Individual skill

crestapps-core-ai-markdown

Skill for Markdig-backed Markdown normalization in CrestApps.Core 2.0 AI document, data source and RAG flows. Covers the CrestApps.Core.AI.Markdown package, AddMarkdown on the AI suite builder and AddCoreAIMarkdown on IServiceCollection, MarkdownAITextNormalizer replacing the default IAITextNormalizer, RagTextNormalizer content, chunk and title normalization with HTML stripping and Microsoft.Extensions.DataIngestion.Markdig parsing, the gpt-4o tokenizer chunker with 500 tokens per chunk and 50 tokens of overlap, the plain-text fallback for unsupported inline types, where the normalizer is used (data source indexing, preemptive retrieval, reference titles), and pairing it with document processing. Use it when indexing Markdown-heavy content for retrieval, replacing the text normalizer, or troubleshooting chunk sizes and leftover markup in retrieved text.

plugins/crestapps-core/skills/crestapps-core-ai-markdown/SKILL.md

Read pinned source

Source commit d86d04f234b1b2bd8145368a2544490f9d557596

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Instructions only
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
13
Repository last updated
Oct 21, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# CrestApps.Core AI Markdown

`CrestApps.Core.AI.Markdown` makes text normalization Markdown-aware. It is opt-in: `AddCoreAIServices()` registers only the plain `DefaultAITextNormalizer`, and the core AI package does not depend on Markdig.

## Guidelines

- Reference the `CrestApps.Core.AI.Markdown` package and call `AddMarkdown()` on `CrestAppsAISuiteBuilder`, or `AddCoreAIMarkdown()` on `IServiceCollection` (namespace `CrestApps.Core.AI.Markdown`).
- Registration adds `MarkdownAITextNormalizer` as the singleton `IAITextNormalizer`. The base registration uses `TryAddSingleton` and this one uses `AddSingleton`, so the Markdown normalizer wins whichever is called first.
- The normalizer delegates to the static `RagTextNormalizer`: HTML is stripped, the text is parsed through `Microsoft.Extensions.DataIngestion.Markdig`, and plain text is extracted before whitespace is normalized.
- `AddMarkdown()` does not register document stores, readers or upload endpoints. Add document processing or ingestion separately (`crestapps-core-document-processing`).

## Register

```csharp