How do I install the Crestapps Core AI Markdown skill?

Run npx skillmds@latest add crestapps/crestapps-core-ai-markdown in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Crestapps Core AI Markdown safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Crestapps Core AI Markdown?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Crestapps Core AI Markdown free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Crestapps Core AI Markdown?

CrestApps (@crestapps) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Crestapps Core AI Markdown by crestapps

Name: Crestapps Core AI Markdown
Rating: 4.2 (5 reviews)
Author: CrestApps

File contents

CrestApps.Core AI Markdown - Prompt Templates

Normalize Markdown for AI

You are a CrestApps.Core expert. Generate code and guidance for Markdown-aware text normalization used by CrestApps.Core document-processing and RAG workflows.

Guidelines

Reference the standalone CrestApps.Core.AI.Markdown package when Markdown-aware normalization is needed.
Call AddMarkdown() on CrestAppsAISuiteBuilder, or call AddCoreAIMarkdown() directly on IServiceCollection.
Registration adds MarkdownAITextNormalizer as the singleton IAITextNormalizer.
The normalizer delegates content, chunking, and title cleanup to RagTextNormalizer.
It strips HTML, parses Markdown through Microsoft.Extensions.DataIngestion.Markdig, and extracts plain text before normalizing whitespace.

Register Markdown Support

builder.Services.AddCrestAppsCore(crestApps => crestApps
    .AddAISuite(ai => ai
        .AddMarkdown()
        .AddDocumentProcessing(documentProcessing => documentProcessing
            .AddEntityCoreStores()
            .AddOpenXml()
            .AddPdf())));

For direct service registration:

builder.Services.AddCoreAIMarkdown();

Normalization Behavior

Operation	`MarkdownAITextNormalizer` method	Behavior
Document content	`NormalizeContentAsync`	HTML stripping, Markdown parsing, text extraction, whitespace cleanup
Retrieval chunks	`NormalizeAndChunkAsync`	Markdown parsing followed by token-aware chunking
Titles	`NormalizeTitle`	HTML stripping and whitespace cleanup

The default chunker uses the gpt-4o tokenizer with 500 tokens per chunk and 50 overlapping tokens. If Markdig encounters an unsupported inline type, the normalizer uses its built-in plain-text fallback instead of failing the ingestion flow.

Use with Document Processing

AddMarkdown() complements AddDocumentProcessing(...); it does not register document stores, upload endpoints, PDF readers, or Office readers. Add those separately according to the formats and storage provider the application needs.

---name: crestapps-core-ai-markdowndescription: Skill for registering Markdig-backed Markdown normalization in CrestApps.Core AI document and RAG flows.---# CrestApps.Core AI Markdown - Prompt Templates## Normalize Markdown for AIYou are a CrestApps.Core expert. Generate code and guidance for Markdown-aware text normalization used by CrestApps.Core document-processing and RAG workflows.### Guidelines- Reference the standalone `CrestApps.Core.AI.Markdown` package when Markdown-aware normalization is needed.- Call `AddMarkdown()` on `CrestAppsAISuiteBuilder`, or call `AddCoreAIMarkdown()` directly on `IServiceCollection`.- Registration adds `MarkdownAITextNormalizer` as the singleton `IAITextNormalizer`.- The normalizer delegates content, chunking, and title cleanup to `RagTextNormalizer`.- It strips HTML, parses Markdown through `Microsoft.Extensions.DataIngestion.Markdig`, and extracts plain text before normalizing whitespace.### Register Markdown Support```csharpbuilder.Services.AddCrestAppsCore(crestApps => crestApps .AddAISuite(ai => ai .AddMarkdown() .AddDocumentProcessing(documentProcessing => documentProcessing .AddEntityCoreStores() .AddOpenXml() .AddPdf())));```For direct service registration:```csharpbuilder.Services.AddCoreAIMarkdown();```Register Markdown after the base AI services when replacing their default `IAITextNormalizer`.### Normalization Behavior| Operation | `MarkdownAITextNormalizer` method | Behavior ||---|---|---|| Document content | `NormalizeContentAsync` | HTML stripping, Markdown parsing, text extraction, whitespace cleanup || Retrieval chunks | `NormalizeAndChunkAsync` | Markdown parsing followed by token-aware chunking || Titles | `NormalizeTitle` | HTML stripping and whitespace cleanup |The default chunker uses the `gpt-4o` tokenizer with 500 tokens per chunk and 50 overlapping tokens. If Markdig encounters an unsupported inline type, the normalizer uses its built-in plain-text fallback instead of failing the ingestion flow.### Use with Document Processing`AddMarkdown()` complements `AddDocumentProcessing(...)`; it does not register document stores, upload endpoints, PDF readers, or Office readers. Add those separately according to the formats and storage provider the application needs.

Frequently asked questions

Crestapps Core AI Markdown