Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add DevExpress/agent-skills --skill devexpress-office-file-api-ai-powered-extensionsgit clone --depth 1 https://github.com/DevExpress/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/devexpress/agent-skills/devexpress-office-file-api-ai-powered-extensions)<a href="https://agentmods.dev/skills/devexpress/agent-skills/devexpress-office-file-api-ai-powered-extensions"><img src="https://agentmods.dev/badge/skills/devexpress/agent-skills/devexpress-office-file-api-ai-powered-extensions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/devexpress/agent-skills/devexpress-office-file-api-ai-powered-extensions"><img src="https://agentmods.dev/badge/skills/devexpress/agent-skills/devexpress-office-file-api-ai-powered-extensions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 301 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00148 | $0.04560 |
| Opus 5 | $0.00074 | $0.02280 |
| Sonnet 5 | $0.00030 | $0.00912 |
| Haiku 4.5 | $0.00015 | $0.00456 |
Grade A, and why
devexpress-office-file-api-ai-powered-extensions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevExpress AI-Powered Extensions for Office File API
The DevExpress AI-Powered Extensions integrate language models into the Office File API through the Microsoft.Extensions.AI (IChatClient) abstraction. Extensions support proofreading, translation, summarization, and contextual Q&A (Ask AI) for Word Processing documents, PDF files, and PowerPoint presentations. Both cloud providers (Azure OpenAI, OpenAI, Google Gemini) and local models (Ollama, ONNX Runtime, AI Foundry Local) are supported. The API follows a BYOK ("bring your own key") model — no DevExpress-hosted LLM is included.
When to Use This Skill
Use this skill when you need to:
- Proofread a Word document (.docx) or PowerPoint presentation with AI (grammar, spelling, style)
- Translate a Word document, PDF file, or PowerPoint presentation to another language
- Translate a specific paragraph, range, slide, or page region rather than the whole document
- Summarize the content of a Word document, PDF file, or presentation
- Ask contextual questions about document content using RAG (Retrieval-Augmented Generation)
- Register an AI provider (Azure OpenAI, OpenAI, Ollama, Gemini, ONNX, AI Foundry Local) with the DevExpress container
- Use the
AIDocProcessingServiceorIAIDocProcessingServicein a console app or ASP.NET Core / Blazor application - Preserve formatting while performing AI-powered document transformations
- Process documents in a headless / server-side .NET environment without a UI control
Prerequisites & Installation
NuGet Packages
| Package | Purpose |
|---|---|
DevExpress.AIIntegration |
Core AI container and IChatClient wiring |
DevExpress.AIIntegration.Docs |
Office File API AI extensions (AIDocProcessingService) |
DevExpress.Document.Processor |
Word Processing and Spreadsheet document engines |
DevExpress.Docs.Presentation |
Presentation (PPTX) document engine |
Plus one AI provider package group (choose one):
| Provider | Required Packages |
|---|---|
| Azure OpenAI | Azure.AI.OpenAI (2.2.0-beta.5), Microsoft.Extensions.AI.OpenAI (9.7.1-preview) |
| OpenAI | OpenAI (2.2.0), Microsoft.Extensions.AI.OpenAI (9.7.1-preview) |
| Ollama (self-hosted) | OllamaSharp |
| Google Gemini / Claude (Semantic Kernel) | Microsoft.SemanticKernel, Microsoft.SemanticKernel.Connectors.* |
| AI Foundry Local | Microsoft.AI.Foundry.Local (0.8.2.1+), Microsoft.Extensions.AI.OpenAI |
| ONNX Runtime | Microsoft.ML.OnnxRuntimeGenAI |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 340 lines · 148 tokens per session scan A ce5e3b009f5d
devexpress-office-file-api-ai-powered-extensions is a skill published in the GitHub repository DevExpress/agent-skills (53 stars, last pushed 24d ago), licensed MIT. It adds 148 tokens to every session and 4,560 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
TEMPLATE
../../../agents/personas/TEMPLATE.md.
ov-add-paper
Load when the user asks to add, import, compile, or ingest a research paper/PDF into OpenViking, especially when they mention ov-add-paper, ARA, claims, evidence, figures, tables, or paper-to-OV knowledge resources.
Presentations
Read, create or edit PowerPoint or Google Slides decks. Use for presentation, slide deck, PowerPoint, PPT, PPTX, or Google Slides requests.
Spreadsheets
Create, edit, analyze, and verify standalone spreadsheet files or Google Sheets-ready workbooks, including .xlsx, .xls, .csv, and .tsv. Do not use for live controlling Microsoft Excel app or a live Excel session.
template-creator
Create or update a reusable personal Codex artifact-template skill. Use when the user invokes $template-creator or asks in natural language to create a reusable template from a reference document, presentation, spreadsheet, ImageGen or Product Design image, email, or Slack message, or explicitly asks to edit or update…
slides
Create and edit presentation slide decks (.pptx) with PptxGenJS and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding charts/diagrams/visuals, or diagnosing layout…