Documents Skills

This skill should be used when a system design needs a diagram — "draw the architecture", "diagram this system", "show the components", "make an architecture/infrastructure/topology diagram", or visualizing boxes-and-arrows, data flow, regions, or failure paths for a design. It generates a self-contained dark-theme HTML + SVG diagram (with PNG/PDF export). Use it whenever the `system-design` orchestrator or a building block reaches the "draw it" step, even if the user doesn't say "diagram".

Automates Microsoft PowerPoint via JXA with AppleScript dictionary discovery. Use when asked to "automate PowerPoint presentations", "create slides programmatically", "JXA PowerPoint scripting", or "export PowerPoint to PDF". Covers presentations, slides, shapes, text, tables, export enums, and interop with Excel.

Automates Apple Pages using JXA with AppleScript dictionary discovery. Use when asked to "automate Pages documents", "create documents programmatically", "JXA Pages scripting", or "export Pages to PDF". Covers documents, templates, text, styles, export, tables, images, and AppleScript bridge fallbacks.

Automates Microsoft Word via JXA with AppleScript dictionary discovery. Use when asked to "automate Word documents", "find and replace in Word", "JXA Word scripting", or "create Word documents programmatically". Covers documents, ranges, find/replace, tables, export, and ObjC bridge patterns.

将用户已授权账号中的抖音视频收藏或用户明确指定的喜欢列表配置并同步到本地 Markdown 或 Obsidian 知识库；默认收藏，只有用户明确说喜欢/点赞才切换来源。首次明确选择推荐的百炼转录、本地 Whisper 或不转录。不得绕过登录、访问他人账号或泄露 Cookie 与私密数据。

| Inspect, build, and verify Office documents (PPTX, DOCX, XLSX) using the oxen CLI. (3) Previewing slide/document/sheet content in terminal, (4) Extracting text or data, (5) Verifying build results, (6) User asks about ".pptx", ".docx", ".xlsx" inspection or generation.

| Create and modify PowerPoint presentations (PPTX) through direct XML manipulation. (3) Inserting images or custom shapes, (4) Applying POTX templates for consistent branding, (5) Editing existing PPTX files, (6) Working with slide layouts and placeholders, (7) User asks to make a "presentation", "slides", "deck", or mentions ".pptx". Supports all 11 standard Office slide layouts.

> Audit the reasoning of any document or argument — a memo, proposal, investment analysis, board paper, article, or the user's own draft — and fallacies, and what would falsify it, with every finding anchored to exact quoted text. Runs a commit-first coaching loop that asks for the user's own judgment before revealing the audit, tracks their recurring blind spots in a persistent reasoning profile, and turns every audit into a rep that sharpens the user's thinking instead of replacing it. Use this skill whenever the user wants reasoning examined — "audit this argument", "is this analysis sound", "poke holes in this proposal", "review the logic of my draft", "what's wrong with this reasoning" — in any language (e.g. Vietnamese "phản biện giúp tôi", "soi lập luận này", "tài liệu này có lỗ hổng gì", "đánh giá đề xuất này giúp tôi", "góp ý bản nháp của tôi"; Spanish "analiza los argumentos de esta propuesta"; Chinese "帮我审一下这份提案的论证"; Japanese "この提案の論理をチェックして"; French "analyse les failles de ce raisonnement"), even when they never say "critical thinking". Also trigger when the user drops a document and asks whether to trust or act on it, or asks to see their thinking progress / reasoning profile. (Company-level strategic bets with a full analysis belong to strategy-board; learning a new topic through dialogue belongs to socratic-questor — this skill leads when the question is whether a specific piece of reasoning holds up, and it is the daily-driver for document-level judgment calls.)

>- Deep-read long books and papers using Mortimer Adler's inspectional / analytical / syntopical method, the Recite step from SQ3R, and S. Keshav's three-pass method for papers, with page-anchored notes as external memory so the agent never has to load the whole text into one context window. Use this skill whenever the user asks to read, study, summarize, analyze, review, or answer questions about a long book, textbook, PDF, EPUB, thesis, dissertation, survey paper, or any document of roughly 50+ pages. Also use it when a `<slug>-notes/` workspace from a previous session already sits next to a source file and the user asks a follow-up question about that book — search the existing notes before re-reading anything. Trigger on these requests in whatever language the user writes them — for example Vietnamese "đọc sách", "tóm tắt sách", "phân tích luận án", or equivalent phrasing in any other language. Do not use this skill for short documents (under ~30 pages) that fit comfortably in context — read those directly instead; the pipeline is overhead they don't need.

>- Write, restructure, classify, and review documentation using the Diataxis framework. Use this skill whenever the user asks to create, improve, audit, or reorganize docs, documentation, knowledge bases, help centers, onboarding guides, internal process docs, manuals, runbooks, product docs, API/developer docs, tutorials, how-to guides, references, or explanations. Also use it when the user mentions Diataxis, tutorial, how-to, reference, explanation, docs taxonomy, documentation architecture, or asks why a document feels confusing. Do not use it for marketing copy, legal contracts, fiction, sales proposals, press releases, or persuasion-first writing unless the user explicitly wants a Diataxis-style documentation analysis.

>- Build interactive presentation websites — slide decks projected to a room, controlled by one presenter. Use this skill WHENEVER the user wants to create, build, or design a presentation, slide deck, talk, or "bài thuyết trình / slide / trình chiếu", and also when they ask to add/edit slides, restyle a deck, scaffold a new presentation project, reuse their presentation setup in another repo, or export slides to PDF — even if they don't say the word "slide" but clearly need projected talk visuals (e.g. "I'm giving a talk next week and need visuals", "dựng deck cho buổi chia sẻ", "làm mấy trang chiếu project. Do NOT use it for printable documents, normal web apps, or dashboards meant for individual users to interact with.

> Socratic questioning partner named Gadfly for deep learning through dialogue. Use this skill when the user wants to learn, understand, or explore a topic through questions rather than explanations. Trigger when the user says "teach me about...", "help me understand...", "I want to learn...", "ask me questions about...", "quiz me", "Socratic method", "Gadfly", or wants to deeply understand something through dialogue rather than passive reading. Also trigger when the user provides a text or document and wants to be questioned about it, or wants to check their own understanding of a concept.

> Ingest documents at scale into Amazon OpenSearch using OpenSearch Ingestion Service (OSIS) pipelines. Upload pre-generated JSONL chunks to S3 and OSIS indexes them — optionally using semantic_enrichment in the sink to create the index with ASE automatically. Cloud ingestion — uploading raw PDF/DOCX and letting document_extractor parse them in the cloud — is available via private beta. Use this skill when the user wants to ingest documents into a cloud OpenSearch domain or collection, process documents at full volume beyond local limits, or set up an OSIS pipeline. Activate even if the user says OSIS, ingestion pipeline, document extraction, S3 ingestion, managed ingestion, or cloud processing.

> Process unstructured documents into search-ready chunks. Use this skill when the user wants to process PDFs or unstructured documents into JSONL chunks using Docling. Activate even if the user says document processing, chunking, Docling, PDF processing, or chunk quality evaluation. For cloud-scale ingestion via OSIS pipelines, see cloud/managed-ingestion-service.

> Process unstructured documents (PDF, DOCX, PPTX, XLSX) into search-ready JSONL chunks using Docling. Runs locally — no AWS or cloud services needed. Use this skill when the user wants to prepare documents for indexing, chunk documents, evaluate chunk quality, or convert PDFs to searchable text. Activate even if the user says process documents, chunk my files, prepare for search, or Docling.

> Build search applications and query log analytics data with OpenSearch. Use this skill when the user mentions OpenSearch, search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic search, RAG, embeddings, KNN, PDF ingestion, document processing, or any related search topic. Also use for log analytics and observability — when the user wants to set up log ingestion, query logs with PPL, analyze error patterns, set up index lifecycle policies, investigate traces, or check stack health. Activate even if the user says log analysis, Fluent Bit, Fluentd, Logstash, syslog, traceId, OpenTelemetry, or log analytics without mentioning OpenSearch.

> Build search applications with OpenSearch. Use this skill when the user mentions search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic search, RAG, embeddings, KNN, PDF ingestion, document processing, search quality evaluation, or any related search topic.

> Build search applications with OpenSearch from scratch. Use this skill when the user mentions search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic search, RAG, embeddings, KNN, PDF ingestion, document processing, or any related search topic. Activate even if the user says search quality, evaluation, nDCG, precision, relevance tuning, or search builder without mentioning OpenSearch.

Cadrer un projet par questionnement structuré et produire ou étendre `docs/PRD.md` selon un template fixe en 8 sections (Problème, Solution, Utilisateur cible, User Stories, Critères de succès, Hors périmètre, Décisions d'implémentation, Notes complémentaires). Utilise sur /cadre, "cadre ce projet", "écris le PRD", "fais-moi un PRD", "crée le PRD", "produis le PRD", "étends le PRD", ou dès qu'il faut formaliser le cadrage d'un projet dans un document versionné. Pair naturel de /interroge (amont) et /planifie (aval).

Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance, issue-tracker and domain-document conventions, preview the proposed configuration, and write only after approval. It does not install Atelier or initialize external tooling.

> Conducts a structured post-incident review following NIST SP 800-61 Rev 2 Post-Incident Activity guidance. Auto-invoked when an incident has been resolved and the team needs to conduct a blameless retrospective, reconstruct the timeline, perform root cause analysis, document lessons learned, and track remediation actions. Produces a PIR report with metrics (MTTD, MTTR, MTTC), control failure mapping, and actionable improvement plan.

> Analyzes Software Bills of Materials (SBOMs) for completeness against NTIA minimum elements, interprets VEX status documents, performs transitive dependency risk analysis, and detects license conflicts. Supports CycloneDX 1.5 and SPDX 2.3 formats with CSAF-based VEX correlation. Auto-invoked when SBOM files are shared, supply chain risk questions arise, or VEX documents require interpretation.

Build and configure the DevExpress Blazor Grid (DxGrid) — a full-featured data grid for Blazor Server, WebAssembly, and Hybrid apps. Use when binding tabular data (IEnumerable/IQueryable/EF Core/server-mode/custom sources), enabling sorting/filtering/grouping/search, implementing CRUD editing (row/edit form/popup/cell), handling selection and focused rows, exporting to CSV/XLSX/PDF, customizing templates and summaries, and supporting large datasets with virtualization. Also use for DxGrid, DevExpress grid, Blazor data grid, virtual scrolling, server mode, and grid feature comparisons or migration scenarios.

Build and configure the DevExpress Blazor TreeList (DxTreeList) — a hierarchical data grid / tree grid for Blazor Server, WebAssembly, and Hybrid apps. Use when displaying tree-structured or parent-child data; binding flat data with KeyFieldName, ParentKeyFieldName, and RootValue; expanding/collapsing nodes; sorting, filtering, search box, and filter panel; implementing CRUD editing for tree nodes; exporting to CSV/XLSX/PDF; loading child nodes on demand; and reordering/re-parenting nodes with drag-and-drop. Also use for DxTreeList, DevExpress TreeList, tree grid, hierarchical grid, parent-child table, and tree grid feature comparisons or migration scenarios.

Build .NET applications with the DevExpress AI-Powered Extensions for Office File API to add NLP-powered document processing capabilities — proofreading, translation, and text transformation for Word documents, PDF files, and PowerPoint presentations. Use when integrating AI language models (Azure OpenAI, OpenAI, Ollama, Google Gemini) with document processing workflows, translating documents programmatically, or proofreading documents with AI. Also use when someone mentions "DevExpress AI", "AIIntegration.Docs", "AIDocProcessingService", "proofread Word document", "translate PDF", "AI document processing .NET", or asks about AI-powered document automation with DevExpress. Requires DevExpress v25.2+.

>- Create, load, modify, secure, and print PDF documents using the new DevExpress.Docs.Pdf API — a modern object-oriented DOM approach for .NET. Use when building .NET applications that need to programmatically generate or edit PDF files using the new DevExpress PDF Document API (CTP). Also use when someone mentions "DevExpress.Docs.Pdf", "new PDF API", "PdfDocument class", "pdf fragment", "pdf pages collection", "pdf form fields", "pdf redaction", "pdf structure tree", "tagged pdf", "pdf/ua", "pdf encryption", "pdf annotations new API", or asks to migrate from PdfDocumentProcessor to the new API. Covers both .NET and .NET Framework.

Build .NET applications with the DevExpress PDF Document API for creating, reading, editing, merging, signing, and extracting content from PDF files programmatically. Use when working with PDF documents, PDF generation, PDF graphics API, interactive PDF forms, digital signatures, PDF/A compliance, text extraction, image extraction, PDF merging/splitting, bookmarks, hyperlinks, annotations, or XMP metadata. Also use when someone mentions "DevExpress PDF", "PdfDocumentProcessor", "PdfGraphics", "DevExpress.Pdf", "create PDF in C#", "merge PDF .NET", "sign PDF", "extract text from PDF", or asks about any PDF automation with DevExpress. Covers both .NET and .NET Framework.

Build .NET applications with the DevExpress Presentation API for creating, reading, modifying, and exporting PowerPoint presentations programmatically without Microsoft Office. Use when working with .pptx files, slides, shapes, text, tables, slide masters and layouts, themes, slide backgrounds, notes, headers/footers, or exporting presentations to PDF. Also use when someone mentions "DevExpress Presentation", "Presentation API", "DevExpress.Docs.Presentation", "create PowerPoint in C#", "pptx automation .NET", "merge presentations", or asks about any PowerPoint/presentation processing with DevExpress. Covers .NET.

Build .NET applications with the DevExpress Word Processing Document API for creating, reading, modifying, and exporting Word documents programmatically without Microsoft Office. Use when working with .docx, .doc, .rtf, .odt, .txt documents, paragraphs, tables, styles, mail merge, headers/footers, fields, track changes, or document conversion. Also use when someone mentions "DevExpress Word", "Word Processing Document API", "RichEditDocumentServer", "DevExpress.XtraRichEdit", "create Word document in C#", "docx automation", "mail merge .NET", or asks about any Word/document processing with DevExpress. Covers both .NET and .NET Framework.

> Create reports programmatically with DevExpress XtraReports runtime API (.NET and .NET Framework). Build XtraReport in code, add bands (DetailBand, GroupHeaderBand), controls (XRLabel, XRTable, XRChart), parameters, expressions. Bind to data sources, calculated fields, group reports. Export to PDF, Excel, Word, CSV, HTML, Images with ExportOptions. Master-detail, subreports, cross-tabs. Works cross-platform WinForms, WPF, ASP.NET Core, Blazor.

DevExpress WinForms Data Grid — GridControl with GridView, BandedGridView, AdvBandedGridView, CardView, LayoutView, TileView, and WinExplorerView, plus the TreeList for hierarchical data. Covers data binding (regular, ServerMode, InstantFeedback, VirtualServerModeSource), column generation (PopulateColumns, AddVisible, unbound columns via UnboundExpression, bands, ColumnEdit), cell display and editing (RepositoryItem, CustomRowCellEdit, DisplayFormat, edit forms, OptionsColumn), conditional formatting (FormatRules), validation (ValidateRow, SetColumnError), filtering (Excel-style, Auto Filter Row, Find Panel, ActiveFilterString), sorting and grouping (SortInfo, GroupInterval), master-detail (LevelTree, pattern views), print and export (ExportToXlsx/Pdf), focus and selection (FocusedRow, MultiSelect), drag-and-drop, and layout persistence (SaveLayoutToXml). Use for any WinForms grid, tree-list, or card-view scenario.

Expert skill for the DevExpress WinForms XtraTabControl (DevExpress.XtraTab, DevExpress.Win.Navigation NuGet). Build tabbed UIs that organize controls into pages — add/remove XtraTabPage pages via the TabPages collection or designer, populate pages, position and orient headers (HeaderLocation, HeaderOrientation), wrap headers into rows (MultiLine), show Prev/Next/Close header buttons (HeaderButtons) and per-page Close buttons (ClosePageButtonShowMode), respond to selection (SelectedPageChanged/SelectedPageChanging) and close (CloseButtonClick) events, hide headers for wizard-style navigation (ShowTabHeader), add header icons (XtraTabPage.ImageOptions), and add custom header buttons (CustomHeaderButtons). Use when a user asks about WinForms tab control, tabbed pages, XtraTabControl, XtraTabPage, tab headers, closable tabs, tab navigation, or organizing controls into pages on a form. For MDI/document interfaces use DocumentManager or XtraTabbedMdiManager instead.

Build WPF applications with the DevExpress Data Grid (GridControl) — a data-aware control that displays and edits data in table, card, and treelist layouts. Use when adding GridControl to a WPF project, binding to data sources (Entity Framework Core, XPO, local collections, ICollectionView, virtual sources, server mode), configuring columns and editors, sorting, filtering, grouping, summaries, master-detail, conditional formatting, printing, and exporting (XLSX/CSV/PDF). Also use when someone mentions "DevExpress WPF grid", "GridControl", "TableView", "CardView", "TreeListView", "dxg:GridControl", "DevExpress.Xpf.Grid", "DevExpress.Wpf.Grid", "Items Source Wizard", "WPF data grid", or asks about working with tabular data, server-mode large datasets, instant feedback mode, or grid CRUD operations in WPF. Covers both .NET 8+ and .NET Framework 4.6.2+.

Build WPF tabbed UIs with DevExpress DXTabControl — define tabs explicitly as DXTabItem children or generate them from a data collection via ItemsSource + ItemHeaderTemplate / ItemTemplate, pick one of three views (MultiLine, Scroll, Stretch) for how headers overflow, customize colors per tab (AccentColor/BorderColor), and template every region of the control (left/right control box, content header/footer, panel area). Use when building document tabs, settings panes, master-detail editors, or any tabbed-page UI in WPF. Also use when someone mentions "DXTabControl", "DXTabItem", "TabControlMultiLineView", "TabControlScrollView", "TabControlStretchView", "TabContentCacheMode", "AccentColor", "AllowHide", "Glyph", "PinMode", or "DragDropMode". The host window should be ThemedWindow (not Window) for proper visual integration. Covers .NET 8+ and .NET Framework 4.6.2+.

>- XAF Reports V2 module, data export, and printing. Covers adding the Reports module (AddReports with ReportDataType and EnableInplaceReports), CollectionDataSource and ViewDataSource for report data binding, creating predefined static reports with PredefinedReportsUpdater.AddPredefinedReport and duplicate guards, registering reports in Module.GetModuleUpdaters, in-place reports (ShowInReport Action, IsInplaceReport), invoking report preview from code via ReportServiceController.ShowPreview and IReportStorage handles, filtering report data with CriteriaOperator, passing parameters via OnBeforeShowPreview and scoped services, customizing export options (ExportOptions), printing without preview, accessing Report Designer and Report Viewer controls in Blazor (DxReportDesigner, DxReportViewer), data export from List Views (ExportController, CSV/XLS/XLSX/PDF/HTML/RTF/DOCX), and ReportDataV2 DbContext registration for EF Core.

Add supplementary materials (PDF, PPTX, DOCX, images) to a lecture session. Converts to Markdown via MarkItDown and indexes into the course wiki — without triggering transcription or slide download.

Build and serve the static course knowledge base locally. Rebuilds from workspace data and starts an HTTP server on port 8765.

Use when a user wants applicant-facing diagnosis and revision advice on a Chinese NSFC (国自然) application draft — asks for 本子把脉, 本子体检, 国自然申请书修改建议, NSFC benzi audit, 帮我看国自然本子, 标书逻辑诊断, 青年/面上/地区基金申请书修改, 对照已中本子, or 从中标样本提炼写法规律 — or wants critique of the title, abstract, key scientific questions, rationale, research contents, innovation, feasibility, research basis, or cross-section consistency. Accepts PDF/DOCX/Markdown/text or extracted draft text. This is applicant revision advice, not formal communication-review opinions; for expert review forms use nsfc-review.

1C:Naparnik (1С:Напарник) MCP server tools - BSL code analysis, review, rewriting, ITS knowledge base, platform documentation search, configuration documentation. Use when checking BSL code quality, searching ITS standards, reading platform docs, comparing versions, or finding configuration-specific documentation.

>- Read, understand and safely edit Cleverence Mobile SMARTS (Склад 15 / Магазин 15) configuration stored as .mslx files - the XML algorithm graphs that drive handheld terminal (ТСД) workflows in 1C integration projects. Use this skill whenever the task touches Cleverence / Mobile SMARTS / "Клеверенс" / ТСД algorithms, .mslx files, document types or operations (обработчики) on the terminal, menu/scan/КМ logic on a scanner, calling 1C online from the TSD, or "почему скан не срабатывает / действие не найдено / кнопка не работает" on a handheld - even if the user does not say ".mslx" explicitly. Covers the action graph, transition chaining, OperationAction parameter mapping, the online 1C call mechanism, marking-code (КМ) line operations, and the CL_-copy rule for not breaking vendor operations on update.

Конвертируй Markdown-файл в DOCX. Используй когда пользователь просит конвертировать, преобразовать .md в .docx, сделать Word из Markdown

Рендерит mermaid-диаграммы в PNG/SVG/PDF через локальный mermaid-cli (mmdc). Используй когда пользователь просит отрендерить mermaid, сделать PNG из диаграммы, превратить mermaid в картинку, конвертировать .mmd в png/svg/pdf, извлечь mermaid из markdown в картинки, сохранить блок mermaid как изображение, нарисовать диаграмму. Принимает .mmd / .mermaid (одна диаграмма) или .md (рендерит каждый блок ```mermaid в отдельную картинку). Поддерживает темы (default/forest/dark/neutral), цвет фона и масштаб для retina. Без Docker и MCP - чистый локальный mmdc.

Auto-generates standardized README documentation from SKILL.md files, validates consistency (frontmatter, descriptions, terminology), and creates usage examples. Use when documenting individual skills, generating docs for multiple skills in a directory, or validating skill quality standards.

Proactive token budget assessment and task chunking strategy. Use this skill when queries involve multiple large file uploads, requests for comprehensive multi-document analysis, complex multi-step workflows with heavy research (10+ tool calls), phrases like "complete analysis", "full audit", "thorough review", "deep dive", or tasks combining extensive research with large output artifacts. This skill helps assess token consumption risk early and recommend chunking strategies before beginning work.

Create new capabilities and skills systematically. Architects, documents, and implements reusable skills with proper specifications.

Document capabilities and skills comprehensively. Creates skill documentation with examples, specifications, and usage patterns.

Collaborate on document creation and refinement. Merges contributions, manages versions, and produces unified documents from multiple sources.

Build chat interfaces for querying documents using natural language. Extract information from PDFs, GitHub repositories, emails, and other sources. Use when creating interactive document Q&A systems, knowledge base chatbots, email search interfaces, or document exploration tools.