zgi

Extract structured contract fields from existing contract text or already parsed contract content according to a configured field list. Use when the user asks for 合同字段抽取, 合同信息抽取, 合同关键信息提取, 合同台账, contract field extraction, contract metadata extraction, contract ledger data, or extracting parties, amount, dates, term, payment terms, renewal terms, breach clauses, or other configured contract fields. This skill does not parse uploaded files directly; it works only after contract text is available from another system or parser.

Design structured user clarification flows with the existing request_user_input capability so the assistant asks stable, focused questions with usable quick options instead of plain natural-language follow-up. Use when the user or another skill needs 问答交互, 表单交互, 结构化质询, 弹出输入框, 选项框, 单选, 多选, 补充信息, 确认参数, 文件上传提示, 表单填写, questionnaire, form interaction, structured clarification, user input, quick replies, or parameter confirmation.

Plan precise slide-by-slide PPT structures from a topic, text content, requirements, or uploaded-material summaries, and prepare a file-generator-ready PPTX payload for downstream generation. Use when the user asks for PPT planning, PowerPoint outline, slide planning, page-by-page PPT requirements, presentation storyboard, report deck structure, pitch deck outline, training deck plan, proposal slides, project report slides, business review slides, or when the user asks to first create a precise outline before generating a PPT file. This skill is the planning and layout layer, not the PPTX file generator.

Rewrite existing assistant replies, service replies, workplace messages, or explanatory answers to sound more natural, human, warm, polite, concise, professional, empathetic, and easy to understand while preserving the original facts and boundaries. Use when the user asks for 回复口吻优化, 语气优化, 改得自然一点, 去 AI 味, 减少机械感, 像正常人说话, 温和一点, 亲切一点, 礼貌一点, 客服话术优化, 办公回复优化, 心理关怀回复, 面向普通用户, polish response, rewrite tone, make it natural, make it warmer, make it less robotic, or humanize this reply.

Generate downloadable SVG and HTML technical diagrams from natural language or structured data, including system architecture, AI Agent architecture, data flow, flowchart, comparison matrix, sequence, state, and ER diagrams.

Generate downloadable SVG charts from structured data, including radar, bar, line, pie, doughnut, scatter, and score distribution charts.

Generate image assets from text prompts or create reference-image variants and edit-style regenerated images for article illustrations, poster concepts, product concept art, marketing materials, ecommerce product scenes, illustrations, icons, and cover drafts. Use when the user asks for 生成图片, 图片生成, 文生图, 文章配图, 活动海报草图, 产品概念图, 营销素材, 插画生成, 图标草案, 封面草案, 电商商品场景图, 参考图生成, 图片变体, 换背景, 改颜色, 加元素, 去元素, generate image, text to image, image variant, image edit, background change, color change, add element, or remove element.

Professionalize vague, casual, incomplete, or tool-specific prompts into structured high-quality prompts for image generation, animation/video generation, technical architecture diagrams, data visualization, chart generation, and general prompt optimization. Use when the user asks for 提示词优化, Prompt 优化, 专业提示词, 生图提示词, 图片生成提示词, 动画提示词, 视频提示词, 架构图提示词, 技术架构图, 数据可视化提示词, 图表提示词, 帮我改成更专业的提示词, 帮我优化一下给某工具用, optimize prompt, professional prompt, image prompt, video prompt, architecture diagram prompt, data visualization prompt, chart prompt, or prompt template.

Support structured business decision analysis for product, technical, project, presales, customer solution, and management choices. Use when the user asks for 决策, 帮我选, 怎么选, 要不要做, 方案对比, 技术选型, 功能优先级, 项目优先级, 风险收益, 取舍, 权衡, 决策复盘, 客户方案, 售前方案, 管理决策, decision, choose, tradeoff, prioritization, roadmap, technical choice, option comparison, risk-benefit, ROI, should we, or decision review.

Detect and redact sensitive information from existing text or already parsed document content before sharing, archiving, model training, logging, ticket handoff, contract sharing, resume sharing, customer chat export, or external delivery. Use when the user asks for 脱敏, 敏感信息隐藏, 隐私清洗, 去标识化, 匿名化, 手机号脱敏, 邮箱脱敏, 身份证脱敏, 银行卡脱敏, 地址脱敏, 姓名脱敏, 公司名脱敏, 客户名脱敏, 订单号脱敏, 合同号脱敏, 日志脱敏, Token 脱敏, 密钥脱敏, password redaction, PII redaction, anonymization, de-identification, privacy cleanup, redact sensitive data, or mask secrets.

Classify customer service tickets, employee issues, tenant property-service requests, and enterprise support questions by issue type, urgency, responsible department, handling team, workspace, and owner role; generate structured routing results, internal handling suggestions, and initial customer replies. Use when the user asks for 客服工单分流, 工单分类, 工单派发建议, 客户问题识别, 问题类型, 紧急程度, 处理部门, 处理团队, 工作空间分配, 物业客服, 报修, 投诉, 咨询, 财务, 法务, 招商, 物业, IT, 行政, 客服, ticket routing, ticket triage, issue classification, urgency, department routing, workspace routing, or customer reply.

Extract candidate information from existing resume text or parsed resume content and provide preliminary screening based on an optional JD or screening criteria. Use when the user asks for 简历初筛, 简历筛选, 候选人评估, 候选人摘要, 简历提取, 简历结构化, JD匹配, 岗位匹配, 面试问题, 是否进入下一轮, HR初筛, 人才库录入, resume screening, candidate screening, CV screening, JD matching, interview questions, or talent pool entry.

Summarize and distill existing content from pasted text, chat context, or already parsed attachment content into summaries, TL;DR, key points, action items, risks, conclusions, decisions, meeting notes, or requirements summaries. Use when the user asks for 总结, 摘要, 提炼重点, 归纳, 归纳需求点, 行动项, 风险, 结论, 会议纪要, summarize, summary, TL;DR, key points, action items, risks, conclusions, decisions, or meeting notes.

Draft and polish formal, clear, business-appropriate emails in Chinese or English. Use when the user asks to write, draft, generate, optimize, rewrite, or polish business emails, customer follow-up emails, meeting invitations, reminders, apology or explanation emails, announcements, report delivery emails, supplier emails, candidate emails, bilingual emails, 商务邮件, 邮件撰写, 写邮件, 客户跟进, 会议邀约, 催办邮件, 道歉邮件, 解释说明, 通知公告, 周报邮件, 月报邮件, 润色邮件, 英文邮件, draft email, follow-up email, meeting invitation, reminder email, apology email, announcement email, or email polishing.

Compare two or more existing parsed documents, pasted document texts, or document contents from chat context to identify similarities, differences, additions, deletions, modifications, conflicts, risks, version changes, and dimension-based comparisons. Use when the user asks for 多文档对比, 文档对比, 版本对比, 合同对比, 方案对比, PRD对比, 招投标文件对比, 制度新旧版本对比, 供应商方案比较, 差异点, 共同点, 冲突点, 新增删除修改, 横向比较, compare documents, document comparison, version comparison, diff, conflict clauses, or vendor comparison.

Generate downloadable files from provided content, including basic exports, styled DOCX documents, HTML-rendered PDFs, and static editable PPTX decks.

Identify the user's real intent from the current message, conversation context, uploaded files, and available capabilities, then classify the request into a standard task type with confidence, recommended action, routing hints, missing information, and evidence. Use for intent recognition, task routing, request classification, workflow dispatch, database routing, knowledge retrieval routing, file export routing, chart or visualization routing, report routing, schedule planning routing, calculation routing, clarification planning, 意图识别, 任务路由, 请求分类, 工作流分发, 数据库查询路由, 知识库检索路由, 文件生成, 图表生成, 可视化, 报告生成.

Perform deterministic arithmetic, percent-based math, and change-rate math.

Answer questions about current time, timezone-aware time lookup, date arithmetic, and date differences.

Plan daily, weekly, or project schedules from user goals, tasks, deadlines, availability, priorities, and constraints.

Generate weekly or monthly work reports from user-provided progress, tasks, metrics, risks, and plans.

Operate database tables explicitly bound to the current Agent.

Retrieve from knowledge bases explicitly configured on the current Agent.

Discover and operate database tables the current AIChat user can access.

Discover and retrieve from knowledge bases the current AIChat user can access.

Call workflows explicitly bound to the current Agent as structured process tools.