- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add billy-enrizky/openbrowser-ai --skill form-filling -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add billy-enrizky/openbrowser-ai --skill form-filling -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add billy-enrizky/openbrowser-ai --skill form-filling -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add billy-enrizky/openbrowser-ai --skill form-filling -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/billy-enrizky/openbrowser-ai/tree/HEAD/plugin/skills/form-fillingFrom the publisher
Automate filling web forms including login, registration, checkout, and multi-step form wizards using Python code execution.
All code runs via openbrowser-ai -c. The daemon starts automatically and persists variables across calls. All browser functions are async -- use await.
The CLI daemon also persists cookies and login state in ~/.config/openbrowser/profiles/daemon/storage_state.json, so authenticated sessions can be reused across later runs.
Before running, verify openbrowser-ai is installed:
openbrowser-ai --help
If not found, install:
# macOS/Linux
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh
# Windows (PowerShell)
irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex
openbrowser-ai -c - <<'EOF'
await navigate("https://example.com/login")
state = await browser.get_browser_state_summary()
print(f"Page: {state.title} ({state.url})")
print(f"Interactive elements: {len(state.dom_state.selector_map)}")
EOF
openbrowser-ai -c - <<'EOF'
# List all interactive elements with their indices
state = await browser.get_browser_state_summary()
for index, element in state.dom_state.selector_map.items():
tag = element.tag_name
text = element.get_all_children_text(max_depth=2)[:60]
placeholder = element.attributes.get("placeholder", "")
input_type = element.attributes.get("type", "")
name = element.attributes.get("name", "")
print(f"[{index}] <{tag}> type={input_type} name={name} placeholder=\"{placeholder}\" text=\"{text}\"")
EOF
openbrowser-ai -c - <<'EOF'
# Fill fields using their indices from Step 2
await input_text(index=5, text="[email protected]")
await input_text(index=7, text="secure-password")
EOF
For fields that need clearing first:
openbrowser-ai -c - <<'EOF'
await click(index=5)
await evaluate("document.activeElement.select()")
await input_text(index=5, text="new-value")
EOF
Standard HTML select elements:
openbrowser-ai -c - <<'EOF'
await select_dropdown(index=12, text="United States")
EOF
To see available options first:
openbrowser-ai -c - <<'EOF'
options = await dropdown_options(index=12)
print(options)
EOF
Custom dropdown components:
openbrowser-ai -c - <<'EOF'
await evaluate("""
(function(){
const select = document.querySelector("select#country");
select.value = "US";
select.dispatchEvent(new Event("change", { bubbles: true }));
})()
""")
EOF
openbrowser-ai -c - <<'EOF'
await click(index=15) # Click checkbox/radio
# Verify state
checked = await evaluate("""document.querySelector("input[name=agree]").checked""")
print(f"Checkbox checked: {checked}")
EOF
openbrowser-ai -c - <<'EOF'
await click(index=20) # Click submit button
await wait(2)
# Verify submission
state = await browser.get_browser_state_summary()
print(f"After submit: {state.url}")
EOF
Or submit via JavaScript:
openbrowser-ai -c - <<'EOF'
await evaluate("document.querySelector(\"form\").submit()")
EOF
openbrowser-ai -c - <<'EOF'
# Check for success/error messages
result = await evaluate("""
(function(){
const success = document.querySelector(".success, .alert-success, [role=\"alert\"]");
const error = document.querySelector(".error, .alert-danger, .validation-error");
return {
success: success?.textContent?.trim(),
error: error?.textContent?.trim(),
url: window.location.href
};
})()
""")
print(result)
EOF
openbrowser-ai -c - <<'EOF'
for step in range(1, 5):
# Discover fields for current step
state = await browser.get_browser_state_summary()
print(f"Step {step}: {len(state.dom_state.selector_map)} elements")
# Fill fields (indices vary per step)
# ... fill fields here ...
# Click Next/Continue
# Find the next button
for idx, el in state.dom_state.selector_map.items():
text = el.get_all_children_text(max_depth=1).lower()
if "next" in text or "continue" in text:
await click(index=idx)
await wait(2)
break
EOF
-c - <<'EOF'), so all Python syntax works without shell escaping issues.browser.get_browser_state_summary() before typing -- do not guess element indices.evaluate() to bypass custom components that do not respond to standard click/type.-c calls while the daemon is running, so you can store field indices in one call and use them in the next.This step is mandatory. Run it after the form submission finishes, whether the submit succeeded or the form rejected the input. Without it, the daemon keeps Chrome running until its 10-minute idle timeout, leaving a stale browser process, a locked profile, and (on macOS/Linux desktop) a visible window with the form still on screen.
Stop the daemon, then verify it is gone:
openbrowser-ai daemon stop
openbrowser-ai daemon status
daemon stop closes every tab, exits Chrome, flushes saved cookies/login state to the profile (so the next run reuses the login), and shuts down the daemon process. daemon status should report the daemon is not running. If it still reports running, run openbrowser-ai daemon doctor and then openbrowser-ai daemon reap. reap stops only verified OpenBrowser daemons and removes stale sockets and PID files.
Form runs can fail mid-workflow (validation error, CAPTCHA, network drop). Guarantee cleanup with a shell trap so a half-filled form never leaks a browser:
trap 'openbrowser-ai daemon stop >/dev/null 2>&1 || true' EXIT
# ... openbrowser-ai -c calls here ...
Do not rely on the idle timeout. Do not call done() as a substitute, done() only marks the task complete inside the agent loop, it does not close the browser.
|
---name: form-fillingdescription: |---# plugin/skills/form-filling/SKILL.mdFAQ
Download plugin/skills/form-filling/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/billy-enrizky/openbrowser-ai.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.