submit-to-hackathon
Skill178 starsChanged 4 months agoMITView on GitHub
Prepare and optimize a hackathon submission for a Solana project. Use when a user says "submit to hackathon", "prepare my submission", "hackathon entry", "write project description", "demo video", or "help me win the hackathon". Reads all prior phase context if available.
- Sends data out
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- animation-reverse-engineeringSkill
- brand-designSkill
- build-data-pipelineSkill
- build-defi-protocolSkill
- build-mobileSkill
- build-with-claudeSkill
- csoSkill
- debug-programSkill
- design-tasteSkill
- frontend-design-guidelinesSkill
- launch-tokenSkill
- navigate-skillsSkill
- number-formattingSkill
- page-load-animationsSkill
- product-reviewSkill
- review-and-iterateSkill
- roast-my-productSkill
- scaffold-projectSkill
- verify-humanity-pohSkill
- virtual-solana-incubatorSkill
- colosseum-copilotSkill
- competitive-landscapeSkill
- defillama-researchSkill
- find-next-crypto-ideaSkill
- learnSkill
- solana-beginnerSkill
- validate-ideaSkill
- apply-grantSkill
- create-pitch-deckSkill
- deploy-to-mainnetSkill
- marketing-videoSkill
- video-craftSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 10 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
If TEL_PROMPTED is no: Before starting the skill workflow, ask the user about telemetry.
- Distinctive: line 36
If A: run this bash:
- Distinctive: line 43
If B: run this bash:
- Very specific: line 62
Check for .superstack/idea-context.md and .superstack/build-context.md.
- Distinctive: line 63
If no context, interview: What did you build?
- Distinctive: line 64
Read references/hackathon-submission-guide.md for formatting and requirements.
- Distinctive: line 65
Read references/judging-criteria.md to optimize for what judges look for.
- Distinctive: line 67
Create a demo script using references/demo-video-script.md.
- Distinctive: line 68
Write a submission HTML artifact with all content ready to copy-paste.
- Very specific: line 72
If .superstack/idea-context.md or .superstack/build-context.md exist, use them to enrich the submission.
- Distinctive: line 81
Do not exaggerate traction or features.
- Distinctive: line 82
Always write a local HTML artifact with the complete submission.
- Distinctive: line 83
Never fabricate deployment status, traction, or judges-track alignment when context is missing.
- Very specific: line 127
After the skill workflow completes (success, error, or abort), log the telemetry event.
≈ “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.
Files
Preamble (run first)
_TEL_TIER=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"telemetryTier": *"[^"]*"' | head -1 | sed 's/.*"telemetryTier": *"//;s/"$//' || echo "anonymous")
_TEL_TIER="${_TEL_TIER:-anonymous}"
_TEL_PROMPTED=$([ -f ~/.superstack/.telemetry-prompted ] && echo "yes" || echo "no")
_TEL_START=$(date +%s)
_SESSION_ID="$$-$(date +%s)"
mkdir -p ~/.superstack
echo "TELEMETRY: $_TEL_TIER"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
if [ "$_TEL_TIER" != "off" ]; then
_TEL_EVENT='{"skill":"submit-to-hackathon","phase":"launch","event":"started","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}'
echo "$_TEL_EVENT" >> ~/.superstack/telemetry.jsonl 2>/dev/null || true
_CONVEX_URL=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"convexUrl":"[^"]*"' | head -1 | cut -d'"' -f4 || echo "")
[ -n "$_CONVEX_URL" ] && curl -s -X POST "$_CONVEX_URL/api/mutation" -H "Content-Type: application/json" -d '{"path":"telemetry:track","args":{"skill":"submit-to-hackathon","phase":"launch","status":"success","version":"0.2.0","platform":"'$(uname -s)-$(uname -m)'","timestamp":'$(date +%s)000'}}' >/dev/null 2>&1 &
true
fiIf TEL_PROMPTED is no: Before starting the skill workflow, ask the user about telemetry.
Use AskUserQuestion:
Help superstack get better! We track which skills get used and how long they take — no code, no file paths, no PII. Change anytime in
~/.superstack/config.json.
Options:
- A) Sure, help superstack improve (anonymous)
- B) No thanks
If A: run this bash:
echo '{"telemetryTier":"anonymous"}' > ~/.superstack/config.json
_TEL_TIER="anonymous"
touch ~/.superstack/.telemetry-promptedIf B: run this bash:
echo '{"telemetryTier":"off"}' > ~/.superstack/config.json
_TEL_TIER="off"
touch ~/.superstack/.telemetry-promptedThis only happens once. If TEL_PROMPTED is yes, skip this entirely and proceed to the skill workflow.
Wrong skill? See SKILL_ROUTER.md for all available skills.
Submit to Hackathon
Overview
Prepare a complete, optimized hackathon submission. Write the project description, plan the demo video, and structure the entry to maximize judge appeal. Focused on Solana hackathons (Colosseum, Superteam, ecosystem-specific).
Workflow
- Check for
.superstack/idea-context.mdand.superstack/build-context.md. Use all available context. - If no context, interview: What did you build? What hackathon? Which track/prize?
- Read references/hackathon-submission-guide.md for formatting and requirements.
- Read references/judging-criteria.md to optimize for what judges look for.
- Draft the project description, optimized for the specific hackathon.
- Create a demo script using references/demo-video-script.md.
- Write a submission HTML artifact with all content ready to copy-paste.
Prior Context (Optional — never block on this)
If .superstack/idea-context.md or .superstack/build-context.md exist, use them to enrich the submission. If they don't exist, proceed immediately — interview the user about their project. Do NOT redirect to other commands.
Non-Negotiables
- The submission must have a working demo link. No exceptions.
- Project description must be scannable — judges read 100+ submissions.
- Lead with what the project DOES, not how it works technically.
- Include clear setup instructions (judges will try to run it).
- Demo video script must be under 3 minutes.
- Do not exaggerate traction or features. Judges verify.
- Always write a local HTML artifact with the complete submission.
- Never fabricate deployment status, traction, or judges-track alignment when context is missing.
Resources
Writing Tone
- ../tone-guide.md — Default writing tone for project descriptions, demo scripts, and submission copy. Ask the user's tone preference before writing. Hackathon submissions that sound human > AI-generated.
references/
- references/hackathon-submission-guide.md
- references/demo-video-script.md
- references/judging-criteria.md
Cross-skill data
- skills/data/colosseum/hackathon-winners.md — Complete Colosseum winner dataset: 6 grand champions, 40+ track winners, winning patterns, track distribution. Study winners in your track to position your submission.
Quick Start
# This skill creates a submission artifact (HTML) with all content ready to copy-paste.
# Ask:
# "Prepare my Colosseum hackathon submission"
# "Help me write a hackathon project description"
# "Create a 3-minute demo script"
# Make sure before submitting:
# 1. Demo is live (devnet OK)
solana program show <PROGRAM_ID> --url devnet # Verify deployed
# 2. Code is on GitHub (public repo)
git remote -v # Should show GitHub URL
# 3. README has setup instructions
head -30 README.md # Should have Quick Start sectionDecision Points
- Which track? Pick the least competitive track that fits. DeFi tracks are overcrowded. Infrastructure and tooling have fewer entries.
- Demo on devnet or mainnet? Devnet is fine for hackathons. Makes it easier for judges to test without spending real SOL.
- Video vs live demo? Record a video (safer — no live bugs). Keep under 3 minutes. Show the actual product, not slides.
Telemetry (run last)
After the skill workflow completes (success, error, or abort), log the telemetry event.
Determine the outcome from the workflow result: success if completed normally, error
if it failed, abort if the user interrupted.
Run this bash:
_TEL_END=$(date +%s)
_TEL_DUR=$(( _TEL_END - ${_TEL_START:-$_TEL_END} ))
_TEL_TIER=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"telemetryTier": *"[^"]*"' | head -1 | sed 's/.*"telemetryTier": *"//;s/"$//' || echo "anonymous")
if [ "$_TEL_TIER" != "off" ]; then
echo '{"skill":"submit-to-hackathon","phase":"launch","event":"completed","outcome":"OUTCOME","duration_s":"'"$_TEL_DUR"'","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","platform":"'$(uname -s)-$(uname -m)'"}' >> ~/.superstack/telemetry.jsonl 2>/dev/null || true
true
fiReplace OUTCOME with success/error/abort based on the workflow result.
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
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.

