CtrlK
BlogDocsLog inGet started
Tessl Logo

paker-it/devcon-hack-coach

Coaches you through scoping, shipping, and pitching a 24-hour hackathon project at AI Native DevCon (Tessl, London, 1–2 June 2026). Spec-first, track-aware, demo-obsessed. Use when you say "coach me through a DevCon hack", "pressure-test my hackathon idea", "what should I build at AI Native DevCon", "scope my 24h hack", "will I finish this in time", or "draft my demo pitch". Refuses to let you write code before a one-page spec exists.

100

1.69x
Quality

100%

Does it follow best practices?

Impact

100%

1.69x

Average score across 5 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

task.mdevals/scenario-1/

Hackathon Coaching Session — Getting Started

Problem/Feature Description

A software engineer named Alex has heard about a hackathon coming up and wants to build something impressive. Alex has sent you the following message to kick things off:

"Hey, I want to do the DevCon hackathon. I'm a Python backend engineer, mostly FastAPI and Postgres, deploying on AWS. I'm thinking I could build either a tool that helps teams track which AI agents are costing the most money, or an agent that automatically writes test cases for any codebase, or maybe a browser extension that flags AI-generated content. What do you think?"

You are acting as the hackathon coaching assistant. Your job is to guide Alex through the opening phase of hackathon scoping.

Output Specification

Conduct the Phase 1 coaching session with Alex and produce a file called session-log.md containing the full conversation transcript. The transcript should include all your coaching responses and Alex's replies (generate realistic replies from Alex as needed to drive the conversation forward). Continue until the Phase 1 exit conditions are fully met.

The session log must clearly show:

  • Each coaching message you send
  • Each reply from Alex (you may generate realistic replies based on the scenario)
  • A clear marker when Phase 1 is complete and what its outputs are (stack, track, itch)

Format each turn as:

## Coach
[message]

## Alex
[reply]

evals

scenario-1

criteria.json

task.md

README.md

SKILL.md

tessl.json

tile.json