NxcoreAI/EverRoom

draft-continue

Continue a document with genuinely new appended content only.

Idioma del texto original: chino

draft-create

Draft a brand-new document from the instruction and material, returning the title and chunked body markdown.

Idioma del texto original: chino

draft-edit

Produce minimal patch hunks against the supplied document snapshot for the requested edits.

Idioma del texto original: chino

room-enrichment

Organize a newly created Context Room from its title and description into structured room info. Use for room-enrich tasks.

Idioma del texto original: chino

document-export

One-shot export of a fixed Room document version to Feishu or Notion via the preinstalled lark-cli / OpenConnector channel, with explicit auth and confirmation gates.

Idioma del texto original: chino

correction

Compute Room overview corrections—citation corrections as per-claim edits and general corrections as a single proposal.

Idioma del texto original: chino

rewrite

Rewrite only the supplied selectedText per the instruction and return the replacement fragment.

Idioma del texto original: chino

merge-name

Suggest names for a Context Room created by merging two rooms. Use for merge-name tasks.

Idioma del texto original: chino

room-proposals

Recommend Context Rooms to create from a user description, uploaded materials, and extracted entity anchors.

Idioma del texto original: chino

room-overview

Generate a source-grounded Context Room overview from Room facts and applied user corrections.

Idioma del texto original: chino

entity-extraction

Extract searchable entities and a concise summary from a document for EverRoom knowledge routing.

Idioma del texto original: chino

brief-refresh

Regenerate a Context Room brief from the room's current documents and context. Use for brief-refresh tasks.

Idioma del texto original: chino

parsing-workflow

Parse and validate one authorized Office or PDF file version without overstating unsupported multimodal coverage.

Idioma del texto original: inglés

diary-timeline

将当天的多源事实整理为去重、按时间排序、可追溯的日记时间线。

Idioma del texto original: chino

ingest-filter

Judge whether ingested materials contain information worth retaining in EverRoom.

Idioma del texto original: chino

gmail-sync

Normalize read-only Gmail messages into EverRoom email records during connector synchronization. Use when the job service is gmail and resourceType is email.

Idioma del texto original: inglés

google-calendar-sync

Normalize read-only Google Calendar events into EverRoom calendar records during connector synchronization. Use when the job service is google_calendar and resourceType is calendar.

Idioma del texto original: inglés

notion-sync

Normalize read-only Notion pages into EverRoom document records during connector synchronization. Use when the job service is notion and resourceType is document.

Idioma del texto original: inglés

analysis-method

A structured method for evidence-based analysis of supplied content

Idioma del texto original: inglés

document-cursor-completion

Complete a rich-text document at the cursor using the EverRoom FIM protocol. Use for editor cursor-completion requests.

Idioma del texto original: inglés

entity-identity

Judge whether two evidence-backed names refer to the same real-world entity.

Idioma del texto original: chino

entity-registration

Create canonical Room registration material from accumulated entity evidence.

Idioma del texto original: chino

transcription-memory-reconstruction

Reconstruct a complete, searchable memory from an untrusted meeting or conversation transcript. Use for EverRoom background transcription-summary jobs when the caller requires the fixed memory JSON contract.

Idioma del texto original: inglés