Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →0xsline/widget-forms
Use when the agent should ask the user for structured input with an in-chat form, including single-select, multi-select, text fields, style pickers, or voice audition choices.
3 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 4 comparable cases; this report requires 8.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
Create a form card in OpenChatCut that asks for video resolution, target aspect ratio, and includes a file upload input field for uploading source footage.
| Checked | Without skill | With skill |
|---|---|---|
| Omits file upload input fields from the ask_followup_questions tool payload. | Missed | Passed |
| Directs the user to upload missing media using editor drag-and-drop or upload controls. | Missed | Passed |
The instructions your model reads when the skill loads.
Use the form tool instead of hand-writing markup: the editor chat renders the form as an interactive card and returns the user's structured answer.
Call ask_followup_questions. It serializes your fields into the editor's
native form card; the user's submission comes back as their next message.
Plan the whole questionnaire before calling the tool. Send one final form, not a trial form followed by a corrected form. The tool supports at most 12 fields; if the user asks for more questions, merge related prompts into combined fields before the first call.
After calling ask_followup_questions, stop the turn and wait for the submitted
answer to appear in chat. Do not apply a choice, create assets, or continue
planning from a recommendation until the user's selection is present in the
conversation.
Build a fields array. Write every visible string in the user's conversation
language.
<form-single> -> { type: "single", variant: "default" }<form-multi> -> { type: "multi", variant: "default" }<form-text> / <form-textarea> -> { type: "text" }<form-visual> -> { type: "single", variant: "visual" }{ type: "single", variant: "voice" }{ type: "single", variant: "scenario" }For form-level text (title, prompt, fields[].label, submitLabel, and
messagePrefix), write like OpenChatCut is a capable video-making partner inviting
the user to describe what they want, not like a rigid survey.
Aim for:
test cases passed with the skill
More skills from the same source and nearby in the registry, with their headline benchmark lift.