Linkding logo

Linkding

Community
jmagar
linkding

Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.

Overview

Publisherjmagar
Repositoryclaude-homelab
Skill namelinkding
Stars
87
Forks
11
Bundled files
5
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.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Linkding 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/jmagar/claude-homelab/tree/main/skills/linkding
  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/jmagar/claude-homelab.git /tmp/claude-homelab
mkdir -p .claude/skills
cp -r /tmp/claude-homelab/skills/linkding .claude/skills/linkding
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Linkding 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 Linkding 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 Linkding 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.

Linkding Bookmark Manager

⚠️ MANDATORY SKILL INVOCATION ⚠️

YOU MUST invoke this skill (NOT optional) when the user mentions ANY of these triggers:

  • "search bookmarks", "Linkding", "bookmark manager", "my bookmarks"
  • "add bookmark", "save link", "save this URL", "save this page", "bookmark this"
  • "archived bookmarks", "archive link", "reading list"
  • "check bookmarks", "find bookmark", "bookmark tags", "show bookmarks tagged X"
  • "did I bookmark this", "did I save this URL", "is this saved"
  • "delete bookmark", "remove bookmark", "remove link"
  • Any mention of Linkding or bookmark management

Failure to invoke this skill when triggers occur violates your operational requirements.

Query and manage bookmarks via the Linkding REST API.

Purpose

This skill provides read and write access to your Linkding bookmark library:

  • Search and list bookmarks by query, tags, or date
  • Add new bookmarks with metadata (title, description, tags)
  • Update existing bookmarks
  • Archive/unarchive bookmarks
  • Delete bookmarks
  • Manage tags and bundles (saved searches)
  • Check if URLs are already saved

Operations include both read and write actions. Always confirm before deleting bookmarks.

Setup

Credentials: ~/.claude-homelab/.env

bash
LINKDING_URL="http://localhost:9090"
LINKDING_API_KEY="your-api-key"

Get your API token from Linkding Settings page.

Quick Reference

List/Search Bookmarks

bash
# List recent bookmarks
./scripts/linkding-api.sh bookmarks

# Search bookmarks
./scripts/linkding-api.sh bookmarks --query "python tutorial"

# List archived
./scripts/linkding-api.sh bookmarks --archived

# Filter by date
./scripts/linkding-api.sh bookmarks --modified-since "2025-01-01T00:00:00Z"

Create Bookmark

bash
# Basic
./scripts/linkding-api.sh create "https://example.com"

# With metadata
./scripts/linkding-api.sh create "https://example.com" \
  --title "Example Site" \
  --description "A great resource" \
  --tags "reference,docs"

# Archive immediately
./scripts/linkding-api.sh create "https://example.com" --archived

Check if URL Exists

bash
./scripts/linkding-api.sh check "https://example.com"

Returns existing bookmark data if found, plus scraped metadata.

Update Bookmark

bash
./scripts/linkding-api.sh update 123 --title "New Title" --tags "newtag1,newtag2"

Archive/Unarchive

bash
./scripts/linkding-api.sh archive 123
./scripts/linkding-api.sh unarchive 123

Delete

bash
./scripts/linkding-api.sh delete 123

Tags

bash
# List all tags
./scripts/linkding-api.sh tags

# Create tag
./scripts/linkding-api.sh tag-create "mytag"

Bundles (saved searches)

bash
# List bundles
./scripts/linkding-api.sh bundles

# Create bundle
./scripts/linkding-api.sh bundle-create "Work Resources" \
  --search "productivity" \
  --any-tags "work,tools" \
  --excluded-tags "personal"

Response Format

All responses are JSON. Bookmark object:

json
{
  "id": 1,
  "url": "https://example.com",
  "title": "Example",
  "description": "Description",
  "notes": "Personal notes",
  "is_archived": false,
  "unread": false,
  "shared": false,
  "tag_names": ["tag1", "tag2"],
  "date_added": "2020-09-26T09:46:23.006313Z",
  "date_modified": "2020-09-26T16:01:14.275335Z"
}

Common Patterns

Save current page for later:

bash
./scripts/linkding-api.sh create "$URL" --tags "toread" --unread

Quick search and display:

bash
./scripts/linkding-api.sh bookmarks --query "keyword" --limit 10 | jq -r '.results[] | "\(.title) - \(.url)"'

Bulk tag update: Update via API PATCH with new tag_names array.

Workflow

When the user asks about bookmarks:

  1. "Save this link for later" → Run create <url> with appropriate metadata and tags
  2. "Find my bookmarks about Python" → Run bookmarks --query "python"
  3. "Is example.com already saved?" → Run check "https://example.com"
  4. "Archive old bookmarks" → Search first, then archive <id> for each
  5. "What tags do I have?" → Run tags
  6. "Show recent bookmarks" → Run bookmarks (defaults to recent)

Notes

  • Requires network access to your Linkding server
  • Uses Linkding REST API v1
  • All data operations return JSON
  • Delete operations are permanent - always confirm before deleting
  • URL checking includes automatic metadata scraping
  • Tags are created automatically when used in bookmarks
  • Bundles are saved searches with filter criteria

🔧 Agent Tool Usage Requirements

CRITICAL: When invoking scripts from this skill via the zsh-tool, ALWAYS use pty: true.

Without PTY mode, command output will not be visible even though commands execute successfully.

Correct invocation pattern:

typescript
<invoke name="mcp__plugin_zsh-tool_zsh-tool__zsh">
<parameter name="command">./skills/SKILL_NAME/scripts/SCRIPT.sh [args]</parameter>
<parameter name="pty">true</parameter>
</invoke>

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Linkding AI skill do?

Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.

Why use Linkding on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jmagar/claude-homelab/tree/main/skills/linkding. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Linkding?

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 Linkding?

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

Is the Linkding AI skill free?

Yes. It is published on GitHub by jmagar 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 👇