Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Scaffolds a new ThunderID doc MDX file, registers it in the sidebar, and verifies no orphan is created. Use whenever asked to create, add, or write documentation for a new guide, quickstart, concept, reference, or use-case page — including requests like "document this feature" or "write docs for X" when no existing page covers the topic.
Use this skill BEFORE generating any file output — PDF, PPTX, DOCX, XLSX, HTML, or Markdown. Triggers include: any request to create, produce, or generate a document, presentation, spreadsheet, report, memo, proposal, invoice, resume, or any formatted file. Also use when the user asks to update formatting preferences, style standards, or brand guidelines. This skill provides a 3-layer formatting lookup: global standards, file-type rules, and document-purpose rules. Always invoke this skill before the file-type-specific skill (docx, pptx, xlsx, pdf).
Read, write, append, and manage Google Sheets via the Google Sheets API (Node.js SDK). Use when you need to interact with spreadsheets — reading data, writing/updating cells, appending rows, clearing ranges, formatting cells, managing sheets. Requires a Google Cloud service account with Sheets API enabled.
Rapid NDA screening with GREEN/YELLOW/RED classification. 10-point checklist for incoming NDAs. Use when triaging NDAs, screening non-disclosure agreements, or routing NDAs for approval.
Score a pitch deck's structure and content against YC, Sequoia, and a16z heuristics. Use before sending a deck to investors, practicing a pitch, or reviewing a seed or Series A fundraising deck.
Extract structured data from multiple documents into comparison matrix with citations. Use for bulk document review.
Guide a user conversationally through generating a new ad video from a template video and a user-provided product image. The host agent performs video understanding, detailed analysis, and rewrite planning; BytePlus Seedance is used only for final video generation with local product images as generation references.
Upload video/audio media to BytePlus VOD (Video on Demand) storage, returning the Vid and playback references; supports both local file upload (ApplyUploadInfo + TOS + CommitUploadInfo) and URL pull upload (UploadMediaByUrl); also supports AI-based comprehensive quality restoration on already-uploaded videos (removing compression artifacts, noise, scratches, and improving clarity). Trigger keywords: upload video, upload media, upload to VOD, URL upload, pull upload, local upload, file upload, UploadMediaByUrl, ApplyUploadInfo, media ingestion, quality restoration, quality enhancement, comprehensive restoration, video denoising, denoise, compression artifact removal.
专门用于将 Excel (.xlsx, .xls) 和 CSV (.csv) 文件转换为高度格式化的 Markdown 文档。 该工具具有内置的结构解析逻辑，能够自动识别表头、合并单元格并优化长文本换行。 当用户需要将表格数据转化为文档报告或在 Markdown 环境中展示数据时，**必须优先调用此工具**，以确保格式的准确性和视觉上的专业性，避免普通代码分析产生的格式错乱。
Seederive 非结构化数据打标平台，使用 LLM 对文本、语音、图片数据进行批量分析处理。 当用户提到以下任何场景时必须使用此 Skill：数据打标、标注、情感分析、标签分类、 观点提取、翻译、评论分析、水军识别、内容评分、标签库管理、提示词优化。 即使用户没有直接提到「Seederive」，只要涉及对一批文本做分类/打标/分析/翻译/评分， 或者提到「帮我分析这些评论」「这些数据的情感是什么」「识别水军」「提取观点」 「翻译这批内容」「建个标签体系」「效果不好帮我优化」等表述，都应触发此 Skill。 也适用于用户提供 CSV/Excel 文件要求批量处理的场景。