Skip to content
Back to search

eb2-guidelines

Agent skill that audits an EB-2 NIW dossier like a USCIS adjudicator and tracks RFE risk.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/orenatobr--eb2-guidelines/badge.svg)](/listings/orenatobr--eb2-guidelines)

HTML

<a href="/listings/orenatobr--eb2-guidelines"><img src="/api/listings/orenatobr--eb2-guidelines/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

For Claude Code, copy the skill folders into your personal skills directory:

git clone https://github.com/orenatobr/eb2-guidelines.git
mkdir -p ~/.claude/skills
cp -R eb2-guidelines/skills/* ~/.claude/skills/

Start a new Claude Code session. Skills load from the `description` in each `SKILL.md`, so they trigger on their own and can also be called by name.

Other agents: each skill is a folder with a `SKILL.md` (YAML frontmatter plus Markdown). Tools that read the Agent Skills format can load `skills/` as it is. For the rest, paste the body of the `SKILL.md` into the agent's instruction file.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 41 lines
  1. # eb2-guidelines
  2. Reads every file of an EB-2 NIW (I-140 National Interest Waiver) dossier the way the adjudicating officer would, and keeps an RFE risk report up to date. It applies a checklist (Dhanasar prongs, credibility, recommendation letters, credentials, form, sworn forms, weak evidence, current policy), verifies critical findings at the source and records each finding with a stable ID and a severity. The output is a technical review and does not replace legal advice.
  3. ## Install
  4. For Claude Code, copy the skill folders into your personal skills directory:
  5. ```bash
  6. git clone https://github.com/orenatobr/eb2-guidelines.git
  7. mkdir -p ~/.claude/skills
  8. cp -R eb2-guidelines/skills/* ~/.claude/skills/
  9. ```
  10. Start a new Claude Code session. Skills load from the `description` in each `SKILL.md`, so they trigger on their own and can also be called by name.
  11. Other agents: each skill is a folder with a `SKILL.md` (YAML frontmatter plus Markdown). Tools that read the Agent Skills format can load `skills/` as it is. For the rest, paste the body of the `SKILL.md` into the agent's instruction file.
  12. ## Usage
  13. Run `/eb2-guidelines` from the folder that holds `eb2-niw/`. It also triggers on "RFE", "EB2" and "EB-2 NIW".
  14. ## Requirements
  15. A local dossier folder named `eb2-niw/`. The last step edits an HTML report source and runs a build script, both of which you supply. Optional: markitdown, tesseract and Google Scholar MCP servers.
  16. ## What is in this repo
  17. | Path | Purpose |
  18. |------|---------|
  19. | `skills/eb2-guidelines/` | The `eb2-guidelines` skill. |
  20. | `CHANGELOG.md` | Notable changes, in Keep a Changelog format. |
  21. | `AGENTS.md` | Rules for AI agents that edit this repo. |
  22. ## Contributing
  23. `main` is protected: changes land through a pull request with one approval. See [AGENTS.md](AGENTS.md) for the conventions.
  24. ## License
  25. MIT, see [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.