bocodes1bocodes1/claude-skills/hackathon-copilot/SKILL.md

hackathon-copilot

Skill0 starsChanged 7 months agoMITView on GitHub

End-to-end hackathon execution - idea selection, judging-criteria optimization, scope control, rapid build planning, live troubleshooting, and demo/pitch prep. Use when preparing for or actively participating in a hackathon

In this repository13 other files it gives its agents.
- deploy-pipelineSkill
- ecommerce-builderSkill
- know-meSkill
- memory-managementSkill
- obsidian-memory-syncSkill
- polymarket-multi-agentSkill
- polymarket-vps-opsSkill
- researcherSkill
- self-healingSkill
- self-improvementSkill
- strategy-preflightSkill
- trade-journalSkill
- visual-promptingSkill

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Prefer one unforgettable feature over five average ones
line 22
Distinctive:
Keep an offline/screenshot fallback in case demo environment fails
line 24
Distinctive:
MVP checklist: must-have vs nice-to-have
line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Hackathon Copilot

Win-focused workflow: pick a judge-friendly idea, build only what scores, ship a polished demo story under time pressure.

Quick Workflow

Define constraints (5 min): theme, hard requirements, team size, deadline, allowed stack
Score ideas against judging criteria — highest score wins, 5-minute time-box
Lock MVP slice that can be demoed in under 2 minutes
Split roles and deliverables across team
Build in sprints (90-minute cycles) with regular risk checks
Prep pitch 3-4 hours before submission: demo script, fallback plan, Q&A bank

Execution Rules

Optimize for judged outcomes, not technical purity
Prefer one unforgettable feature over five average ones
Freeze scope early; only add features that improve judged criteria
Keep an offline/screenshot fallback in case demo environment fails
Maintain a visible "done list" and "risk list" throughout

Deliverables to Produce

One-line thesis: user + pain + magic + why now
3-bullet judging mapping: innovation, technical depth, impact/UX
MVP checklist: must-have vs nice-to-have
Demo flow script: 90-120 seconds
Q&A bank: likely judge questions with crisp answers

If Time Is Collapsing

Cut integrations first, keep core user loop intact
Replace flaky live APIs with cached/sample data
Record a 45-second backup demo video
Shift one teammate fully to polish (UX text, visual consistency, onboarding)

Quick Decision Framework

Should we add this feature?
+-- Does it improve a judging criterion? -> YES: add if time allows
+-- Is it visible in the demo? -> NO: skip entirely
+-- Can we fake it for demo? -> YES: fake it, note as future work
+-- Will it break existing work? -> YES: absolutely not

Common Failure Modes

Problem	Fix
Idea deadlock (team can't agree)	Score against criteria. Highest wins. 5-min time-box.
Demo breaks during presentation	Switch to backup video immediately. Never debug live.
API/service goes down mid-build	Swap to mock data + hardcoded responses. Demo the UX, not the integration.
Scope creep ("just one more feature")	Does it improve a judging criterion? No -> cut it.
Team member stuck >30 min	Pair up, simplify task, or reassign to polish.
Running out of time	3h before deadline: freeze features, all hands on demo + polish.
Judge asks about scalability	"We designed for demo-ready with clear path to scale" + show architecture diagram.
No clear differentiator	Reframe around the user story, not the tech.

Integration Points

researcher: Quick market validation for idea selection
visual-prompting: Fast mockups and visual assets for demo polish

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free