retro-activity

Correlate Git commit history and AI conversation logs to estimate time spent.

Updated Oct 15, 2021
One-click install
npx skills add https://github.com/toqoz/config --skill retro-activity
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: retro-activity
Source: https://github.com/toqoz/config/tree/main/home/agents/skills/retro-activity
Command: npx skills add https://github.com/toqoz/config --skill retro-activity

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the lack of visibility into personal work patterns, helping you identify time-sinks, context-switching costs, and opportunities for better AI leverage.

Core Features & Use Cases

  • Work Pattern Analysis: Automatically aggregates commit history and AI conversation logs to visualize how you spend your time across different repositories.
  • Efficiency Benchmarking: Compares your actual work time against a calculated normal baseline to highlight where AI is providing the most value.
  • Actionable Improvement: Provides concrete, data-backed suggestions to improve your work rhythm, prioritization, and commit habits for the following week.

Quick Start

Run the retro-activity skill to generate a retrospective report of your work patterns for the current week.

Frequently Asked Questions about retro-activity

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze git commit history to estimate time spent on a project?

You can analyze git commit history to estimate time spent by correlating commit timestamps with AI conversation logs to identify productivity patterns. This process visualizes time distribution across local repositories and calculates work baselines.

Can I generate a weekly retrospective from local repositories managed by ghq?

Yes, you can generate a weekly retrospective from local repositories managed by ghq. The skill aggregates local project metadata, git commits, and AI conversation logs to produce a retrospective report detailing your work rhythm.

What is the best way to identify context-switching costs in my developer workflow?

The best way to identify context-switching costs is by analyzing developer work activity through correlated git commits and AI conversation logs. This highlights time-sinks and visualizes how time is distributed across different repositories.

Does this work pattern analysis require Python 3 to run?

Yes, this work pattern analysis requires Python 3 to run. It uses Python scripts to process local project metadata, git commit history, and AI conversation logs to generate actionable improvement suggestions.

How do AI conversation logs improve work pattern analysis?

AI conversation logs improve work pattern analysis by providing data to benchmark actual work time against a calculated normal baseline. This correlation highlights where AI provides the most value and identifies time-sinks.

What kind of improvement suggestions can I get from a developer time-tracking retrospective?

A developer time-tracking retrospective provides concrete, data-backed suggestions to improve your work rhythm, prioritization, and commit habits for the following week based on aggregated git history and AI conversation efficiency.