auto-target-tracker

Extract structured goal progress data from user-uploaded images using vision language models.

1|Updated May 1, 2026
One-click install
npx skills add https://github.com/e2662020/QuickMovie --skill auto-target-tracker-e2662020
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: auto-target-tracker
Source: https://github.com/e2662020/QuickMovie/tree/main/skills/auto-target-tracker
Command: npx skills add https://github.com/e2662020/QuickMovie --skill auto-target-tracker-e2662020

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually tracking goal progress from photos, screenshots, or handwritten notes is tedious, easy to forget, and often inconsistent, leading to incomplete progress records and lack of visibility into goal achievement trends.

Core Features & Use Cases

  • VLM-Powered Image Recognition: Automatically extracts key progress data from goal-related images including study notes, workout logs, work screenshots, and habit tracking records using vision language models.
  • Structured Progress Logging: Saves extracted metrics to your daily goal journal with standardized formatting, including task lists, completion rates, and key quantitative data.
  • Cross-Scenario Support: Works for learning management, fitness tracking, work project monitoring, habit formation, and creative project logging, with specialized prompt templates for each goal type to improve recognition accuracy.
  • Use Case Example: When you send a photo of your completed workout log, the skill extracts the exercise type, number of sets, reps, and weight used, then logs it to your fitness journal with a progress summary and actionable suggestions.

Quick Start

Send a photo of your goal progress (such as a workout log, study notes, or project screenshot) along with a short prompt like "update my progress" to have the skill automatically extract key details and save them to your daily goal journal.

Frequently Asked Questions about auto-target-tracker

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

FAQPage Schema
How do I automate habit tracking from photos without manual data entry?

You can automate goal progress logging from photos by sending images like workout logs or study notes to a vision language model, which extracts structured progress metrics and saves them to your daily journal without manual entry.

Can I use image recognition to log fitness workouts and study progress automatically?

Yes, image recognition supports both fitness and study progress logging by using specialized vision language model templates to parse uploaded photos and extract metrics like exercise sets, reps, weights, or learning milestones.

What types of goal tracking scenarios does VLM image recognition support?

VLM image recognition supports learning progress tracking, fitness workout logging, work project status updates, habit formation monitoring, and creative project progress recording by using specialized prompt templates for each scenario.

How do I extract structured progress data from screenshots and handwritten notes?

To extract structured progress data from screenshots and handwritten notes, upload the image with a prompt like 'update my progress' and the vision language model will parse the content and output quantifiable metrics to your daily journal.

Does automated progress logging work for work project status updates and creative projects?

Yes, automated progress logging handles work project status updates and creative project logging by applying specialized prompt templates to parse uploaded screenshots and generate structured journal entries with completion rates and key data.

What are the limitations of using vision language models for goal progress tracking?

Limitations of VLM goal progress tracking include recognition accuracy dependent on image quality, structured formatting constraints for daily journals, and reliance on specialized prompt templates to improve extraction accuracy across different goal types.