Agent skill
tui-message-input
Generate and render a pixel-precise ASCII TUI Message Input component with complete output blocks (TUI_RENDER, COMPONENT_SPEC, PENCIL_SPEC, PENCIL_BATCH_DESIGN) for Pencil MCP drawing workflows. Use when the user asks to create a message input in a terminal UI, text-based interface, or Pencil MCP project.
Install this agent skill to your Project
npx add-skill https://github.com/partme-ai/full-stack-skills/tree/main/skills/t2ui-skills/tui-message-input
SKILL.md
Purpose
- Produce an ASCII Text UI (TUI) representation of Message Input.
- Always output layout attributes (top/left/width/height, spacing, colors, typography, zIndex).
- Always output Pencil MCP–ready specs and a
batch_designplan (≤25 operations per call).
Workflow
- Parse input — Read the input model JSON (widthCols, grid, props, state, style, typography, layout, hotkeys).
- Calculate layout — Convert column/row positions to pixel coordinates using the grid (cellWidthPx=8, cellHeightPx=16).
- Render TUI_RENDER — Build the monospace ASCII art with box-drawing characters, respecting widthCols.
- Build COMPONENT_SPEC — Emit the JSON spec with bbox, style, typography, state, and hotkeys.
- Build PENCIL_SPEC — Emit the canvas and component list for Pencil MCP.
- Plan PENCIL_BATCH_DESIGN — Emit batch_design calls (max 25 ops per call) to create the design in Pencil.
- Validate — Verify bbox dimensions in COMPONENT_SPEC match the TUI_RENDER grid; confirm batch ops stay within the 25-op limit.
Input Model (Recommended)
{
"widthCols": 70,
"grid": { "cellWidthPx": 8, "cellHeightPx": 16 },
"props": {},
"modelValue": null,
"state": { "focused": false, "disabled": false, "loading": false, "error": null },
"style": {
"fillColor": "#ffffff",
"textColor": "#111111",
"strokeColor": "#e5e7eb",
"strokeThickness": 1,
"cornerRadius": 12
},
"typography": { "fontFamily": "Inter", "fontSize": 14, "fontWeight": 400, "lineHeight": 20 },
"layout": { "paddingPx": 16, "gapPx": 8 },
"hotkeys": []
}
Output Contract (Mandatory)
OUTPUT: TUI_RENDER
...monospace-only text...
OUTPUT: COMPONENT_SPEC
{
"id": "tui-message-input_1",
"name": "Message Input",
"type": "tui-message-input",
"bbox": { "topPx": 0, "leftPx": 0, "widthPx": 0, "heightPx": 0 },
"zIndex": 1,
"layout": { "paddingPx": 16, "gapPx": 8, "align": "left", "valign": "top" },
"style": {
"fillColor": "#ffffff",
"textColor": "#111111",
"strokeColor": "#e5e7eb",
"strokeThickness": 1,
"cornerRadius": 12,
"opacity": 1
},
"typography": { "fontFamily": "Inter", "fontSize": 14, "fontWeight": 400, "lineHeight": 20 },
"overflow": { "mode": "truncate", "ellipsis": "…", "maxLines": 1 },
"state": { "focused": false, "disabled": false, "loading": false, "error": null },
"hotkeys": []
}
OUTPUT: PENCIL_SPEC
{
"canvas": { "widthPx": 390, "heightPx": 844, "backgroundColor": "#ffffff" },
"grid": { "cellWidthPx": 8, "cellHeightPx": 16 },
"nodes": [],
"components": []
}
OUTPUT: PENCIL_BATCH_DESIGN
CALL 1:
root=G()
screen=I(root,{type:"frame",name:"Screen"})
U(screen,{width:390,height:844,x:0,y:0})
CALL 2:
cmpBg=I(screen,{type:"rect",name:"Message Input/Background"})
U(cmpBg,{x:24,y:24,width:342,height:96,fillColor:"#ffffff",strokeColor:"#e5e7eb",strokeThickness:1,cornerRadius:12})
cmpText=I(screen,{type:"text",name:"Message Input/Text",content:"Message Input"})
U(cmpText,{x:40,y:56,width:310,height:20,textColor:"#111111",fontFamily:"Inter",fontSize:14,fontWeight:600})
Rendering Rules (Component-Level)
Follow the shared rules from tui-front-ui:
- No TAB characters.
- Do not exceed
widthCols. - Provide a header row, body area, and minimal hotkeys if interactive.
disabled=truemust suppress interaction hints.loading=truemust show a stable placeholder.error!=nullmust be printed in a single line footer (truncated to width).
Examples (Must include all output blocks)
Example 1 — Minimal / default
OUTPUT: TUI_RENDER
┌──────────────────────────────────────────────────────────────┐
│ [Message Input] │
├──────────────────────────────────────────────────────────────┤
│ Search │
│ [ type here...______________________________ ] │
└──────────────────────────────────────────────────────────────┘
OUTPUT: COMPONENT_SPEC
{
"id": "tui-message-input_ex1",
"name": "Message Input",
"type": "tui-message-input",
"bbox": { "topPx": 24, "leftPx": 24, "widthPx": 342, "heightPx": 96 },
"zIndex": 1,
"layout": { "paddingPx": 16, "gapPx": 8, "align": "left", "valign": "top" },
"style": { "fillColor": "#ffffff", "textColor": "#111111", "strokeColor": "#e5e7eb", "strokeThickness": 1, "cornerRadius": 12, "opacity": 1 },
"typography": { "fontFamily": "Inter", "fontSize": 14, "fontWeight": 400, "lineHeight": 20 },
"overflow": { "mode": "truncate", "ellipsis": "…", "maxLines": 1 },
"state": { "focused": false, "disabled": false, "loading": false, "error": null },
"hotkeys": []
}
OUTPUT: PENCIL_SPEC
{
"canvas": { "widthPx": 390, "heightPx": 844, "backgroundColor": "#ffffff" },
"grid": { "cellWidthPx": 8, "cellHeightPx": 16 },
"nodes": [],
"components": [
{ "id": "tui-message-input_ex1", "name": "Message Input", "bbox": { "topPx": 24, "leftPx": 24, "widthPx": 342, "heightPx": 96 }, "zIndex": 1 }
]
}
OUTPUT: PENCIL_BATCH_DESIGN
CALL 1:
root=G()
screen=I(root,{type:"frame",name:"Screen"})
U(screen,{width:390,height:844,x:0,y:0})
CALL 2:
cmpBg=I(screen,{type:"rect",name:"Message Input/Background"})
U(cmpBg,{x:24,y:24,width:342,height:96,fillColor:"#ffffff",strokeColor:"#e5e7eb",strokeThickness:1,cornerRadius:12})
cmpText=I(screen,{type:"text",name:"Message Input/Text",content:"Message Input"})
U(cmpText,{x:40,y:56,width:310,height:20,textColor:"#111111",fontFamily:"Inter",fontSize:14,fontWeight:600})
Example 2 — Styled / customized
OUTPUT: TUI_RENDER
┌──────────────────────────────────────────────────────────────┐
│ [Message Input] │
├──────────────────────────────────────────────────────────────┤
│ Email │
│ [ ada@example.com|___________________________ ] [x] │
├──────────────────────────────────────────────────────────────┤
│ Keys: <tab> next <enter> commit <esc> back │
└──────────────────────────────────────────────────────────────┘
OUTPUT: COMPONENT_SPEC
{
"id": "tui-message-input_ex2",
"name": "Message Input",
"type": "tui-message-input",
"bbox": { "topPx": 24, "leftPx": 24, "widthPx": 342, "heightPx": 104 },
"zIndex": 1,
"layout": { "paddingPx": 20, "gapPx": 10, "align": "left", "valign": "top" },
"style": { "fillColor": "#ffffff", "textColor": "#111111", "strokeColor": "#111111", "strokeThickness": 2, "cornerRadius": 12, "opacity": 1 },
"typography": { "fontFamily": "Inter", "fontSize": 14, "fontWeight": 600, "lineHeight": 20 },
"overflow": { "mode": "truncate", "ellipsis": "…", "maxLines": 1 },
"state": { "focused": false, "disabled": false, "loading": false, "error": null },
"hotkeys": []
}
OUTPUT: PENCIL_SPEC
{
"canvas": { "widthPx": 390, "heightPx": 844, "backgroundColor": "#ffffff" },
"grid": { "cellWidthPx": 8, "cellHeightPx": 16 },
"nodes": [],
"components": [
{ "id": "tui-message-input_ex2", "name": "Message Input", "bbox": { "topPx": 24, "leftPx": 24, "widthPx": 342, "heightPx": 104 }, "zIndex": 1 }
]
}
OUTPUT: PENCIL_BATCH_DESIGN
CALL 1:
root=G()
screen=I(root,{type:"frame",name:"Screen"})
U(screen,{width:390,height:844,x:0,y:0})
CALL 2:
cmpBg=I(screen,{type:"rect",name:"Message Input/Background"})
U(cmpBg,{x:24,y:24,width:342,height:104,fillColor:"#ffffff",strokeColor:"#111111",strokeThickness:2,cornerRadius:12})
cmpText=I(screen,{type:"text",name:"Message Input/Text",content:"Message Input"})
U(cmpText,{x:40,y:60,width:310,height:20,textColor:"#111111",fontFamily:"Inter",fontSize:14,fontWeight:600})
Example 3 — Disabled / error / edge-case
OUTPUT: TUI_RENDER
┌──────────────────────────────────────────────────────────────┐
│ [Message Input] Disabled │
├──────────────────────────────────────────────────────────────┤
│ Password │
│ [ ••••••••••_______________________________ ] │
└──────────────────────────────────────────────────────────────┘
OUTPUT: COMPONENT_SPEC
{
"id": "tui-message-input_ex3",
"name": "Message Input",
"type": "tui-message-input",
"bbox": { "topPx": 24, "leftPx": 24, "widthPx": 342, "heightPx": 112 },
"zIndex": 1,
"layout": { "paddingPx": 16, "gapPx": 8, "align": "left", "valign": "top" },
"style": { "fillColor": "#ffffff", "textColor": "#6b7280", "strokeColor": "#e5e7eb", "strokeThickness": 1, "cornerRadius": 12, "opacity": 1 },
"typography": { "fontFamily": "Inter", "fontSize": 14, "fontWeight": 400, "lineHeight": 20 },
"overflow": { "mode": "truncate", "ellipsis": "…", "maxLines": 1 },
"state": { "focused": false, "disabled": true, "loading": false, "error": "Something went wrong" },
"hotkeys": []
}
OUTPUT: PENCIL_SPEC
{
"canvas": { "widthPx": 390, "heightPx": 844, "backgroundColor": "#ffffff" },
"grid": { "cellWidthPx": 8, "cellHeightPx": 16 },
"nodes": [],
"components": [
{ "id": "tui-message-input_ex3", "name": "Message Input", "bbox": { "topPx": 24, "leftPx": 24, "widthPx": 342, "heightPx": 112 }, "zIndex": 1 }
]
}
OUTPUT: PENCIL_BATCH_DESIGN
CALL 1:
root=G()
screen=I(root,{type:"frame",name:"Screen"})
U(screen,{width:390,height:844,x:0,y:0})
CALL 2:
cmpBg=I(screen,{type:"rect",name:"Message Input/Background"})
U(cmpBg,{x:24,y:24,width:342,height:112,fillColor:"#ffffff",strokeColor:"#e5e7eb",strokeThickness:1,cornerRadius:12,opacity:1})
cmpText=I(screen,{type:"text",name:"Message Input/Error",content:"Error: Something went wrong…"})
U(cmpText,{x:40,y:60,width:310,height:20,textColor:"#6b7280",fontFamily:"Inter",fontSize:14,fontWeight:400})
Component Summary Row (for page aggregation)
| id | name | top | left | width | height | z | keyProps | state | hotkeys |
| tui-message-input | Message Input | 0 | 0 | 0 | 0 | 0 | keyProps=... | state=... | hotkeys=... |
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?