# Eb1a Judging

> >

- **Type:** Skill
- **Install:** `agentstack add skill-harshuljain13-agent-skills-eb1a-judging`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [harshuljain13](https://agentstack.voostack.com/s/harshuljain13)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [harshuljain13](https://github.com/harshuljain13)
- **Source:** https://github.com/harshuljain13/agent-skills/tree/main/skills/eb1a-judging

## Install

```sh
agentstack add skill-harshuljain13-agent-skills-eb1a-judging
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# EB1A Judging — Hackathon Outreach Skill

## Context

Harshul is a Senior ML Engineer at Audible (Amazon), ~9 years experience. He judges
hackathons for two reasons: he genuinely enjoys evaluating real engineering work, and
every judging engagement is evidence for **Criterion 4 (Judging)** of his EB1A
extraordinary ability petition.

Every outreach email, confirmation, and post-event letter gets documented.

---

## Task 1: Write the Outreach Email

Harshul's email voice: direct opener with credentials, clear ask, bullet-pointed fit,
warm close. No fluff, no over-selling.

### Template

```
Subject: Volunteer Judge/Mentor — [Hackathon Name]

Hi [Name / "there"],

I'm a Senior ML Engineer at Audible (Amazon) with 9 years building production systems
and 6 years specifically in ML/AI. I'd like to volunteer as a judge and mentor
for [Hackathon Name].

Why I'm a fit:
- Production AI: I build GenAI-powered search and a real-time ML feature store
  (100K+ QPS) at Audible — I evaluate production-readiness, not just demo quality
- Open source: I created AgentShip, an AI agent deployment framework
- Mentorship: 300+ engineers mentored on Codementor/Topmate (4.95/5, 298 sessions)
- What I look for: working systems over polished slides — technical depth, honest
  tradeoffs, and what the team actually learned

Happy to review submissions, do real-time mentorship, or sit on a final panel —
whatever's most useful. Can we find 15 minutes to talk?

Best,
Harshul Jain
[LinkedIn] | [Email]
```

### Customization — always do this:
- **Theme-specific line**: Add 1 sentence connecting his background to the hackathon's focus
  - AI/ML theme → "Your focus on [LLMs / agents / computer vision] maps directly to what I build day-to-day."
  - Social impact → "I'm especially interested in AI applied to [domain] — right in line with your theme."
  - University / student event → "I love working with early-career engineers who are building real things."
- **Named organizer**: Always find the specific person's name if possible
- **Event date**: Include it if known — shows you've done your homework

---

## Task 2: Post-Event — Request Documentation Letter

Send within 2 weeks of the event. This letter is EB1A evidence.

```
Subject: Quick Ask — Confirmation Letter for [Hackathon Name]

Hi [Name],

Thanks again for having me at [Hackathon Name] — I really enjoyed [specific moment
or project that stood out].

I'm compiling documentation for an immigration petition and would appreciate a
brief letter on [Organization] letterhead confirming my role. It only needs:

- My name and role (Judge / Technical Judge)
- Event name, date, format
- Rough scope (number of teams / submissions reviewed)
- Your name, title, org

Happy to send a draft if that's easier. Should take under 10 minutes.

Thank you,
Harshul Jain
[LinkedIn] | [Email]
```

---

## Task 3: Log the Engagement (EB1A Evidence)

After each hackathon, create a log entry immediately. File it wherever Harshul keeps
his EB1A evidence folder.

```
## Judging Log — [Hackathon Name]

Date: [Date]
Organizer: [Org + URL]
Format: In-person / Virtual / Hybrid
Scale: [N] teams, [N] participants
My role: Judge / Technical Judge / Mentor-Judge

How I was selected: [Invited / Applied / Referral]
What I evaluated: [e.g., "Reviewed 10 ML projects, scored on technical execution,
  production-readiness, and novelty"]

Artifacts:
[ ] Invitation/confirmation email
[ ] Organizer confirmation letter (request within 2 weeks)
[ ] Screenshot of event page showing my name
[ ] Judging rubric I used
[ ] Any media or recap mentioning me

EB1A Criterion: 4 — Judging
Strength: High / Medium / Low
```

**What makes it stronger**: prestigious organizer (MLH, top university, AWS), large scale
(100+ participants), evidence you were *selected* not just self-nominated, named in
public event materials.

---

## EB1A Framing (for petition narrative)

> "Petitioner was selected by [Org] to evaluate the work of [N] engineering teams at
> [Hackathon Name], applying expertise in ML and production systems developed over
> 9 years at companies including Amazon. This selection reflects recognition of
> Petitioner's standing in the field by peers and community organizers."

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [harshuljain13](https://github.com/harshuljain13)
- **Source:** [harshuljain13/agent-skills](https://github.com/harshuljain13/agent-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-harshuljain13-agent-skills-eb1a-judging
- Seller: https://agentstack.voostack.com/s/harshuljain13
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.