- Home
- Skills
- Technical Documentation
- lecture notes
lecture notes
Converts PPT/PDF slides into high-fidelity lecture notes with LaTeX formulas and side-by-side slide comparisons.
Free
Works with the AI Agents you already use
lecture notes
Example session with this skill installed
Convert my 20-page Corporate Finance PPTX on Stock Valuation into a detailed lecture note PDF with LaTeX formulas and side-by-side slide views.
- Read your context and instructions
- Compiled the lecture notes
I have processed the courseware "Stock Valuation" and generated the full derivation-focused lecture notes.
Lecture Notes Generation Summary
| Step | Action | Status | Result |
|---|---|---|---|
| 1 | Slide Extraction | Completed | 20 images generated (150 DPI) |
| 2 | Script Generation | Completed | gen_stock_valuation_pdf.py created |
| 3 | PDF Construction | Completed | 28-page PDF produced |
| 4 | Font Flattening | Completed | 0 remaining fonts (Vectorized) |
Deliverable: Detailed Lecture Notes Structure
import sys
sys.path.insert(0, "./scripts")
import noteskit as nk
# Content initialized for Corporate Finance - Lecture 3
parts = [
nk.cover("Corporate Finance", "Lecture 3: Stock Valuation", "Peking University", "Detailed Study Guide"),
nk.toc([("Part I: Valuation Theory", ["Dividend Discount Model", "Gordon Growth"])])
]
# Example of page 7 derivation
parts.append(nk.slide(7, "Dividend Discount Model"))
parts.append(nk.p("The fundamental value of a stock is the present value of all future dividends."))
parts.append(nk.deriv("Derivation: Gordon Growth Model", [
("Step 1", "Starting from the DDM formula: " + nk.imath(r"$P_0=\sum \frac{Div_t}{(1+r_E)^t}$")),
("Step 2", "Assuming constant growth $g$ where $r_E > g$"),
nk.dline(r"$P_0=\frac{Div_1}{r_E-g}$")
]))
parts.append(nk.formula_boxed(r"$P_0=\frac{Div_1}{r_E-g}$", "Core Conclusion"))
nk.build(parts, "Stock_Valuation_Notes.html", "Stock_Valuation_Notes.pdf")
Next steps
- Review
Stock_Valuation_Notes.pdffor formula clarity. - Check the highlighted "疑似笔误" (Suspected Errors) tags where slide data was inconsistent.
- Deploy the HTML version if interactive viewing is needed in a browser.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual note-taking from complex lecture slides often leads to missing derivations, low-quality screenshots, and broken formulas. This skill automates the transformation of PPT, PPTX, or PDF courseware into high-fidelity, structured lecture notes in HTML and PDF formats. It prioritizes technical accuracy by embedding original slide images alongside detailed LaTeX-rendered explanations and step-by-step derivations.
What it does
- Slide synchronization extracts every slide as a high-resolution image and pairs it with corresponding text to prevent context loss.
- LaTeX rendering converts mathematical notations into professional, vector-based formulas using matplotlib mathtext.
- Step-by-step derivation generates dedicated blocks for complex proofs and logical breakdowns.
- Vector-outline PDF generation flattens all fonts into vector shapes, ensuring perfect rendering on mobile devices and WeChat previews without font corruption.
- Content verification implements a zero-trust check against source slide data to ensure names, numbers, and formulas are copied accurately.
How it works
- Extraction: The
slides_to_pages.shscript converts the source document into individual page images. - Authoring: A Python script is generated using the
noteskitAPI to define the lecture structure, headers, and explanations. - Building: The script runs
noteskit.build()to compile the content into an HTML middle-product and a final flattened PDF. - Validation: The
preview_pdf.pyutility renders key pages to verify layout integrity, formula sizing, and page breaks.
Frameworks & tools
Requires Python 3 with matplotlib, weasyprint, pymupdf, and Pillow. It utilizes LibreOffice (soffice) for initial document conversion and Noto Sans CJK for multi-language support.
Why this beats prompting it yourself
Generic LLM prompts often hallucinate specific numbers from slides or fail to maintain the strict page-by-page mapping required for academic study. This skill provides a specialized Python framework that enforces structural discipline, handles complex CSS-based pagination, and solves the common PDF font-rendering issues that occur on mobile devices.
Use cases
- Generating pre-study materials for university courses with heavy mathematical content.
- Creating standardized corporate training manuals from existing slide decks.
- Producing high-fidelity digital summaries for technical seminars that require precise formula rendering.
- Converting legacy PDF notes into modern, mobile-compatible vector documents.
Known limitations
The final PDF output is flattened into vector outlines, meaning text cannot be selected, searched, or copied. LaTeX support is limited to matplotlib mathtext capabilities and does not support full LaTeX packages like boxed environments.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Technical Documentation.
PDF text is not searchable due to vector flattening. Does not support full LaTeX packages; formulas must follow matplotlib mathtext syntax. Requires LibreOffice for PPT/PPTX processing.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
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 to use
No account required to browse
Trust & safety
Security scan
Security scan passed 22 days ago
- Free with an Agensi account