Document Browser

Organization

pnp

document-browser

Create or update a professional live-linked document browser dashboard for a SharePoint document library, using real metadata fields, a clean navy-and-yellow design system, visible refresh, reliable SharePoint Open/Download links, and a 3-card desktop layout. Use when the user says: - "create a document browser" - "make a live dashboard for this document library" - "build a document library dashboard" - "use the document browser skill on this library" - "make sure the dashboard is live linked"

Overview

Publisher	pnp
Repository	`sharepoint-skills`
Skill name	`document-browser`
Stars	141
Forks	60
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

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 Document Browser AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/pnp/sharepoint-skills/tree/main/Skills/document-browser/document-browser
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/pnp/sharepoint-skills/tree/main/Skills/document-browser/document-browser

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/document-browser/document-browser .claude/skills/document-browser

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Document Browser 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 Document Browser 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 Document Browser 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.

Document Browser

When to use

Use this skill when the user wants a professional document browser dashboard for a SharePoint document library or folder. The dashboard must browse documents using real metadata, search, filters, cards, read-only Open links, Download links, and live-linked data whenever supported.

Inputs

Target SharePoint document library URL, list ID, or selected/current library.
Optional folder path inside the library.
Optional approval rule, default: show approved documents only when content approval is enabled.
Optional dashboard file name and destination folder.
Optional requested filters.

Steps

Resolve and inspect
- Resolve the target library ID and web URL.
- Retrieve the full schema and use internal field names only.
- Identify approval status, Document Title, name/path fields, description/abstract, metadata filters, Document Owner, contacts, author/editor, created/modified dates.
Title and owner rules
- Prefer Document Title for card titles. Match Document Title, documentTitle, and Document_x0020_Title.
- Fall back to Title, then file name.
- Show Document Owner name directly below the card title. Match documentOwner / Document Owner; fall back to Author only if no owner exists.
Live-linked build
- Use LiveData/list binding for supported library roots or list sources.
- Include ka-livedata-manifest and runtime code that reads window.__LD_RESULTS__.
- Include a visible Refresh live data button wired to refresh().
- Don't claim live-linked unless newly added/updated source documents appear after refresh without regenerating HTML.
Design requirements Use this exact visual system:

Color palette
- Navy: #03274A
- Blue: #164C80
- Yellow accent: #FFD633
- Pale blue: #CAD8E5
- Line / border: #D7E2EC
- Sand background: #F7F5F3
- Text: #161616
- Muted text: #5A5A57
Typography
- Primary font stack: Aptos, "Segoe UI", Arial, sans-serif
Hero header
- Large rounded navy (or navy-to-blue gradient) hero banner
- Soft yellow translucent circle accent in the upper-right
- Short uppercase kicker in yellow with letter-spacing
- Large white title
- Pale lead text under the title
- Optional simple flat-vector illustration on the right side of the hero
Layout & cards
- Exactly 3 document cards per desktop row (grid-template-columns: repeat(3, minmax(0, 1fr))), collapsing to 2 then 1 on smaller screens
- White cards with subtle border (#D7E2EC), soft shadow, and large border-radius (~20–22px)
- Left yellow accent bar on the card header area
- Document title in navy, bold
- Document Owner / contacts shown directly under the title in muted text
- Abstract preview with hover/focus popup
- Metadata shown as small rounded pills
- Pill-shaped action buttons (primary = solid blue, secondary = outlined)
Overall feel
- Clean, modern, professional knowledge-browser aesthetic
- Generous white space, soft shadows, clear hierarchy
- Card-first design (avoid dense tables)
Dashboard features
- Search across Document Title/title, filename, abstract/description, metadata, Document Owner, contacts, author/editor.
- Filter using real fields. Prefer Practice, Service Area, Industry Sectors, Market, Regions, Lead Office, Document Type, Year created when present.
- Cards include title, Document Owner below title, abstract preview with hover/focus popup, metadata pills, dates, Open and Download actions.
Open and Download link rules — critical
- In SharePoint HTML preview the dashboard runs inside about:srcdoc; do not use location.origin for Open or Download because it may resolve to null.
- Define a constant site URL from the resolved web URL, e.g. var SITE='https://tenant.sharepoint.com/sites/site';.
- Do not render href="#". If no path is available, render a disabled text control instead.
- Build links from a decoded server-relative SharePoint path.
- Resolve path in this order: FileRef / File_x0020_Ref / ServerRelativeUrl / Path; then EncodedAbsUrl parsed to pathname; then FileDirRef + '/' + FileLeafRef.
- Use safeDecode() repeatedly before encoding route parameters so Documents%2520Browser becomes Documents Browser, then re-encodes only once.
- Verified working Open pattern: SITE + '/_layouts/15/Doc.aspx?sourcedoc=' + encodeURIComponent(serverRelativePath) + '&file=' + encodeURIComponent(fileName) + '&action=embedview&mobileredirect=true'.
- The serverRelativePath must be decoded first, then encoded exactly once in the sourcedoc route parameter.
- Do not replace this with the direct file URL ?web=1&action=embedview unless it has been manually tested in the target dashboard after saving.
- Do not use download.aspx?SourceUrl=...&transform=pdf for Open; it can fail with File Not Found when spaces are double-encoded.
- Download: SITE + '/_layouts/15/download.aspx?SourceUrl=' + encodeURIComponent(serverRelativePath).
- Add target="_blank", rel="noopener", and data-interception="off".
- Never use PDF transform links for Open; never append download=1; validate no %2520, no null/sites, no href="#", and no absolute URL inside SourceUrl.
Validate before saving
- Confirm live manifest/source exists.
- Confirm visible refresh control exists and is wired.
- Confirm 3-column desktop grid exists.
- Confirm Document Title is first title source and Document Owner appears below title.
- Confirm the navy / yellow / sand design system and hero structure are present.
- Confirm Open uses the verified Doc.aspx?sourcedoc=...&file=...&action=embedview&mobileredirect=true pattern; confirm Download uses SITE, robust source-path fallback, and neither link renders #, null/sites, PDF transform, direct untested ?web=1&action=embedview, or double-encoded %2520.
Save
- Create or update an .html file in the requested destination.
- Prefer saving HTML dashboards to a Reports library or the location requested by the user unless updating an explicitly selected existing file.
- Provide the file link.

Output format

Respond with:

Link to the dashboard.
Whether it is fully live-linked.
Note that it uses 3 desktop columns, Document Title, Document Owner below title, the navy-and-yellow design system, visible refresh, and robust decoded server-relative Open/Download links.
Any limitation or workaround.

Honesty

If live binding can't target the requested folder or view, say so and offer a workaround. Don't invent working links or data.

Frequently asked questions

What does the Document Browser AI skill do?

Why use Document Browser on TypingMind?

Because you install it once and use it with any model. Document Browser 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 Document Browser in TypingMind?

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

Which AI models can use Document Browser?

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 Document Browser?

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

Is the Document Browser 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

Plan Canvas

affaan-m

CommunityPopular

Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or…

Improve Codebase Architecture

mattpocock

CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Teach

Teach the user a new skill or concept, within this workspace.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Document Browser

When to use

Inputs

Steps

Output format

Honesty

Frequently asked questions

Related AI Skills

Set up your own AI workspace now