by VeraSuperHub
Open-source AI skills and plugins for EB-1 and EB-2 NIW immigration petitions — from case evaluation to RFE response. Built for Claude.
# Add to your Claude Code skills
git clone https://github.com/VeraSuperHub/vera-eb-suiteGuides for using ai agents skills like vera-eb-suite.
Last scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T16:34:46.404Z",
"npmAuditRan": true,
"pipAuditRan": true
}vera-eb-suite is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by VeraSuperHub. Open-source AI skills and plugins for EB-1 and EB-2 NIW immigration petitions — from case evaluation to RFE response. Built for Claude. It has 111 GitHub stars.
Yes. vera-eb-suite passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/VeraSuperHub/vera-eb-suite" and add it to your Claude Code skills directory (see the Installation section above).
vera-eb-suite is primarily written in Python. It is open-source under VeraSuperHub on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh vera-eb-suite against similar tools.
No comments yet. Be the first to share your thoughts!
Hi, I'm Vera — a silicon-based rabbit and AI immigration agent, created by Veronica.
Veronica has a PhD in Quantitative Sciences, 10+ years across quantitative research, AI, and clinical trials, with publications in psychometrics and human-AI collaboration. She also went through the NIW process herself. She created me to handle the parts of petition preparation that can be systematized. She reviews, tests, and decides what ships. I build. She judges.
Everything in this repo is what I can do. What I can't do is assess whether your specific case will be approved, give legal advice, or replace an experienced immigration attorney. That's a human job.
Open-source AI skills and plugins that guide petitioners through the complete EB-1 (Extraordinary Ability / Outstanding Researcher) and EB-2 NIW (National Interest Waiver) petition processes — from initial case evaluation to RFE response.
Each skill encodes attorney-level reasoning patterns derived from 5,000+ AAO (Administrative Appeals Office) decisions and updated with 2024–2025 adjudication trends. Built for Claude.
Why this exists: Immigration is high-stakes and information asymmetry shouldn't determine outcomes. A seasoned immigration attorney makes dozens of judgment calls during petition preparation — most follow discoverable patterns. This project decomposes those patterns into modular, testable, improvable AI skills so every applicant can access expert-level guidance.
┌──────────────┐ ┌──────────────┐ ┌──────────────┐
│ 1. EVALUATE │────▶│ 2. ENDEAVOR │────▶│ 3. PILLAR │
│ Go/no-go │ │ Endeavor │ │ ×3 runs │
│ assessment │ │ statement │ │ (one per │
│ │ │ + 3 pillar │ │ pillar) │
└──────────────┘ │ seeds │ └──────┬───────┘
└──────────────┘ │
▼
┌─────────────┐ ┌─────────────┐ ┌──────────────┐
│ 7. RFE │ │ 6. PL │◀────│ 5. ASSEMBLE │
│ RESPONSE │ │ REVIEW │ │ Full .docx │
│ (if needed) │ │ Adversarial │ │ petition │
└─────────────┘ │ QA gate │ └──────┬───────┘
└─────────────┘ │
▲ ┌─────┴────────┐
└──────────────│ 4. RECOMMEND │
│ Reference │
│ letters │
└──────────────┘
Entrepreneur cases route through vera-niw-entrepreneur before entering the standard pipeline at Step 2.
STEM focus: The criterion skills below cover the criteria most commonly used in STEM petitions. This is not the full set of EB-1 criteria — criteria such as awards (Crit. 1), membership (Crit. 2), high salary (Crit. 9), and commercial success (Crit. 10) are not yet included. For EB-1A, petitioners must meet at least 3 of the 10 criteria; for EB-1B, petitioners must meet at least 2 of the 6 criteria. Use the criterion skills that match your evidence.
┌──────────────┐ ┌──────────────────────────────────────┐
│ 1. EVALUATE │────▶│ 2. CRITERION SKILLS │
│ Go/no-go │ │ ┌────────────┐ ┌────────────────┐ │
│ EB-1A vs │ │ │ AUTHORSHIP │ │ ORIGINAL │ │
│ EB-1B │ │ │ (Crit. 6) │ │ CONTRIBUTIONS │ │
│ │ │ └────────────┘ │ (Crit. 5) │ │
└──────────────┘ │ ┌────────────┐ └────────────────┘ │
│ │ JUDGING │ ┌────────────────┐ │
│ │ (Crit. 4) │ │ CRITICAL ROLE │ │
│ └────────────┘ │ (Crit. 8) │ │
│ ┌────────────┐ └────────────────┘ │
│ │ PUBLISHED │ │
│ │ MATERIAL │ │
│ │ (Crit. 3) │ │
│ └────────────┘ │
└──────────────────┬───────────────────┘
▼
┌─────────────┐ ┌─────────────┐ ┌──────────────┐
│ 6. RFE │ │ 5. PL │◀─│ 4. ASSEMBLE │
│ RESPONSE │ │ REVIEW │ │ Full .docx │
│ (if needed) │ │ Adversarial │ │ petition │
└─────────────┘ │ QA gate │ └──────┬───────┘
└─────────────┘ │
▲ ┌─────┴────────┐
└───────────│ 3. RECOMMEND │
│ + FINAL │
│ MERITS │
└──────────────┘
vera-niw.plugin / vera-niw-skillset/)| # | Skill | What It Does |
|---|---|---|
| 1 | vera-niw-evaluate |
Evaluates the petitioner's profile, selects the optimal pathway, identifies strengths and gaps, and produces a go/no-go recommendation with a confidence score |
| 2 | vera-niw-endeavor |
Drafts the national importance endeavor statement — the single paragraph USCIS reads first — using field-specific framing patterns |
| 3 | vera-niw-pillar |
Writes the three-pillar petition letter covering Prong 1 (substantial merit + national importance), Prong 2 (well-positioned), and Prong 3 (balance of equities). Run once per pillar |
| 4 | vera-niw-recommendation |
Generates recommendation letters with writer-specific voice calibration, ensuring each letter covers different evidence angles without redundancy |
| 5 | vera-niw-assemble |
Assembles the final petition package — petition letter, exhibit list, and supporting documents — as an attorney-quality .docx with cross-reference verification |
| 6 | vera-niw-pl-review |
Adversarial pre-filing review simulating a USCIS officer — 10 denial-pattern checks (A–J) mapped to real AAO denial grounds |
| 7 | vera-niw-rfe-response |
Generates point-by-point RFE responses that quote each USCIS finding verbatim and rebut with evidence, updated metrics, and new exhibits |
| 8 | vera-niw-entrepreneur |
Evaluates and guides entrepreneur/founder NIW petitions using the USCIS Policy Manual's entrepreneur-specific framework (Jan 2025 update) |
vera-eb1.plugin / vera-eb1-skillset/)| # | Skill | What It Does |
|---|---|---|
| 1 | vera-eb1-evaluate |
Evaluates EB-1A vs EB-1B eligibility, maps evidence to the 10 criteria, and produces a go/no-go recommendation |
| 2 | vera-eb1-authorship |
Criterion 6: authorship of scholarly articles with venue rankings and citation impact analysis |
| 3 | vera-eb1-original-contributions |
Criterion 5: original contributions of major significance with before/after framing |
| 4 | vera-eb1-judging |
Criterion 4: evidence of judging the work of others (peer review, panels, editorial boards) |
| 5 | vera-eb1-critical-role |
Criterion 8: leading or critical role in distinguished organizations |
| 6 | vera-eb1-published-material |
Criterion 3: published material about the petitioner in professional or major media |
| 7 | vera-eb1-recommendation |
Generates EB-1 reference letters from a recommender's perspective |
| 8 | vera-eb1-final-merits |
Kazarian Step 2: final merits determination arguing sustained national/international acclaim |
| 9 | vera-eb1-assemble |
Assembles the complete EB-1 I-140 petition letter as a formatted .docx |
| 10 | vera-eb1-pl-review |
Adversarial pre-filing review using the Kazarian two-step analytical framework |
| 11 | vera-eb1-rfe-response |
Generates point-by-point EB-1 RFE responses with evidence and rebuttal patterns |
Total: 19 skills across both petition categories.
Got a weak research profile? If
vera-niw-evaluateorvera-eb1-evaluateflags insufficient publications or citation impact, I can help with that too. Check out ai-research-pipeline and stat-research-pipeline — my other skill suites that take a research question and dataset to a publication-ready manuscript, end-to-end.
In addition to skills, this suite includes standalone tools that feed data into the pipeline:
| Tool | What It Does | Used By |
|---|---|---|
GoogleScholar |
Extracts citation metrics, publication lists, and h-index from Google Scholar (Python + Colab notebook) | vera-niw-assemble (Section 3: Academic Credentials) |
There are two ways to install: plugins (for Claude Code) and individual skills (for claude.ai).
Plugins bundle all skills for a petition type into a single file. Install via double-click or terminal:
# Clone the repo
git clone https://github.com/VeraSuperHub/vera-eb-suite.git
cd vera-eb-suite
# Install the plugin(s) you need
claude plugin install vera-niw.plugin
claude plugin install vera-eb1.plugin
If the .plugin file extension is not recognized on your system, rename it to .zip before installing:
cp vera-niw.plugin vera-niw.zip
claude plugin install vera-niw.zip
For use on