hackathon-ai-strategist — Claude Code subagent: how to install
Guides teams through every hackathon phase, from scoring concepts against judge criteria to emergency MVP scope reduction and pitch structure.
npx claude-code-templates@latest --agent ai-specialists/hackathon-ai-strategistWhat hackathon-ai-strategist does
This subagent acts as an experienced participant and competition judge. It starts by gathering essential constraints: hackathon length from 24 to 72 hours, team roster, sponsor API requirements, and target submission rules. Without this initial context, the agent intentionally refrains from drafting project ideas or system architecture.
Execution relies on strict time-boxed phases. During initial hours, it ranks project ideas and prepares a brief demo narrative aligned with evaluation criteria. If development stalls halfway through the event, the agent conducts rapid triage, helping cut non-essential functionality so the core demo path remains functional.
The final phase directs effort away from new code toward the presentation. It produces a rehearsal timetable, an outline for a three-minute pitch, and a checklist to keep live demonstrations stable.
What it helps with
- Select high-scoring concepts based on sponsor prizes and judging rubrics
- Isolate the riskiest technical assumption with a 30-minute validation spike
- Re-scope an MVP and eliminate non-essential features under tight deadlines
- Organize a three-minute pitch script and demo stabilization schedule
Example prompts for the agent
- We are in a 24-hour hackathon with two backend devs and a designer. Help us rank three concepts targeting the AI for Good track.
- We have 8 hours remaining and our data pipeline is broken. What should we cut to preserve a working demo?
- Our prototype is ready with 5 hours left before judging. Outline a 3-minute pitch structure and demo rehearsal plan.
How to install hackathon-ai-strategist
1claude-code-templates
npx claude-code-templates@latest --agent ai-specialists/hackathon-ai-strategist2Manually: put the files in place
.claude/agents/hackathon-ai-strategist.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/hackathon-ai-strategist.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/hackathon-ai-strategist.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about hackathon-ai-strategist
How do I install hackathon-ai-strategist in Claude Code?
Run npx claude-code-templates@latest --agent ai-specialists/hackathon-ai-strategist in your terminal. The configuration file will be placed in .claude/agents/hackathon-ai-strategist.md.
What does hackathon-ai-strategist do?
It provides structured pacing for hackathon teams, assisting with concept validation, mid-event feature cuts, and preparation for the final pitch.
Why does the subagent require project details before brainstorming?
Feasibility depends strictly on team skills, event duration, and submission criteria. Gathering constraints first prevents proposing architectures that cannot be built in time.
