Autofillin logo

Autofillin

Organization
sundial-org
autofillin

Automated web form filling and file uploading skill with Playwright browser automation. Handles login persistence, form detection, file uploads, and waits for manual confirmation before submission.

Overview

Publishersundial-org
Repositoryawesome-openclaw-skills
Skill nameautofillin
Stars
664
Forks
97
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by sundial-org on GitHub. Read the source before you install it.

Installation

Install the Autofillin AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/autofillin
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/sundial-org/awesome-openclaw-skills.git /tmp/awesome-openclaw-skills
mkdir -p .claude/skills
cp -r /tmp/awesome-openclaw-skills/skills/autofillin .claude/skills/autofillin
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Autofillin in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Autofillin on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Autofillin is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AutoFillIn - Browser Form Automation Skill

Trigger Command: autofillin

An intelligent automation skill that fills web forms, uploads files/folders to correct positions, and handles complex multi-field submissions with persistent login support.

What's New in v1.2.0

  • Enhanced Error Handling: Graceful error recovery with detailed messages
  • Consolidated Configuration: Merged mcp-config into SKILL.md
  • Improved Robustness: Better port conflict handling and process management
  • Cross-platform Fixes: Improved Windows/Linux compatibility

Changelog

VersionChanges
v1.2.0Enhanced error handling, consolidated config, improved robustness
v1.1.0Added Playwright support, session persistence, folder upload
v1.0.0Initial release with Chrome debug mode

Features

  • Navigate to any web form URL
  • Auto-fill text fields, textareas, dropdowns
  • Upload files/folders to correct form positions
  • Persistent login via saved browser storage
  • Wait for manual confirmation before submission
  • Support for multi-file uploads with position mapping
  • Graceful error recovery

Quick Setup

bash
# 1. Install Playwright browsers
npx playwright install chromium

# 2. First-time login (saves session for reuse)
npx playwright open --save-storage=~/.playwright-auth.json "https://your-target-site.com"
# Login manually in the browser that opens, then close it

# 3. Future runs will auto-login using saved session
npx playwright open --load-storage=~/.playwright-auth.json "https://your-target-site.com"

MCP Configuration

Add to your MCP settings (Claude Code, OpenCode, etc.):

json
{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["-y", "@anthropic-ai/mcp-server-playwright"]
    },
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/"]
    }
  }
}

Environment variables for shell integration:

bash
export CHROME_DEBUG_PORT=9222
export CHROME_USER_DATA_DIR="$HOME/.chrome-autofillin"

Browser Automation Options

Option 1: Playwright CLI (Recommended for OAuth sites)

bash
# First login - saves session
npx playwright open --save-storage=~/.playwright-auth.json "https://molthub.com/upload"

# Subsequent uses - loads saved session
npx playwright open --load-storage=~/.playwright-auth.json "https://molthub.com/upload"

Advantages:

  • No "unsafe browser" blocks from Google/GitHub OAuth
  • Session persistence across runs
  • Works with MCP browser tools

Option 2: Chrome Debug Mode (For non-OAuth sites)

bash
# Start Chrome with debug port
./scripts/start-chrome.sh "https://example.com/form"

# With your default Chrome profile (keeps existing logins)
./scripts/start-chrome.sh --use-default-profile "https://example.com/form"

Note: Chrome debug mode with custom --user-data-dir is blocked by Google OAuth. Use Playwright for sites requiring Google/GitHub login.

Usage Examples

Basic Form Filling

autofillin https://example.com/form
- Fill "Name" field with "John Doe"
- Fill "Email" field with "john@example.com"
- Upload resume.pdf to file input

MoltHub Skill Upload

autofillin https://molthub.com/upload

Form Data:
- Slug: autofillin
- Display name: AutoFillIn - Browser Form Automation Skill
- Version: 1.2.0
- Tags: automation, browser, form, playwright, mcp
- Changelog: v1.2.0 - Enhanced error handling, consolidated config

Upload:
- Folder: ~/clawd/skills/autofillin/

[WAIT FOR MANUAL CONFIRMATION TO PUBLISH]

Multi-file Upload with Position Mapping

autofillin https://example.com/document-upload

Files to upload:
- Position 1 (ID Document): ~/documents/id_card.pdf
- Position 2 (Proof of Address): ~/documents/utility_bill.pdf
- Position 3 (Photo): ~/photos/headshot.jpg

[WAIT FOR MANUAL CONFIRMATION]

Workflow

1. BROWSER SETUP
   - Check for saved session (~/.playwright-auth.json)
   - Launch Playwright Chromium with session
   - Or prompt for one-time login if no session exists

2. NAVIGATION & LOGIN
   - Navigate to target URL
   - Detect if login is required
   - If login needed: Fill username, prompt for password, save session

3. PAGE ANALYSIS
   - Take accessibility snapshot
   - Identify all form fields
   - Map field labels to input elements

4. AUTO-FILL PHASE
   - Fill text fields using fill() or fill_form()
   - Select dropdown options
   - Upload files/folders via upload_file()

5. CONFIRMATION PHASE
   - Display summary of filled data
   - WAIT FOR MANUAL CONFIRMATION
   - User reviews and clicks Submit/Publish

MCP Tools Used

ToolPurpose
take_snapshotGet page accessibility tree
fillFill single form field
fill_formFill multiple fields at once
upload_fileUpload file or folder
browser_clickClick buttons
evaluate_scriptRun JavaScript
navigate_pageNavigate to URLs

Credential Management

Safe Storage (Recommended)

bash
# Use macOS Keychain
security add-generic-password -a "github" -s "autofillin" -w "your-password"
security find-generic-password -a "github" -s "autofillin" -w

# Use Linux secret-tool
secret-tool store --label="autofillin-github" service autofillin username github

# Use Windows Credential Manager
cmdkey /add:autofillin-github /user:github /pass:your-password

Session Persistence

Sessions saved to ~/.playwright-auth.json include cookies, localStorage, and sessionStorage.

Error Handling

ErrorCauseSolution
Unsafe browserGoogle OAuth blockedUse Playwright instead of Chrome debug
Login requiredSession expiredRun with --save-storage
Element not foundPage changedTake new snapshot
Upload failedWrong file typeCheck webkitdirectory
Port in useAnother Chrome instanceScript auto-kills conflicting process
Chrome not foundNot installedRun setup-env.sh

Troubleshooting

Chrome won't start with debug mode

bash
# Check if port is in use
lsof -i:9222

# Kill existing processes
pkill -f "remote-debugging-port=9222"

# Retry
./scripts/start-chrome.sh "https://example.com"

Session not persisting

bash
# Verify auth file exists
ls -la ~/.playwright-auth.json

# Re-authenticate
npx playwright open --save-storage=~/.playwright-auth.json "https://target-site.com"

File upload not working

  • Ensure file path is absolute
  • Check file permissions: ls -la /path/to/file
  • For folder uploads, verify the input has webkitdirectory attribute

Files in This Skill

autofillin/
├── SKILL.md              # This documentation (includes MCP config)
└── scripts/
    ├── setup-env.sh      # Environment setup (cross-platform)
    ├── start-chrome.sh   # Chrome debug launcher
    └── autofillin.sh     # Main orchestrator with error handling

Author

License

MIT

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Autofillin AI skill do?

Automated web form filling and file uploading skill with Playwright browser automation. Handles login persistence, form detection, file uploads, and waits for manual confirmation before submission.

Why use Autofillin on TypingMind?

Because you install it once and use it with any model. Autofillin is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Autofillin in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/autofillin. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Autofillin?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Autofillin?

As many as you like. As long as a model supports skills, you can use Autofillin with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Autofillin AI skill free?

It is published on GitHub by sundial-org. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇