Skills Plugins MCP Prompt Model 博客 我的中心

discovery-question-form

Structured clarification form for unresolved material requirements.

DeepseekModel 官方收录技能 质量 优秀 · 90 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=nexu-io-open-design-plugins-official-atoms-discovery-question-form-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name discovery-question-form description Structured clarification form for unresolved material requirements. od {"scenario":"general","mode":"discovery"} Discovery question form This atom defines the <question-form> protocol. It does not decide whether clarification is required. Follow the active skill and core prompt's requirements-clarification policy. When they identify unresolved information that would materially change the design direction, content structure, or delivery format, surface the smallest possible set of questions that unblocks the workflow. The questions are rendered as a <question-form> artifact inline in the originating assistant message. This is assistant text parsed by the host, not a plugin GenUI surface or a native tool call. Submitted answers return as the next user message, beginning with [form answers — <form-id>] . Activation boundary A first turn or new project does not by itself require a form. A discovery pipeline stage only makes this protocol available; declaring or entering the stage does not trigger a form. Missing metadata is not automatically a question. First use the request, conversation, plugin inputs, memory, active skill, and design system. If enough information is available to proceed safely, do not emit a form. If a material blocker remains, ask only for that unresolved information. Emission shape Emit the form as a question-form block whose body is a JSON object with a top-level questions array. Do not emit a bare question object by itself; the renderer only recognizes the wrapped form contract. < question-form id = "discovery" title = "Quick brief — 30 seconds" > { "description": "I'll lock these in before building. Skip what doesn't apply — I'll fill defaults.", "questions": [ { "id": "audience", "label": "Who's the primary audience?", "type": "checkbox", "options": ["VC", "Customer", "Internal team"], "maxSelections": 2, "required": true } ] } </ question-form > Question object shape Each entry in the top-level questions array uses: id : stable answer key, for example audience . label : user-facing question copy. type : one of radio , checkbox , select , text , textarea , number , range , date , time , datetime-local , color , url , email , tel , file , or switch . options : required for choice controls; strings are allowed, or objects with localized label and stable value . At most 6-7 options per question; merge near-duplicates instead of listing more. Choose radio vs select by option count, not importance: radio for a short list, select once it runs long (languages, timezones, voices). checkbox is always a plain list. select options may carry group (first group expands, the rest collapse) and trailingLabel (a short end-of-row code such as ZH-CN ). Both optional. Label options in the user's words, not jargon: "Magazine-style layout", not "Editorial". Reword only label ; never change a stable value . Keep each label under ~40 characters; put anything longer in description . allowCustom : leave unset or set to true for finite-choice controls so users can type their own answer instead of accepting only generated options. Set allowCustom: false only when the downstream system needs an exact machine id. customLabel / customPlaceholder : optional localized copy for that custom answer input. maxSelections : include this for checkbox controls with a limited selection count. required : set to true only when the answer is needed before work can continue. Convergence The discovery atom completes when the next user message contains an answer for every required question. Treat those submitted answers as conversation context and do not ask the same questions again unless later input invalidates an answer.
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。