Agent SkillsChatCut-Inc/agent-plugin › widget-forms

widget-forms

GitHub

将 ChatCut 的表单语义映射到插件宿主,支持文本、单选、音频及同意确认等字段,通过 MCP 工具交互并处理媒体渲染限制。

claude/skills/widget-forms/SKILL.md ChatCut-Inc/agent-plugin

Trigger Scenarios

需要结构化用户输入 处理表单提交

Install

npx skills add ChatCut-Inc/agent-plugin --skill widget-forms -g -y
More Options

Non-standard path

npx skills add https://github.com/ChatCut-Inc/agent-plugin/tree/main/claude/skills/widget-forms -g -y

Use without installing

npx skills use ChatCut-Inc/agent-plugin@widget-forms

指定 Agent (Claude Code)

npx skills add ChatCut-Inc/agent-plugin --skill widget-forms -a claude-code -g -y

安装 repo 全部 skill

npx skills add ChatCut-Inc/agent-plugin --all -g -y

预览 repo 内 skill

npx skills add ChatCut-Inc/agent-plugin --list

SKILL.md

Frontmatter
{
    "name": "widget-forms",
    "description": "Ask for structured ChatCut input using the current plugin host's supported form surface."
}

Widget Forms Host Adapter

The canonical agent's raw <widget>, <choices/>, and <visual-option> tags render only inside ChatCut. Never emit those tags from the published Codex or Claude Code plugin.

Semantic contract mapping

This adapter owns how plugin hosts implement a caller's host-neutral form contract. It does not decide which fields the workflow requires.

Map semantic field types as follows:

  • short_text: one text input.
  • explicit_consent: one explicit, initially unselected confirmation control using the caller's full localized copy. An attachment or another submitted field is never consent.
  • audio_reference: plugin forms cannot record or upload media. Render the other fields, ask the user to attach the audio to the conversation, then load asset-import. Return the imported ChatCut audio assetId to the calling workflow; never return a local path, attachment URL, or raw bytes as an asset id.
  • playable_single_choice: one choice surface with stable option values, localized labels, and playable media when the host supports it. Keep the value-to-label map in context when a host returns the visible label.
  • playable_preview: one display-only, non-submitting audio surface using the exact caller-provided runtime media URL. Use only a host-supported safe media renderer; never emit raw <audio> HTML or expose the URL as ordinary prose.

Codex

Call the ChatCut MCP tool ask_followup_questions. Put related fields into one form, write visible text in the user's language, and stop after the call until the submitted answer appears in chat. Use the current tool schema for field and option shapes.

Map playable_single_choice to one single field with variant:"voice". Use each stable value as the option id and keep its localized label, description, and audioUrl tied to the same caller-provided item. An action without playable media has no audioUrl.

Map an AI-avatar identity choice to one single field with variant:"visual". Use the live identityId as the option id, the returned name as its label, previewVideoUrl as previewVideo, and previewImageUrl as preview. The image remains the poster and automatic fallback if video loading fails. Keep create_avatar as a label-only option. Selecting it returns that value to the workflow; it does not open ChatCut's native avatar dialog, so request the source attachment separately and use asset-import.

Do not call ask_followup_questions solely to display a playable_preview, because a passive preview is not a question. Use Codex's supported audio attachment/media rendering when available. If this host session has no safe runtime-URL audio renderer, say that the preview is available in the ChatCut project assets and continue with the caller's separate branch decision; do not print HTML, a bare URL, or a fake widget tag.

Map explicit_consent to a single-select field containing only one confirmation option. Use the caller's full confirmation copy as its label and do not preselect it. Mark every blocking field as required and verify every required answer after submission before continuing.

Claude Code

Follow the structured-input recipe in chatcut-plugin-basics-claude: use one visualize.show_widget Elicitation form, submit only through .elicit-submit, and wait for the user to send the filled prompt. Never call ChatCut's ask_followup_questions in Claude Code because that host does not render its MCP-App result.

Map explicit_consent to an unchecked checkbox using the caller's complete localized copy. Do not add a file chooser for audio_reference; request the conversation attachment outside the form and load asset-import after the user sends it.

For playable_single_choice, resolve bundled media keys through ${CLAUDE_PLUGIN_ROOT}/assets/widget-media/manifest.json; use a label-only card when a key is absent and never embed or process the original source URL. Keep the stable value in the label-to-id map rather than exposing it as the DOM audio key. Runtime media URLs are not in the bundled manifest: do not embed them in Elicitation HTML. Present them through the host's normal safe link/audio surface, then use a label-only confirmation control.

AI-avatar previews are runtime catalog media and are not bundled in the plugin manifest. Keep each authoritative identityId mapped to its returned name, use label-only selectable cards in Elicitation, and tell the user that live video previews are available in ChatCut's AI Avatars library. Never embed or print the provider preview URL. A create_avatar selection returns to the workflow and then follows the normal conversation-attachment plus asset-import path.

Version History

  • 014586d Current 2026-08-27 10:43

    新增 Semantic contract mapping 章节,明确 short_text、explicit_consent、audio_reference 等字段类型的具体映射规则与限制。

  • e1867a8 2026-08-02 23:37

    简化了Codex和Claude Code的说明,移除了关于工具发现、缓存及媒体卡片引用的复杂细节,聚焦于核心调用逻辑。

  • 5e9afe0 2026-07-22 10:58

Same Skill Collection

chatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md
chatcut/skills/asset-import/SKILL.md
chatcut/skills/chatcut-plugin-basics-claude/SKILL.md
chatcut/skills/chatcut-plugin-basics/SKILL.md
chatcut/skills/create-motion-graphics/SKILL.md
chatcut/skills/export/SKILL.md
chatcut/skills/image-gen/SKILL.md
chatcut/skills/known-errors/SKILL.md
chatcut/skills/music/SKILL.md
chatcut/skills/shader-gen/SKILL.md
chatcut/skills/transcription/SKILL.md
chatcut/skills/verification/SKILL.md
chatcut/skills/video-gen/SKILL.md
chatcut/skills/voice/SKILL.md
chatcut/skills/widget-forms/SKILL.md
claude/skills/create-motion-graphics/SKILL.md
claude/skills/export/SKILL.md
claude/skills/image-gen/SKILL.md
claude/skills/known-errors/SKILL.md
claude/skills/motion-graphic-gen/SKILL.md
claude/skills/music/SKILL.md
claude/skills/shader-gen/SKILL.md
claude/skills/transcription/SKILL.md
claude/skills/verification/SKILL.md
claude/skills/video-gen/SKILL.md
codex/skills/asset-import/SKILL.md
codex/skills/create-motion-graphics/SKILL.md
codex/skills/export/SKILL.md
codex/skills/image-gen/SKILL.md
codex/skills/known-errors/SKILL.md
codex/skills/music/SKILL.md
codex/skills/shader-gen/SKILL.md
codex/skills/transcription/SKILL.md
codex/skills/verification/SKILL.md
codex/skills/video-gen/SKILL.md
codex/skills/widget-forms/SKILL.md
chatcut/skills/product-help/SKILL.md
chatcut/skills/talking-head-guide/SKILL.md
claude/skills/asset-import/SKILL.md
claude/skills/chatcut-plugin-basics-claude/SKILL.md
claude/skills/digital-human/SKILL.md
claude/skills/multicam-sync/SKILL.md
claude/skills/product-help/SKILL.md
claude/skills/talking-head-guide/SKILL.md
claude/skills/voice/SKILL.md
codex/skills/chatcut-plugin-basics/SKILL.md
codex/skills/digital-human/SKILL.md
codex/skills/multicam-sync/SKILL.md
codex/skills/product-help/SKILL.md

Metadata

Files
0
Version
2f39109
Hash
6efd903b
Indexed
2026-07-22 10:58

Accueil - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-28 07:20
浙ICP备14020137号-1 $Carte des visiteurs$