HackStack

Project Info

Trekly

Devpost

This project did not submit a demo video on Devpost.

Inspiration

We’ve all had ideas we were excited about—starting a blog, building an app, launching a startup—but most of them never make it past the first day. The problem isn’t a lack of motivation; it’s a lack of direction. When faced with too many resources and no clear path forward, people procrastinate or give up entirely. We wanted to solved that.

What it does

Trekly is a personal AI project planner that transforms vague ideas into structured, step-by-step roadmaps tailored to your goals, timeline, skill level, and learning preferences. It generates a week-by-week plan filled with actionable steps, interactive activities, and curated resources. Each action plan is designed not just to teach a skill, but to help you build confidence, develop momentum, and reflect on your growth. Trekly is about more than just finishing a project—it’s about accomplishing something you never thought you could. Every step is designed to move you closer to a better, more capable version of yourself. By showing up consistently, learning actively, and pushing through uncertainty, Trekly helps you build not just skills, but belief in your own potential.

How we built it

Used React frontend and JavaScript to create a smooth, responsive onboarding and roadmap experience. Project details questionnaire inputs are processed through Google Gemini and refined with a carefully engineered prompt, which generates a structured, JSON-based roadmap. Chatbot interface powered by the Claude API (Anthropic), which understands the user's current progress and context to provide live feedback, encouragement, and step-by-step support.

What we learned

Clear, structured instructions can dramatically improve the quality and reliability of LLM-generated outputs. We also realized how important it is to deeply consider the user’s motivation and what they hope to accomplish when using the app. Building Trekly taught us how to balance structure with flexibility, giving users enough guidance without restricting creativity.

What's next

Next, we want to let users save and share their roadmaps, track progress step-by-step, and attach links, images, or code as they build. We’re also exploring more domain-specific templates, like “launching a portfolio,” “learning full-stack development,” or “preparing for technical interviews.” Our goal is to turn Trekly into a personal project coach—one that not only helps you get started, but keeps you going, celebrates your progress, and grows with you.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • AnthropicIn code
  • CSSIn code
  • HTMLIn code
  • JavaScriptIn code
  • ReactIn code
  • Tailwind CSSIn code
  • Google GeminiClaimed

6 of 7 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

78 KB

Source files

13

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars