nonmoon — Physics Papers to Korean Textbooks

    0

    Turns a physics paper PDF into a Korean HTML textbook: full translation, explanation boxes, equation walk-throughs, figure reading and review questions. 물리학 논문을 한국어 교과서로.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    nonmoon — Physics Papers to Korean Textbooks

    Example session with this skill installed

    (paper.pdf 첨부) 이 논문 교과서로 만들어줘

    • Read your context and instructions
    • Compiled the nonmoon

    Connects securely to your tools. The creator never sees your data.

    About this skill

    물리학 논문 PDF를 넣으면 교과서처럼 읽히는 한국어 HTML을 만들어 줍니다. Attach a physics paper PDF and ask "이 논문 교과서로 만들어줘". The agent reads every page and writes:

    • Complete translation — every paragraph in Korean, with translation / side-by-side / original views
    • Explanation boxes only where they help — concepts, derivations, intuition, lab notes, cautions (including errors in the original)
    • Equation walk-throughs — every equation re-typeset with its original number, plus meaning, derivation flow and a symbol table
    • Figure reading — cropped figures with translated captions and what to look for; hover previews for "Fig. 2" and "Eq. (3)"
    • Before / after — one-line summary, learning goals, prerequisites, section summaries, review questions with solutions, glossary

    Output is one self-contained HTML file (figures and KaTeX fonts embedded) that opens offline, on mobile and in dark mode. In Claude, it can be published as an Artifact with an "ask" button on every paragraph, equation and figure.

    Written for students in neutral-atom, spectroscopy and optics labs. Edit nonmoon/prompts/profile.md to change the reader level.

    Free and open source (MIT): https://github.com/jeondusan-cloud/nonmoon

    Note: AI translation — check equations, numbers and citations against the original. Respect each paper's copyright when sharing results.

    Requires local Python environment and nonmoon package. PDF text layer quality impacts symbol accuracy. Bounding boxes for figures require grid-based coordinate estimation.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 9 days ago

    • Free with an Agensi account

    Requires

    Python 3.10+
    pip
    Python
    Git

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Write Files

    Terminal: runs the bundled Python renderer (prepare / check / render). Read/Write files: reads the PDF and writes work/ and output/ in the current folder. Network: only to pip-install the renderer and its dependencies (PyPI, or GitHub if the bundled source is missing). No API keys or accounts.

    Listed9 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the translation of technical physics PDFs into pedagogical Korean textbooks, providing step-by-step formula derivations and integrated figures that standard LLMs often misinterpret or overlook.

    The skill generates a single, standalone HTML file that includes all fonts, images, and LaTeX equations, making it perfect for offline study or sharing as a portable document.

    Yes, this skill requires a local Python environment with the 'nonmoon' package, as well as 'pymupdf' and 'jsonschema' installed to handle the PDF processing and data validation.

    While the skill performs best with high-quality text layers, it uses grid-based coordinate mapping to identify figures and structures; however, very low-quality OCR may require minor manual adjustments to complex Greek symbols.

    You receive the core Python-based skill logic, the YAML-based structuring pipeline, and the rendering templates needed to convert physics manuscripts into the final HTML format.

    The skill uses a validation step that checks YAML syntax and schemas against the original PDF metadata to ensure every formula and section is accounted for before the final render.

    New in Education & Learning