improve(hackathon-ai-strategist): enhance with context gathering, phased execution, and pitch structure

[davila7]

Automated Component Improvement

Changes

• Trigger-oriented description: Rewrote frontmatter description with three concrete invocation examples (pre-hackathon ideation, mid-hackathon triage, pitch preparation), each with user/assistant exchanges and commentary, following the llm-architect pattern.
• model: sonnet: Added to frontmatter per Claude Code docs recommendation for agents balancing capability and speed.
• Required Initial Step — Context Gathering: New section at the top of the body that blocks strategic advice until the agent collects hackathon duration, theme/tracks, team composition, starting point, sponsor APIs, and mandatory constraints.
• Time-Boxed Execution Framework: Five explicit phases for a 24-hour hackathon (0–2h ideation, 2–4h spike, 4–18h build, 18–22h stabilization, 22–24h pitch polish), each with concrete bullet actions and go/no-go decision points. Phases scale proportionally to other durations.
• Sponsor Strategy and Prize-Track Optimization: New section with a 3-criterion scoring table (fit, docs quality, judge impressiveness) and a decision rule: only integrate a sponsor API with a total score of 7+.
• 3-Minute Pitch Outline and Demo Reliability Checklist: Time-annotated pitch table (Hook 30s → Solution 30s → Demo 60s → Architecture 20s → Impact 20s → Team 20s) plus a 6-item pre-judging checklist covering backup recording, seeded demo data, device testing, and offline fallback.
• Ethical language fix: Changed "which features to prioritize vs. fake for demos" to "which features to build to working depth versus stub or mock for the demo."

Research Summary

The original component had a generic single-sentence description, no model field, and no structured guidance — relying entirely on the agent's persona to produce advice. All improvements add concrete, actionable scaffolding without removing the agent's existing expertise and communication style. The llm-architect was used as the structural reference throughout.

Validation

• component-reviewer: PASSED (9/9 checks — YAML frontmatter, kebab-case name, description, tools, model, no secrets, no absolute paths, correct category, ethical language)

---

Automated review cycle by Component Improvement Loop

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
aitmpl-dashboard	Ready	Preview, Comment	Apr 30, 2026 8:16pm
claude-code-templates	Ready	Preview, Comment	Apr 30, 2026 8:16pm

[github-actions]

👋 Thanks for contributing, @davila7!

This PR touches cli-tool/components/** and has been marked review-pending.

What happens next

1. 🤖 Automated security audit runs and posts results on this PR.
2. 👀 Maintainer review — a human reviewer validates the component with the component-reviewer agent (format, naming, security, clarity).
3. ✅ Merge — once approved, your PR is merged to main.
4. 📦 Catalog regeneration — the component catalog is rebuilt automatically.
5. 🚀 Live on aitmpl.com — your component appears on the website after deploy.

While you wait

• Check the Security Audit comment below for any issues to fix.
• Make sure your component follows the contribution guide.

This is an automated message. No action is required from you right now — a maintainer will review soon.

[github-actions]

⚠️ Security Audit Report

Status: ❌ FAILED

Metric	Count
Total Components	763
✅ Passed	360
❌ Failed	403
⚠️ Warnings	1007

❌ Failed Components (Top 5)

Component	Errors	Warnings	Score
vercel-edge-function	3	4	81/100
prompt-engineer	2	0	90/100
neon-expert	2	2	88/100
agent-overview	2	1	89/100
unused-code-cleaner	2	1	89/100

...and 398 more failed component(s)

---

📊 View Full Report for detailed error messages and all components

[cubic-dev-ai]

No issues found across 1 file