activitywatch-analysis-skill
🥈SilverAnalyzes ActivityWatch data to calculate focus scores, detect repetitive app switching, and generate actionable insights. Benefits operations teams by identifying productivity patterns and areas for improvement. Integrates with ActivityWatch and Claude Code.
2620Updated 2mo ago
Intermediate30min to implementautomation
Saves ~60 min per use
Quick InstallView Source
git clone https://github.com/BayramAnnakov/activitywatch-analysis-skill.gitWorks with:
Claude
Overview
About This Skill
ActivityWatch Analysis Skill quantifies your productivity and focus by analyzing app usage patterns collected by ActivityWatch. It calculates dual scores—productivity (what you worked on) and focus (attention quality)—and detects 'death loops' of repetitive app switching that fragment attention. The skill includes 80+ preconfigured apps for developers, recognizes AI coding workflows, analyzes browser activity at the site level, and supports custom category weighting via JSON config. All processing runs locally on your machine with no external data sharing.
How to Use
Install ActivityWatch and run the calibration step first (analyze_aw.py --calibrate) to detect uncategorized apps and configure category_config.json. Then run analysis for any date range: analyze_aw.py --from today --report or analyze_aw.py --from week --report. Integrate as a Claude Code skill by copying the directory to ~/.claude/skills/ and use commands like /activitywatch, /activitywatch week, or /activitywatch review.
Use Cases
Identify repetitive app-switching patterns causing attention fragmentation
Track and compare focus scores across days or weeks to spot productivity trends
Separate productive work (IDE, terminals) from distraction (social media, entertainment)
Categorize Telegram chats as work-related or personal to refine productivity scoring
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/BayramAnnakov/activitywatch-analysis-skillRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Analyze my ActivityWatch data from [DATE RANGE] and provide a detailed report. Calculate my focus score, identify any repetitive app switching patterns, and suggest actionable improvements. My primary work involves [TASK TYPES] in the [INDUSTRY] sector.
Example Output
# ActivityWatch Analysis Report ## Focus Score - **Overall Focus Score:** 78/100 - **Peak Focus Period:** 10:00 AM - 12:00 PM (Focus Score: 92) - **Lowest Focus Period:** 2:00 PM - 4:00 PM (Focus Score: 65) ## Repetitive App Switching Patterns - **Most Frequent App Switch:** Slack to Email (18 times) - **Potential Death Loop:** Browser to Notepad (12 times) - **Suggested Improvement:** Use browser bookmarks or a task manager to reduce switching. ## Actionable Insights - **Schedule Deep Work Blocks:** Based on peak focus periods. - **Minimize Distractions:** Consider using focus apps during low focus periods. - **Batch Similar Tasks:** Group email and Slack tasks to reduce switching.
Apply to these tools
Browse all toolsProductiv
Control SaaS spending with visibility and analytics
Claude
AI assistant built for thoughtful, nuanced conversation
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
GPT for work
Automate your spreadsheet tasks with AI power
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan