What is orchardcore-ai-documents?

A document-processing feature for Orchard Core that uploads files, extracts their text, splits it into smaller sections, creates vector representations, and searches those vectors for AI conversations. Retrieval-Augmented Generation (RAG) means finding relevant stored content before generating an answer.

Use it to build document upload and storage flows, index supported files with Azure AI Search or Elasticsearch, and retrieve relevant content for AI responses.

It lets an AI chat use information from uploaded PDFs, Office files, and plain text instead of relying only on its general training. CSV and XLSX files use a separate tabular workflow.

orchardcore-ai-documents — Skill for Claude Code by CrestApps

Install

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.

Any agent

npx skills add CrestApps/CrestApps.AgentSkills --skill orchardcore-ai-documents

Clone the repo

git clone --depth 1 https://github.com/CrestApps/CrestApps.AgentSkills

Made for: Claude Code.

Or install crestapps-orchardcore, the plugin that ships this one along with the rest of its 94 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/orchardcore-ai-documents/github.svg)](https://agentmods.dev/skills/crestapps/crestapps.agentskills/orchardcore-ai-documents)

Your own site

<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/orchardcore-ai-documents"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/orchardcore-ai-documents/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/orchardcore-ai-documents"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/orchardcore-ai-documents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 216 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,919 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

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 →

medium Excessive Agency · line 263
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00216	$0.02919
Opus 5.5	$0.00086	$0.01168
Sonnet 5.5	$0.00043	$0.00584
Haiku 4.5	$0.00022	$0.00292

Measured 3d ago against content hash 9304c5b561b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

orchardcore-ai-documents 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 3d 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.

plugins/crestapps-orchardcore/skills/orchardcore-ai-documents/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchard Core AI Documents

Configure document upload and RAG

You are an Orchard Core expert. Generate configuration, recipes, and code that let users and administrators attach documents to CrestApps AI chat surfaces, and let the model retrieve from them.

Guidelines

The base feature CrestApps.OrchardCore.AI.Documents is EnabledByDependencyOnly. It depends on CrestApps.OrchardCore.AI.Chat.Interactions and OrchardCore.Indexing, and comes along with any of the sub-features below.
Embeddable documents follow upload, scan, extract, chunk, embed, index, and vector search. Tabular files (.csv, .tsv, .xlsx, .xls) are non-embeddable; they are loaded into the conversation's tabular workspace instead.
Indexing needs an AI Documents index profile from CrestApps.OrchardCore.AI.Documents.Elasticsearch or CrestApps.OrchardCore.AI.Documents.AzureAI (see orchardcore-ai-documents-elasticsearch and orchardcore-ai-documents-azureai).
The AI Documents index names its embedding deployment. The picker lists deployments in the embedding slot, so the deployment must declare textEmbedding. It is locked once the index exists.
Pick the active index once. Changing it later loses access to documents of existing sessions.
PDF and Office formats need the extractor features (see orchardcore-ai-documents-extractors). Azure Blob Storage is optional (see orchardcore-ai-documents-azure-storage).
Every upload is scanned before it is stored. Enable OrchardCore.Antivirus to add ClamAV.
Install packages in the web/startup project.

Features

Feature	Feature ID	Depends on
AI Documents	`CrestApps.OrchardCore.AI.Documents`	`CrestApps.OrchardCore.AI.Chat.Interactions`, `OrchardCore.Indexing` (dependency only)
AI Documents for Chat Interactions	`CrestApps.OrchardCore.AI.Documents.ChatInteractions`	AI Documents
AI Documents for Profiles	`CrestApps.OrchardCore.AI.Documents.Profiles`	AI Documents, `CrestApps.OrchardCore.AI.Chat.Core`
AI Documents for Chat Sessions	`CrestApps.OrchardCore.AI.Documents.ChatSessions`	AI Documents, `CrestApps.OrchardCore.AI.Chat`
AI Documents - Azure Blob Storage	`CrestApps.OrchardCore.AI.Documents.Azure`	AI Documents
AI Documents indexing using Azure AI Search	`CrestApps.OrchardCore.AI.Documents.AzureAI`	AI Documents, `OrchardCore.AzureAI`
AI Documents indexing using Elasticsearch	`CrestApps.OrchardCore.AI.Documents.Elasticsearch`	AI Documents, `OrchardCore.Elasticsearch`
AI Documents (PDF)	`CrestApps.OrchardCore.AI.Documents.Pdf`	none
AI Documents (OpenXml)	`CrestApps.OrchardCore.AI.Documents.OpenXml`	none

Read the full file on GitHub · 223 lines

Changes

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.

3d ago Changed · -104 lines · +91 tokens per session 9304c5b561b1
1mo ago First seen · 327 lines · 125 tokens per session scan A 5dc0b640a754

Subscribe to this mod's changes

orchardcore-ai-documents is a skill published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed 4d ago), licensed MIT. It adds 216 tokens to every session and 2,919 once invoked, about $0.0009 per session on Opus 5.5. 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.

Data and AI Documents RAG and vectors agent-skills ai ai-agents-framework dotnet mcp mcp-server

hybrid-rag

Create and query a per-review hybrid RAG index of included PRISMA evidence. Uses dense sentence-transformers retrieval plus BM25 (Qdrant/ChromaDB) or native FTS (LanceDB), fused with Reciprocal Rank Fusion.

giovannifrontera/academic-research-prisma-wiki-rag · 56 tokens

markitdown

Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

K-Dense-AI/scientific-agent-skills · 62 tokens

azure-ai

Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.

microsoft/skills · 76 tokens

microsoft-extensions-ai

Build provider-agnostic .NET AI integrations with Microsoft.Extensions.AI, IChatClient, embeddings, middleware, structured output, vector search, and evaluation. USE FOR: building or reviewing .NET code that uses Microsoft.Extensions.AI, Microsoft.Extensions.AI.Abstractions, IChatClient, IEmbeddingGenerator…

managedcode/dotnet-skills · 128 tokens

managedcode-markitdown

Use ManagedCode.MarkItDown when a .NET application needs deterministic document-to-Markdown conversion for ingestion, indexing, summarization, or content-processing workflows. USE FOR: ManagedCode.MarkItDown integration; document ingestion flows; Office or rich-text conversion to Markdown; indexing and summarization…

managedcode/dotnet-skills · 113 tokens

rag-web-fallback

Only reach for external web search when the local corpus comes back empty or clearly insufficient. Forces the agent to try knowledge-rag first, then explicitly document why it needed to escalate. Prevents wasted API cost, latency, and (in air-gapped deployments) accidental network calls.

lyonzin/knowledge-rag · 61 tokens