# Send Orchata to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "orchata", "name": "Orchata", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ehudsn/orchata", "canonicalUrl": "https://clawhub.ai/ehudsn/orchata", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/orchata", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=orchata", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "orchata", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-06T18:02:09.144Z", "expiresAt": "2026-05-13T18:02:09.144Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=orchata", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=orchata", "contentDisposition": "attachment; filename=\"orchata-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "orchata" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/orchata" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/orchata", "downloadUrl": "https://openagent3.xyz/downloads/orchata", "agentUrl": "https://openagent3.xyz/skills/orchata/agent", "manifestUrl": "https://openagent3.xyz/skills/orchata/agent.json", "briefUrl": "https://openagent3.xyz/skills/orchata/agent.md" } } ``` ## Documentation ### Orchata Skills This document describes how to effectively use Orchata, a RAG (Retrieval-Augmented Generation) platform with tree-based document indexing. Load this into your context to interact with Orchata knowledge bases. ### What is Orchata? Orchata is a knowledge management platform that: Organizes documents into Spaces - Logical containers for related content Uses tree-based indexing - Documents are parsed into hierarchical structures with sections, summaries, and page ranges Provides semantic search - Find relevant content using natural language queries Exposes MCP tools - AI assistants can directly manage and query knowledge bases ### Spaces A Space is a container for related documents. Think of it as a folder with semantic search capabilities. Each space has a name, description, and optional icon Descriptions are used by smart_query to recommend relevant spaces Spaces can be archived (soft-deleted) ### Documents A Document is content within a space. Supported formats include: PDF (text-based and scanned with OCR) Word documents (.docx) Excel spreadsheets (.xlsx) PowerPoint presentations (.pptx) Markdown files (.md) Plain text files (.txt) Images (PNG, JPG, etc.) Document Status: StatusDescriptionPENDINGUploaded, waiting for processingPROCESSINGBeing parsed and indexedCOMPLETEDReady for queriesFAILEDProcessing error occurred Important: Only query documents with status: "COMPLETED". Other statuses won't return results. ### Document Trees Documents are indexed into hierarchical tree structures: Each tree has nodes representing sections/chapters Nodes contain: title, summary, startPage, endPage, textContent Trees enable precise navigation of large documents ### Queries Two types of queries are available: query_spaces - Search document content using tree-based reasoning smart_query - Discover which spaces are relevant for a query ### Space Management list_spaces List all knowledge spaces in the organization. list_spaces list_spaces with status="active" list_spaces with page=1 pageSize=20 Parameters: page (number, optional): Page number (default: 1) pageSize (number, optional): Items per page (default: 10) status (string, optional): Filter by active, archived, or all manage_space Create, get, update, or delete a space. manage_space with action="create" name="Product Docs" description="Technical documentation" manage_space with action="create" name="Legal" description="Case files" icon="briefcase" manage_space with action="get" id="space_abc123" manage_space with action="update" id="space_abc123" description="Updated description" manage_space with action="delete" id="space_abc123" Parameters: action (string, required): create, get, update, or delete id (string): Space ID (required for get/update/delete) name (string): Space name (required for create) description (string, optional): Space description icon (string, optional): Icon name. Defaults to "folder" slug (string, optional): URL-friendly identifier isArchived (boolean, optional): Archive status (for update) Valid Icons: folder, book, file-text, database, package, archive, briefcase, inbox, layers, box If an invalid icon is provided, the tool returns an error with the list of valid options. ### Document Management list_documents List documents in a space. list_documents with spaceId="space_abc123" list_documents with spaceId="space_abc123" status="completed" list_documents with spaceId="space_abc123" status="all" Parameters: spaceId (string, required): Space ID page (number, optional): Page number pageSize (number, optional): Items per page (max: 100) status (string, optional): Filter by status. Values: pending, processing, completed, failed, or all. Omitting returns all documents. Note: Status values are case-insensitive (completed and COMPLETED both work). save_document Upload or upsert documents (single or batch). Single document: save_document with spaceId="space_abc123" filename="guide.md" content="# Guide\\n\\nContent here..." Batch upload: save_document with spaceId="space_abc123" documents=[{"filename": "doc1.md", "content": "..."}, {"filename": "doc2.md", "content": "..."}] Parameters: spaceId (string, required): Space ID filename (string): Filename (required for single) content (string): Content (required for single) documents (array, optional): Array of {filename, content, metadata} for batch metadata (object, optional): Custom key-value pairs get_document Get document content by ID or filename. Returns processed markdown text. get_document with spaceId="space_abc123" id="doc_xyz789" get_document with spaceId="space_abc123" filename="guide.md" get_document with spaceId="*" filename="guide.md" Parameters: spaceId (string, required): Space ID, or * to search all spaces (requires filename) id (string, optional): Document ID filename (string, optional): Filename Notes: Either id or filename is required Use spaceId="*" to search all spaces when you know the filename but not the space For completed documents, returns the extracted markdown text (not raw PDF binary) When using *, the response includes the spaceId where the document was found update_document Update document content or metadata. update_document with spaceId="space_abc123" id="doc_xyz789" content="New content..." update_document with spaceId="space_abc123" id="doc_xyz789" append=true content="Additional content" Parameters: spaceId (string, required): Space ID id (string, required): Document ID content (string, optional): New content metadata (object, optional): New metadata append (boolean, optional): Append instead of replace separator (string, optional): Separator for append mode delete_document Permanently delete a document. delete_document with spaceId="space_abc123" id="doc_xyz789" Parameters: spaceId (string, required): Space ID id (string, required): Document ID ### Query Tools query_spaces Search documents across one or more spaces using tree-based reasoning. query_spaces with query="How do I authenticate API requests?" query_spaces with query="installation guide" spaceIds="space_abc123" query_spaces with query="error handling" spaceIds=["space_abc", "space_def"] topK=10 Parameters: query (string, required): Natural language search query spaceIds (string or array, optional): Space ID(s) to search. Omit or use * for all spaces topK (number, optional): Maximum results (default: 10) compact (boolean, optional): Use compact format (default: false). See When to Use Compact below. When to Use Compact: ModeWhen to useWhat you getcompact=false (default)Most queries. Any time you need actual data, facts, numbers, dates, or details from documents.Full results with document metadata, tree context, page ranges, and complete content.compact=trueBroad discovery queries where you only need to know which documents are relevant, not their content.Minimal results: just content snippet, source filename, and score. Rule of thumb: Default to compact=false. Only use compact=true when you're browsing/surveying and don't need the actual content yet. Response (compact=true format): { "results": [ { "content": "Relevant text content...", "source": "filename.pdf", "score": 0.95 } ], "total": 5 } smart_query Discover which spaces are relevant for a query using LLM reasoning. smart_query with query="How do I install the SDK?" smart_query with query="billing questions" maxSpaces=3 Parameters: query (string, required): Query to find relevant spaces for maxSpaces (number, optional): Maximum spaces to return (default: 5) Response: { "query": "How do I install the SDK?", "relevantSpaces": [ {"spaceId": "space_abc123", "relevance": "Contains SDK installation guides"}, {"spaceId": "space_def456", "relevance": "Has developer tutorials"} ], "totalFound": 2 } Use case: When you don't know which space to search, use smart_query first to discover relevant spaces, then use query_spaces with those space IDs. ### Tree Visibility Tools These tools let you explore the hierarchical structure of indexed documents. get_document_tree Get the tree structure of a document showing sections, summaries, and page ranges. get_document_tree with spaceId="space_abc123" documentId="doc_xyz789" Parameters: spaceId (string, required): Space ID documentId (string, required): Document ID Response: { "documentId": "doc_xyz789", "totalPages": 45, "totalNodes": 12, "nodes": [ { "nodeId": "0001", "title": "Introduction", "summary": "Overview of the system architecture...", "pages": "1-5", "depth": 0 }, { "nodeId": "0002", "title": "Installation", "summary": "Step-by-step installation guide...", "pages": "6-12", "depth": 0 } ] } Use case: Use this to understand a document's structure before drilling into specific sections. get_tree_node Get the full text content of a specific tree node/section. get_tree_node with documentId="doc_xyz789" nodeId="0002" Parameters: documentId (string, required): Document ID nodeId (string, required): Node ID from the tree structure Response: { "documentId": "doc_xyz789", "filename": "manual.pdf", "nodeId": "0002", "title": "Installation", "summary": "Step-by-step installation guide...", "pages": "6-12", "depth": 0, "content": "## Installation\\n\\nTo install the software, follow these steps:\\n\\n1. Download the installer...\\n\\n..." } Use case: After viewing the tree structure, use this to read the full content of a specific section. ### Pattern 1: Search for Information (Default Approach) For most questions, a single query_spaces call is all you need. Start here before trying multi-step workflows. query_spaces with query="your question" This searches all spaces with full details (compact=false by default). One call, done. If you want to narrow to specific spaces: query_spaces with query="your question" spaceIds="known_space_id" If you truly don't know which spaces exist: smart_query with query="your question" # Then use the returned spaceIds: query_spaces with query="your question" spaceIds=["returned_space_id"] Avoid over-searching. The multi-step workflow (smart_query -> query_spaces -> get_document_tree -> get_tree_node) is rarely necessary. For most questions, a single query_spaces call returns the answer directly. Only escalate to tree browsing if results are insufficient. ### Pattern 2: Look Up Specific Data When looking for specific facts, numbers, dates, names, or details: Just query directly -- one call: query_spaces with query="total amount on invoice #1234" The default compact=false returns full content with document metadata, so you get the actual data you need in one step. Do not use compact=true for data lookups -- it strips the detail you need. ### Pattern 3: Browse a Large Document When you need to navigate a large document's structure: Get the document structure: get_document_tree with spaceId="space_id" documentId="doc_id" Identify relevant sections from the node titles and summaries Read specific sections: get_tree_node with documentId="doc_id" nodeId="relevant_node_id" ### Pattern 4: Add New Content When adding documents to a knowledge base: Find or create the appropriate space: list_spaces # or manage_space with action="create" name="New Space" description="..." Upload the content: save_document with spaceId="space_id" filename="document.md" content="..." Wait for processing (status will change from PENDING -> PROCESSING -> COMPLETED) Verify it's ready: list_documents with spaceId="space_id" status="COMPLETED" ### manage_space - Valid Icons When creating or updating a space, use one of these icon values: folder (default) book file-text database package archive briefcase inbox layers box Invalid icons will return a helpful error message with the list of valid options. ### list_documents - Status Parameter The status parameter accepts the following values (case-insensitive): "all" - Returns documents in any status (COMPLETED, FAILED, PENDING, PROCESSING) "completed" - Returns only successfully processed documents "failed" - Returns only documents that failed processing (includes errorMessage field) "pending" - Returns documents waiting to be processed "processing" - Returns documents currently being processed Documents with status="FAILED" will include an errorMessage field explaining what went wrong during processing. ### save_document - Processing Workflow Documents are processed asynchronously: save_document returns immediately with status="PROCESSING" Background job generates embeddings and indexes the document (typically 1-3 seconds) Status changes to "COMPLETED" when ready Document becomes searchable via query_spaces To check completion status: Use get_document to check a specific document's status Use list_documents with status="processing" to see all processing documents Use list_documents with status="failed" to see any failures Example: // Save document const result = await save_document({...}); // result.document.status === "PROCESSING" // Check status after a moment const doc = await get_document({id: result.document.id}); // doc.status === "COMPLETED" (when ready) ### get_tree_node - Content Availability get_tree_node may return "(No text content cached for this node)" for certain nodes. This occurs for: Structural/organizational nodes without associated text content Nodes that serve as section headers in the tree hierarchy This is expected behavior. To read actual document content: Use get_document to retrieve the full processed markdown Use query_spaces to search and retrieve relevant content chunks The tree structure (via get_document_tree) is always available and shows document organization, summaries, and page ranges. ### DO Start with a single query_spaces call - it usually has the answer in one step Use compact=false (the default) for most queries - you get full content and context Check document status before querying - only COMPLETED documents are searchable Use descriptive queries - natural language works best Use tree tools for large documents - navigate structure instead of reading everything Write good space descriptions - they're used by smart_query for discovery ### DON'T Don't over-search - avoid multi-step workflows (smart_query -> query_spaces -> get_document_tree -> get_tree_node) when a single query_spaces call suffices Don't use compact=true for data lookups - it strips the content you need; only use it for broad discovery Don't query PENDING/PROCESSING documents - they won't return results Don't use very short queries - more context = better results Don't forget to check processing status after uploading new documents ### Error Handling Common errors and solutions: ErrorCauseSolution"Document not found"Wrong ID or no accessVerify the document ID with list_documents"Space not found"Wrong ID or archivedUse list_spaces to find valid space IDsEmpty search resultsDocument not COMPLETED or no matchesCheck document status; try broader query"Tree not found"Document uses vector indexing or not processedCheck if document status is COMPLETED"Invalid icon"Icon name not in allowed listUse one of: folder, book, file-text, database, package, archive, briefcase, inbox, layers, box"No text content cached"Tree node content not cachedThis is normal for structural nodes; use get_document for full content ### Troubleshooting Tips If save_document fails: Verify the space exists with manage_space with action="get" id="..." Ensure content is valid text/markdown Check that the space is not archived If list_documents returns 0 results: Try status="all" or omit the status parameter entirely Verify the spaceId is correct with list_spaces Check if documents are still processing (status="processing") If get_tree_node returns no content: Some nodes are structural and don't have cached text content Use get_document to get the full processed document text instead Or use query_spaces to search for specific content ### Quick Reference TaskToolExampleList all spaceslist_spaceslist_spaces with status="active"Create a spacemanage_spacemanage_space with action="create" name="Docs"List documentslist_documentslist_documents with spaceId="..."Upload contentsave_documentsave_document with spaceId="..." content="..."Get document textget_documentget_document with spaceId="..." id="..."Search contentquery_spacesquery_spaces with query="..."Find relevant spacessmart_querysmart_query with query="..."View doc structureget_document_treeget_document_tree with spaceId="..." documentId="..."Read a sectionget_tree_nodeget_tree_node with documentId="..." nodeId="..." ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ehudsn - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-06T18:02:09.144Z - Expires at: 2026-05-13T18:02:09.144Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/orchata) - [Send to Agent page](https://openagent3.xyz/skills/orchata/agent) - [JSON manifest](https://openagent3.xyz/skills/orchata/agent.json) - [Markdown brief](https://openagent3.xyz/skills/orchata/agent.md) - [Download page](https://openagent3.xyz/downloads/orchata)