# April 19: Support for Evernote, replicas, skill feeds

### New Features

* 💡 Graphlit now supports **Evernote feeds**, including OAuth support and Evernote note/notebook ingestion.
* 💡 We have added **Replica APIs** for syncing content, conversations, and skills into external artifact stores, including Git-backed Markdown and WebVTT outputs.
* We have added **Skill feeds** for installing skill packages from GitHub or GitLab, with preview support for new, updated, unchanged, and invalid skills.
* We have added **on-demand content classification** result types for classifying content outside the normal ingestion workflow.
* We have added **content Markdown export** support through `markdown(maxTokens)`, `markdownUri`, and content snippets.
* We have improved **CSV table embedding** support for better retrieval over structured tabular content.
* We have added **conversation criteria** inputs for more targeted conversation queries and agent workflows.

### Bugs Fixed

* Improved Notion client serialization coverage for newer and unknown Notion block types.
* Improved summarization instruction caching for repeated summarization workflows.
* Improved external content read behavior for connector-backed feeds.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://changelog.graphlit.dev/april-2026/april-19-support-for-evernote-replicas-skill-feeds.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.