly says otherwise.

- If the user asks for page actions, apply them sequentially with short pauses, usually around 0.1 seconds.

- If the question is presented as an image, read the image directly **instead of** trying to extract text from it.

- Reuse the same browser profile for the same site when login state matters.

- Treat a persistent profile as a login-state aid, not as a guarantee of silent auto-login. It may restore cookies, local storage, or only saved credentials, so some sites may still require a visible login click or confirmation step.

- After attaching through CDP, verify the active tab and current URL before trusting the first snapshot. If the current page is not the target page, use `tab list` and switch to the expected site tab first.

- Do not re-click options that already match the target state.

- Do not rely on actions that a normal user could not perform. Prefer the normal user flow whenever possible.

- Do not submit automatically unless the user explicitly asks for it.

- Keep answers short and easy to scan.

- Just carefully analyze answer, do not search the web unless the user explicitly asks for it.

## Output rules

### Single choice

Return only the final option letter.

### Multiple select

Use comma-separated letters with no extra commentary.

### Fill in the blank or short answer

Return only the expected word or phrase.

## Profile storage

- Default the profile root to `%LOCALAPPDATA%\AutoStudy\browser`.
- When Chrome is launched for this skill outside the workspace, keep profile folders under the active profile root and reuse the same site profile.

## Environment-specific guidance

- For Windows-native usage, read `references/runtime-windows.md`.
- For WSL usage that launches Windows Chrome, read `references/runtime-wsl.md`.

## Browser guidance

- Read `references/browser.md`.

## Platform-specific guidance

- For Xuexitong specifics, read `references/xuexitong.md`.
- For Yuketang specifics, read `references/yuketang.md`.
- For Pintia specifics, read `references/pintia.md`.

## Prerequisites

- Google Chrome (on Windows)
- [Agent Browser CLI](https://github.com/vercel-labs/agent-browser)
- [Agent Browser Skill](https://clawhub.ai/MaTriXy/agent-browser-clawdbot)

Related Skills

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

n8n Workflow Mastery — Complete Automation Engineering System

3891
from openclaw/skills

You are an expert n8n workflow architect. You design, build, debug, optimize, and scale n8n automations following production-grade methodology. Every workflow you create is complete, functional, and follows the patterns in this guide.

Workflow & Productivity

Insurance Operations Automation

3891
from openclaw/skills

Comprehensive insurance operations framework for AI agents. Covers the full insurance lifecycle — underwriting, claims, policy management, renewals, compliance, and broker operations.

Workflow & Productivity

afrexai-business-automation

3891
from openclaw/skills

Turn your AI agent into a business automation architect. Design, document, implement, and monitor automated workflows across sales, ops, finance, HR, and support — no n8n or Zapier required.

Workflow & Productivity

Business Automation Strategy — AfrexAI

3891
from openclaw/skills

> The complete methodology for identifying, designing, building, and scaling business automations. Platform-agnostic — works with n8n, Zapier, Make, Power Automate, custom code, or any combination.

Auto Repair Shop Operations

3891
from openclaw/skills

Complete operational reference for independent auto repair shops. Covers labor rates, parts markup, ASE certification, EPA compliance, diagnostic workflows, flat rate times, KPIs, technician compensation, equipment costs, and growth playbook from solo shop to multi-location.

AI Automation Agency Blueprint

3891
from openclaw/skills

You are an AI Automation Agency strategist. Help the user build, price, sell, and scale an AI agent services business — from solo consultant to 7-figure agency. Every recommendation must be specific, actionable, and backed by real economics.

Business Strategy & Growth

Accounts Payable Automation Framework

3891
from openclaw/skills

You are an AP process optimizer. When the user describes their payable workflows, vendor relationships, or payment processes, generate a complete accounts payable management framework.

Workflow & Productivity

agent-autopilot

3891
from openclaw/skills

Self-driving agent workflow with heartbeat-driven task execution, day/night progress reports, and long-term memory consolidation. Integrates with todo-management for task tracking.

Workflow & Productivity

n8n-workflow-automation

3891
from openclaw/skills

Designs and outputs n8n workflow JSON with robust triggers, idempotency, error handling, logging, retries, and human-in-the-loop review queues. Use when you need an auditable automation that won’t silently fail.

Workflow & Productivity

autoresearch-pro

3891
from openclaw/skills

Automatically improve OpenClaw skills, prompts, or articles through iterative mutation-testing loops. Inspired by Karpathy's autoresearch. Use when user says 'optimize [skill]', 'autoresearch [skill]', 'improve my skill', 'optimize this prompt', 'improve my prompt', 'polish this article', 'improve this article', or explicitly requests quality improvement for any text-based content. Supports three modes: skill (SKILL.md files), prompt (any prompt text), and article (any document).

Workflow & Productivity

auto-respawn

3891
from openclaw/skills

Your agent always comes back. Anchor identity and memory on-chain so any new instance can resurrect from just an address — no local state, no single point of failure. Permanent identity and recovery on the Autonomys Network.

Agent Orchestration & Management