This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle.
What I Built
Scope Slip is a small prototype for freelancers who need to turn a vague request into a clear piece of work.
Describe the request, choose a suggested service, edit what is included and what needs confirming, then download the outline. The sample menu covers small jobs such as a one-page website, spreadsheet cleanup and captions.
A freelancer or studio could pay to adapt this to their own services. The demo is free. The services are examples; there are no customers, sales or payments behind it yet.
Demo
Try Scope Slip. The first model download needs an internet connection.
Code
Source and instructions. The app code is MIT-licensed; model, runtime and font licences are kept in the repository.
How I Built It
MiniLM, an open model, compares the meaning of the request with seven sample services. It runs in a browser worker through Transformers.js. The top three matches are suggestions. The outline text comes from the selected service menu, and users can edit it.
Request text stays in the tab. Public model and runtime files download on first use. No paid model endpoint, account or payment is needed.
ChatGPT in Codex substantially produced the implementation, tests and this write-up. Real browser checks covered matching, editing, downloads and small-phone layouts. These are functional checks, not measured accuracy or user research.
Why Does Open Innovation Matter?
The open model makes local matching possible without sending the request to a paid AI service. The open app source lets someone replace the sample menu with their own, inspect the matching and change the outline format. The next useful feedback would come from a real freelancer trying it.
Prize Categories
Best Use of GitHub Copilot — GitHub Actions option. The actual workflow runs tests and lint, builds the app and deploys the public demo. This entry uses the GitHub Actions route listed in that category.
Top comments (0)