Browsing History

Community

glebis

browsing-history

Query browsing history from all synced devices (iPhone, Mac, iPad, desktop). Supports natural language queries for filtering by date, device, domain, and keywords. Uses LLM classification for content categories. Can output to stdout or save as markdown/JSON to Obsidian vault.

Overview

Publisher	glebis
Repository	`claude-skills`
Skill name	`browsing-history`
Stars	379
Forks	56
Bundled files	3
License	MIT
Links	Skill source Repository

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.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by glebis on GitHub. Read the source before you install it.

Installation

Install the Browsing History 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.
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.

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/glebis/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/browsing-history .claude/skills/browsing-history

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

Use it in TypingMind

Enable Browsing History 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 Browsing History 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 Browsing History 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.

Browsing History Skill

Query browsing history from all synced devices with natural language.

When to Use

Use this skill when the user asks about:

Articles/pages they read (yesterday, last week, etc.)
Browsing history from specific devices (iPhone, iPad, desktop)
Finding pages by topic, domain, or keyword
Exporting browsing history to files
Grouping history by category or domain

Database

Location: ~/data/browsing.db

Synced devices: iPhone, iPad, Mac, desktop, Android

Timestamps

visit_time: Actual visit timestamp from Chrome (100% coverage for all devices)
first_seen: Import timestamp (fallback when visit_time unavailable)

The skill uses COALESCE(visit_time, first_seen) for accurate time-based queries.

Usage

bash
python3 ~/.claude/skills/browsing-history/browsing_query.py "<query>" [options]

Options

Option	Description	Example
`--device`	Filter by device	`--device iPhone`
`--days`	Number of days back	`--days 7`
`--domain`	Filter by domain	`--domain medium.com`
`--limit`	Max results	`--limit 50`
`--format`	Output format	`--format json`
`--output`	Save to file	`--output history.md`
`--group-by`	Group results	`--group-by domain` or `--group-by category`
`--categorize`	Use LLM to categorize	`--categorize`

Example Queries

Basic queries:

bash
# Yesterday's browsing history
python3 ~/.claude/skills/browsing-history/browsing_query.py "yesterday"

# Articles from iPhone yesterday
python3 ~/.claude/skills/browsing-history/browsing_query.py "yesterday" --device iPhone

# Last week's history grouped by domain
python3 ~/.claude/skills/browsing-history/browsing_query.py "last week" --group-by domain

# Find articles about economics
python3 ~/.claude/skills/browsing-history/browsing_query.py "economics" --days 7

Save to Obsidian:

bash
# Save yesterday's history as markdown
python3 ~/.claude/skills/browsing-history/browsing_query.py "yesterday" \
  --output ~/Research/vault/browsing-2025-11-27.md

# Save with LLM categorization
python3 ~/.claude/skills/browsing-history/browsing_query.py "yesterday" \
  --categorize --group-by category \
  --output ~/Research/vault/browsing-categorized.md

# Save as JSON
python3 ~/.claude/skills/browsing-history/browsing_query.py "last week" \
  --format json --output ~/Research/vault/history.json

Device-specific:

bash
# iPhone tabs
python3 ~/.claude/skills/browsing-history/browsing_query.py "yesterday" --device iPhone

# Desktop history
python3 ~/.claude/skills/browsing-history/browsing_query.py "today" --device desktop

# All mobile devices
python3 ~/.claude/skills/browsing-history/browsing_query.py "yesterday" --device mobile

Search and filter:

bash
# Sites starting with "joy"
python3 ~/.claude/skills/browsing-history/browsing_query.py "joy" --days 7

# Medium.com articles
python3 ~/.claude/skills/browsing-history/browsing_query.py "last month" --domain medium.com

Natural Language Patterns

The script recognizes:

Pattern	Interpretation
`yesterday`	Previous day
`today`	Current day
`last week`	Past 7 days
`last month`	Past 30 days
`last N days`	Past N days

Keywords are searched in URL and title.

Output Formats

Markdown (default)

markdown
# Browsing History: yesterday

*47 unique URLs from 2025-11-27*

## 2025-11-27

- [Article Title](https://example.com/article) - iPhone - 14:32
- [Another Page](https://another.com/page) - desktop - 16:45

Markdown with categories (--categorize --group-by category)

markdown
# Browsing History: yesterday

## News & Current Events
- [Breaking: Something Happened](https://news.com/...) - iPhone

## Technology & Programming
- [How to Build APIs](https://dev.to/...) - desktop

## Research & Learning
- [Academic Paper on AI](https://arxiv.org/...) - Mac

JSON (--format json)

json
{
  "query": "yesterday",
  "date_range": "2025-11-27",
  "total": 47,
  "results": [
    {"url": "...", "title": "...", "device": "iPhone", "time": "14:32", "category": "News"}
  ]
}

Workflow Examples

User: "Show me articles I read yesterday on my phone"

bash
python3 ~/.claude/skills/browsing-history/browsing_query.py "yesterday" --device iPhone

User: "Save my browsing history from last week to Obsidian, grouped by category"

bash
python3 ~/.claude/skills/browsing-history/browsing_query.py "last week" \
  --categorize --group-by category \
  --output ~/Research/vault/browsing-week.md

User: "Help me find that article about economics I read on my computer"

bash
python3 ~/.claude/skills/browsing-history/browsing_query.py "economics" \
  --device desktop --days 7

User: "Sites that start with 'joy' from last week"

bash
python3 ~/.claude/skills/browsing-history/browsing_query.py "joy" --days 7

Notes

URLs are deduplicated per day (same URL on same day = one entry)
visit_time: Actual visit timestamps from Chrome history
- Desktop: 100% coverage (from Chrome SQLite last_visit_time)
- Mobile: 100% coverage (extracted from Chrome Sync LevelDB)
first_seen: Fallback import timestamp (~15min resolution)
LLM categorization uses Claude 3.5 Haiku via llm CLI

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 Browsing History AI skill do?

Why use Browsing History on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/glebis/claude-skills/tree/main/browsing-history. 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 Browsing History?

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 Browsing History?

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

Is the Browsing History AI skill free?

Yes. It is published on GitHub by glebis 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

Newsletter Generation

bytedance

OrganizationPopular

Use this skill when the user requests to generate, create, write, or draft a newsletter, email digest, weekly roundup, industry briefing, or curated content summary. Supports topic-based research,…

Systematic Literature Review

bytedance

OrganizationPopular

Use this skill when the user wants a systematic literature review, survey, or synthesis across multiple academic papers on a topic. Also covers annotated bibliographies and cross-paper comparisons.…

Apify Automation

Automate web scraping and data extraction with Apify -- run Actors, manage datasets, create reusable tasks, and retrieve crawl results through the Composio Apify integration.

Browser Scrape

DEPRECATED in v0.2.0 -- use browser-extract instead; this is a thin shim for backward compatibility, removed in v0.3.0

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Browsing History Skill

When to Use

Database

Timestamps

Usage

Options

Example Queries

Natural Language Patterns

Output Formats

Markdown (default)

Markdown with categories (--categorize --group-by category)

JSON (--format json)

Workflow Examples

Notes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now