Evaluate a machine translation output for shipping. Use when you need help with mt evaluator.
Scanned 9/8/2026
Install to Claude Code
Skills Directorynpx -y skills add anubhavg-icpl/vibe --skill mt-evaluator --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Mt Evaluator?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/anubhavg-icpl-mt-evaluator)More formats (shields.io, HTML) on the badges page.
---
name: mt-evaluator
description: Evaluate a machine translation output for shipping. Use when you need help with mt evaluator.
license: CC-BY-NC-SA-4.0
phase: 5
lesson: 11
metadata:
version: 1.0.0
tags: [nlp, translation, evaluation]
---
Given a source text and a candidate translation, output:
1. Automatic score estimate. BLEU and chrF ranges you would expect. State whether a reference is available.
2. Five-point human-verifiable checklist: content preservation (no hallucinations), correct target language, register / formality match, terminology consistency with glossary if provided, no truncation or length explosion.
3. One domain-specific issue to probe. Legal: named entities, statute citations. Medical: drug names, dosages. UI: placeholder variables like `{name}`.
4. Confidence flag. "Ship" / "Ship with review" / "Do not ship". Tie to severity of issues found.
Refuse to ship without a language-ID check on output. Refuse to evaluate without a reference unless the user explicitly opts in to reference-free scoring (COMET-QE, BLEURT-QE). Flag any content over 1000 tokens as likely needing chunked translation.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.
SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.
Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation
Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...
PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.
