Agent skill
pencil-mcp-batch-get
Batch search and read node information. The Agent's 'Eyes'. Use to find specific components e.g. all nodes named 'Button' or get child structure within a container.
Install this agent skill to your Project
npx add-skill https://github.com/partme-ai/full-stack-skills/tree/main/skills/pencil-skills/pencil-mcp-batch-get
SKILL.md
Tools
This skill is designed to call the Pencil MCP tool:
batch_get
If your client namespaces MCP tools, it may appear as mcp__pencil__batch_get.
When to use this skill
Intent Recognition (CRITICAL)
Even if a trigger phrase matches, you must verify the user's intent:
- Is the user explicitly asking to use "Pencil"?
- Is the current conversation context clearly about "Pencil" design tasks?
If the answer is NO, do NOT use this skill. (e.g., if the user just says "Find the button" in a general context, they might mean simple text search or other tools).
CRITICAL PREREQUISITE: You must ONLY use this skill when the user EXPLICITLY mentions "Pencil".
ALWAYS use this skill when:
- You need to Find specific nodes by name or ID.
- You need to Read the properties of specific nodes.
- You need to inspect the children of a Frame.
- The user asks to "Find the button", "Get properties of X" in Pencil.
Trigger phrases include:
- "Pencil find all buttons" (Pencil 查找所有按钮)
- "Get node info with Pencil" (用 Pencil 获取节点信息)
- "Read properties using Pencil" (使用 Pencil 读取属性)
- "Pencil search components" (Pencil 搜索组件)
Input Parameters
filePath(string, optional): Path to file.patterns(array, optional): Search patterns (e.g.,["name=Button"]).nodeIds(array, optional): Specific IDs to read.searchDepth(integer, optional): Depth for search.readDepth(integer, optional): Depth for reading children structure. Keep low (<3).includePathGeometry(boolean, optional): Include vector path data.resolveVariables(boolean, optional): Return computed values instead of variable refs.
How to use this skill
- Combine Requests: If you need to search AND read by ID, do it in ONE call.
- Smart Traversal:
- Start with top-level or known IDs.
- If you see
...(truncated children), make a new call with those specific child IDs.
- Design Systems: To list available components, search for reusable nodes inside the design system frame.
Examples
1. Simple: Get Root Children
Get the top-level nodes of the document to understand the general structure. See 1-get-root.json.
2. Medium: Search by Name
Find all nodes that contain "Button" in their name. See 2-search-name.json.
3. Complex: Detailed Search
Search for specific nodes by ID and name pattern, resolving variables to see actual values, and getting full geometry. See 3-detailed-search.json.
Keywords
English keywords: batch get, search nodes, find elements, read properties, inspect structure, get components
Chinese keywords (中文关键词): 批量获取, 搜索节点, 查找元素, 读取属性, 检查结构, 获取组件
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ocrmypdf-batch
OCRmyPDF batch processing skill — process multiple PDFs, Docker automation, shell scripting, and CI/CD integration. Use when the user needs to OCR many PDFs, set up automated OCR pipelines, or integrate OCR into workflows.
ocrmypdf-optimize
OCRmyPDF optimization skill — compress PDFs, configure PDF/A output, JBIG2 encoding, and lossless optimization. Use when the user needs to reduce PDF file size, create archival PDF/A files, or optimize OCR output.
ocrmypdf-image
OCRmyPDF image processing skill — deskew, rotate, clean, despeckle, remove border from scanned documents. Use when the user needs to improve scanned PDF quality, fix skewed pages, remove noise, or clean up scanned documents before OCR.
ocrmypdf-api
OCRmyPDF Python API and plugin skill — use OCRmyPDF programmatically from Python, integrate with applications, and extend with plugins (EasyOCR, PaddleOCR, AppleOCR). Use when the user needs to call OCRmyPDF from Python code, build OCR pipelines, or use alternative OCR engines.
ocrmypdf
OCRmyPDF core skill — add searchable OCR text layer to scanned PDFs, convert images to searchable PDFs, support 100+ languages via Tesseract. Use when the user needs to OCR a PDF, make a scanned PDF searchable, or extract text from scanned documents.
svelte
Guides Svelte and SvelteKit development including reactive components, stores, transitions, lifecycle hooks, SSR, file-based routing, and deployment. Use when the user needs to build Svelte components, create SvelteKit applications, implement reactivity patterns, or configure Svelte with Vite.
Didn't find tool you were looking for?