Style Bento logo

Style Bento

Organization
pnp
style-bento

Bento style tokens and row template for the list-styling skill. Card layout inspired by bento boxes — distinct compartments separated by thin borders, each section labeled, warm earth tones. Layout is a horizontal row of compartments (name | status | progress | deadline) with visible dividers between each. Use when the user says "bento," "compartment," "warm style," "earth tones," "organized," or similar.

Overview

Publisherpnp
Repositorysharepoint-skills
Skill namestyle-bento
Stars
141
Forks
60
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by pnp on GitHub. Read the source before you install it.

Installation

Install the Style Bento AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pnp/sharepoint-skills/tree/main/Skills/style-bento/style-bento
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pnp/sharepoint-skills.git /tmp/sharepoint-skills
mkdir -p .claude/skills
cp -r /tmp/sharepoint-skills/Skills/style-bento/style-bento .claude/skills/style-bento
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Style Bento in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Style Bento on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Style Bento is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Bento — Style Tokens + Row Template

Warm, organized, compartmentalized. Each row is a card divided into labeled compartments like a bento box — visible dividers, each section has a header label above its content.

Layout philosophy: Horizontal compartments with dividers. Not a sidebar split, not a single stack. Four distinct compartments in a row: Name | Status | Progress | Deadline. Each compartment has a tiny uppercase label above the content. The dividers between compartments ARE the design.

Badge Tokens

  • padding: 4px 10px
  • border-radius: 4px
  • font-size: 11px
  • font-weight: 600
  • text-transform: uppercase

status_colors

Valuebgtextborder
Draft#9ca3af#ffffff0px
In Review#3b82f6#ffffff0px
Revising#ea580c#ffffff0px
Approved#16a34a#ffffff0px
Published#15803d#ffffff0px
_fallback#d1d5db#ffffff0px

Progress Bar Tokens

  • progress_track_height: 8px
  • progress_track_bg: #f3f4f6
  • progress_track_border: 0px
  • progress_track_radius: 4px
  • progress_fill_radius: 4px
  • progress_color_low: #ef4444
  • progress_color_mid: #ea580c
  • progress_color_high: #22c55e
  • progress_label_font_size: 20px
  • progress_label_font_weight: 700
  • progress_label_color: #1f2937

Row Card Tokens

  • card_border: 1px solid #e5e7eb
  • card_border_radius: 8px
  • card_background: #ffffff
  • card_margin_bottom: 8px
  • card_shadow: 0px 1px 3px #0000000d
  • compartment_border: 1px solid #e5e7eb (dividers between sections)
  • compartment_label_color: #9ca3af
  • compartment_label_size: 9px
  • compartment_label_weight: 600
  • compartment_label_transform: uppercase
  • compartment_label_spacing: 0.5px
  • overdue_accent: 2px solid #dc2626 (left border accent on overdue cards)

Row Template Layout

Horizontal compartment grid. Each section is a labeled box.

┌──────────────────┬───────────┬──────────────────┬──────────────┐
│ DOCUMENT         │ STATUS    │ PROGRESS         │ DEADLINE     │
│                  │           │                  │              │
│ API Guide.docx   │ [In Rev]  │        72%       │ 📅 5/15/2026 │
│                  │           │ ████████████░░░  │ DEADLINE     │
│                  │ On Track  │                  │              │
└──────────────────┴───────────┴──────────────────┴──────────────┘
  ↑ overdue cards get a 2px red left border accent

rowFormatter JSON

Adapt before applying. The column names below ([$Status], [$Progress], [$Deadline]) are example placeholders — replace them with the actual internal column names from the user's list. Also update every status value string ('Draft', 'In Review', 'Revising', etc.) to match the user's actual Choice values. Follow list-styling Step 3.

json
{
  "$schema": "https://developer.microsoft.com/json-schemas/sp/v2/view-formatting.schema.json",
  "hideSelection": false,
  "hideColumnHeaders": true,
  "rowFormatter": {
    "elmType": "div",
    "style": {
      "display": "flex",
      "border": "1px solid #e5e7eb",
      "border-left": "=if([$Deadline] < @now, '3px solid #dc2626', '1px solid #e5e7eb')",
      "border-radius": "8px",
      "background-color": "#ffffff",
      "margin-bottom": "8px",
      "box-shadow": "0px 1px 3px #0000000d",
      "overflow": "hidden",
      "min-height": "90px"
    },
    "children": [
      {
        "elmType": "div",
        "style": {
          "flex": "2",
          "padding": "14px 16px",
          "display": "flex",
          "flex-direction": "column",
          "gap": "6px",
          "border-right": "1px solid #e5e7eb"
        },
        "children": [
          {
            "elmType": "span",
            "txtContent": "DOCUMENT",
            "style": {
              "font-size": "9px",
              "font-weight": "600",
              "color": "#9ca3af",
              "text-transform": "uppercase",
              "letter-spacing": "0.5px"
            }
          },
          {
            "elmType": "div",
            "style": {
              "font-size": "14px",
              "font-weight": "700",
              "color": "#1f2937",
              "line-height": "1.3"
            },
            "txtContent": "=if([$FileLeafRef] == '', [$Title], [$FileLeafRef])"
          }
        ]
      },
      {
        "elmType": "div",
        "style": {
          "flex": "1",
          "padding": "14px 16px",
          "display": "flex",
          "flex-direction": "column",
          "gap": "8px",
          "align-items": "center",
          "justify-content": "center",
          "border-right": "1px solid #e5e7eb"
        },
        "children": [
          {
            "elmType": "span",
            "txtContent": "STATUS",
            "style": {
              "font-size": "9px",
              "font-weight": "600",
              "color": "#9ca3af",
              "text-transform": "uppercase",
              "letter-spacing": "0.5px"
            }
          },
          {
            "elmType": "span",
            "txtContent": "[$Status]",
            "style": {
              "display": "inline-block",
              "padding": "4px 10px",
              "border-radius": "4px",
              "font-size": "11px",
              "font-weight": "600",
              "text-transform": "uppercase",
              "white-space": "nowrap",
              "color": "#ffffff",
              "background-color": "=if([$Status] == 'Draft', '#9ca3af', if([$Status] == 'In Review', '#3b82f6', if([$Status] == 'Revising', '#ea580c', if([$Status] == 'Approved', '#16a34a', if([$Status] == 'Published', '#15803d', '#d1d5db')))))"
            }
          },
          {
            "elmType": "span",
            "txtContent": "=if([$Deadline] < @now, '⚠ At Risk', '✓ On Track')",
            "style": {
              "font-size": "10px",
              "font-weight": "500",
              "color": "=if([$Deadline] < @now, '#dc2626', '#16a34a')"
            }
          }
        ]
      },
      {
        "elmType": "div",
        "style": {
          "flex": "1.5",
          "padding": "14px 16px",
          "display": "flex",
          "flex-direction": "column",
          "gap": "6px",
          "align-items": "center",
          "justify-content": "center",
          "border-right": "1px solid #e5e7eb"
        },
        "children": [
          {
            "elmType": "span",
            "txtContent": "PROGRESS",
            "style": {
              "font-size": "9px",
              "font-weight": "600",
              "color": "#9ca3af",
              "text-transform": "uppercase",
              "letter-spacing": "0.5px"
            }
          },
          {
            "elmType": "span",
            "txtContent": "=toString([$Progress]) + '%'",
            "style": {
              "font-size": "20px",
              "font-weight": "700",
              "color": "=if([$Progress] < 30, '#ef4444', if([$Progress] < 66, '#ea580c', '#16a34a'))"
            }
          },
          {
            "elmType": "div",
            "style": {
              "width": "100%",
              "height": "8px",
              "background-color": "#f3f4f6",
              "border-radius": "4px",
              "overflow": "hidden"
            },
            "children": [
              {
                "elmType": "div",
                "style": {
                  "width": "=toString([$Progress]) + '%'",
                  "height": "100%",
                  "border-radius": "4px",
                  "background-color": "=if([$Progress] < 30, '#ef4444', if([$Progress] < 66, '#ea580c', '#22c55e'))"
                }
              }
            ]
          }
        ]
      },
      {
        "elmType": "div",
        "style": {
          "flex": "1",
          "padding": "14px 16px",
          "display": "flex",
          "flex-direction": "column",
          "gap": "4px",
          "align-items": "center",
          "justify-content": "center"
        },
        "children": [
          {
            "elmType": "span",
            "txtContent": "DEADLINE",
            "style": {
              "font-size": "9px",
              "font-weight": "600",
              "color": "#9ca3af",
              "text-transform": "uppercase",
              "letter-spacing": "0.5px"
            }
          },
          {
            "elmType": "span",
            "txtContent": "=toLocaleDateString([$Deadline])",
            "style": {
              "font-size": "13px",
              "font-weight": "=if([$Deadline] < @now, '700', '500')",
              "color": "=if([$Deadline] < @now, '#dc2626', '#374151')"
            }
          },
          {
            "elmType": "span",
            "txtContent": "=if([$Deadline] < @now, '⚠ OVERDUE', '')",
            "style": {
              "font-size": "10px",
              "font-weight": "700",
              "color": "#dc2626"
            }
          }
        ]
      }
    ]
  }
}

Checklist — "I Can't Believe That's SharePoint"

  • ✅ Full rowFormatter — NOT default column grid
  • ✅ Horizontal compartment layout with VISIBLE DIVIDERS between sections
  • ✅ Each compartment has a tiny uppercase label (DOCUMENT, STATUS, PROGRESS, DEADLINE)
  • ✅ Labels are 9px, gray, uppercase with letter-spacing — subtle but structured
  • ✅ Progress percentage is LARGE (20px) and centered in its compartment
  • ✅ Warm earth-tone badge colors (burnt orange, olive green)
  • ✅ Overdue cards get a red left-border accent — not the whole border
  • ✅ No sidebar — this is a horizontal grid, like bento box compartments
  • ✅ Subtle shadow (not hard offset) — organized, not aggressive
  • ✅ On Track / At Risk indicator under the status badge
  • ✅ Completely different layout from Neobrutalism (compartments vs sidebar) and Glassmorphism (horizontal vs stacked)

Responsive / mobile

  • ≤ 600 px: bento compartments stack vertically rather than sitting side-by-side. Set the row container to flex-wrap: wrap and each compartment to min-width: 0 so titles ellipsis-truncate.
  • ≤ 480 px: hide the compartment labels (Document / Status / Progress / Deadline), keep only the values. The compartment dividers carry the structure on their own.
  • Padding step-down: 16px desktop → 12px tablet → 8px mobile.
  • Touch targets: any customRowAction element stays ≥ 44 × 44 px on mobile.

Implementation notes

The tokens + rowFormatter JSON in this file has grown large. When adapting it for a real library, treat the tokens block as the source of truth and re-derive the rowFormatter from it — do not mass-edit both halves of the file in parallel. A future iteration should split this into two reference files (tokens first, then rowFormatter that consumes them).

Frequently asked questions

What does the Style Bento AI skill do?

Bento style tokens and row template for the list-styling skill. Card layout inspired by bento boxes — distinct compartments separated by thin borders, each section labeled, warm earth tones. Layout is a horizontal row of compartments (name | status | progress | deadline) with visible dividers between each. Use when the user says "bento," "compartment," "warm style," "earth tones," "organized," or similar.

Why use Style Bento on TypingMind?

Because you install it once and use it with any model. Style Bento is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Style Bento in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pnp/sharepoint-skills/tree/main/Skills/style-bento/style-bento. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Style Bento?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Style Bento?

As many as you like. As long as a model supports skills, you can use Style Bento with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Style Bento AI skill free?

Yes. It is published on GitHub by pnp under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇