Browsing History Skill for Claude
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.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/glebis/claude-skills --skill browsing-historyWhat comes with it
26 066 bytes besides the instructionThe instruction itself
14 sections, as written by the authorBrowsing 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
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:
# 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:
# 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:
# 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:
# 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)
# 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)
# 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)
{
"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"
python3 ~/.claude/skills/browsing-history/browsing_query.py "yesterday" --device iPhone
User: "Save my browsing history from last week to Obsidian, grouped by category"
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"
python3 ~/.claude/skills/browsing-history/browsing_query.py "economics" \
--device desktop --days 7
User: "Sites that start with 'joy' from last week"
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
llmCLI
Other skills for the same job
different authors, same section of the catalogue
Expert in building and selling Notion templates as a business - not just making templates, but building a sustainable digital product business. Covers template design, pricing, marketplaces, marketing, and scaling to real revenue. Use when: notion template, sell templates, digital product, notion business, gumroad.
Vector graphics and diagram creation, format conversion (ODG/SVG/PDF) with LibreOffice Draw.
Use when ready to document findings, generate a report, or summarize binary analysis results. Compiles analysis findings into structured reports - correlates facts from triage/static/dynamic phases, validates hypotheses, generates documentation with evidence chains. Keywords - "summarize findings", "generate report", "document analysis", "what did we find", "write up results", "export findings
> Activate this skill when a student provides study material (PDF or pasted notes) and a syllabus, and wants to prepare for an exam. Extracts key definitions, points, keywords, diagrams, exam-ready sentences, and practice questions strictly from the provided material.
小红书美妆内容创作技能，支持笔记生成、笔记优化、文生图描述创作；适用于美妆护肤产品的内容创作、测评和营销推广
Write a client proposal, quote, scope of work, or engagement letter for a service business. Covers project understanding, scope, timeline, pricing presentation, and terms. Use whenever the user asks for a proposal, quote, project proposal, client proposal, SOW, statement of work, engagement letter, or B2B service engagement document — for web dev, consulting, trades, or any service business.
When the user wants to create, optimize, or structure a documentation site. Also use when the user mentions "docs," "documentation site," "docs subdomain," "docs.yourdomain.com," "help center," "knowledge base," "Getting Started," "API Reference," "user guides," or "tutorials." For API marketing landing, use api-page-generator.
When the user wants to create LinkedIn post copy or optimize for LinkedIn. Also use when the user mentions "LinkedIn post," "LinkedIn article," "professional post," "post to LinkedIn," "LinkedIn content," "LinkedIn copy," "B2B LinkedIn," "LinkedIn engagement," "LinkedIn feed," "share box," "document post," "poll," "Newsletter," "reshare," or "LinkedIn marketing." For LinkedIn ads, use linkedin-ads.
How to use it
Take glebis/browsing-history from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.