NotebookLM PDF Cleaner

Create a presentation-ready copy of a NotebookLM-exported slide-deck PDF by masking the small visible NotebookLM footer badge at the bottom-right of each pag...

Security Scan

The skill's code and instructions match its stated narrow purpose (masking the small NotebookLM footer) and do not request credentials or network access, though it omits declaring two Python package dependencies.

Purpose & Capability

The script implements exactly what the description says (creates a masked '*-clean.pdf' copy by overlaying a white rectangle). However, the package metadata/requirements do not declare the Python dependencies used in the script (pypdf and reportlab). No unrelated credentials, binaries, or system paths are requested.

Instruction Scope

SKILL.md confines the work to NotebookLM slide-deck PDFs and instructs running the included script. The script enforces PDF-only input, refuses to overwrite the source file, and only strips metadata/annotations when explicit flags are used. It does not read unrelated files or environment variables, nor does it send data to external endpoints.

Install Mechanism

There is no install spec (instruction-only), which is low risk. But the script depends on third-party Python libraries (pypdf, reportlab) that are not declared in the skill metadata; the environment must already have them or the user must install them via pip. No downloads or archive extraction are performed by the skill itself.

Credentials

The skill requests no environment variables, credentials, or config paths. This is proportionate for its stated purpose.

Persistence & Privilege

The skill is not always-enabled and does not modify system or other-skill configuration. It runs as an on-demand script and writes only the specified output file.

Assessment

This skill appears to do exactly what it claims: overlay a white rectangle over the bottom-right badge and write a new '*-clean.pdf' without exfiltrating data. Things to consider before installing or running: 1) Dependencies: the script requires pypdf and reportlab but the skill metadata doesn't declare them — install via a trusted source (e.g., pip install pypdf reportlab) or run in a virtualenv. 2) Backup: always run it on a copy of your PDF (the script defaults to writing a new file, but double-check). 3) Flags: --strip-metadata and --strip-annots will remove provenance/comments; use them only if you intend to remove that information. 4) Visual correctness: the script overlays a white rectangle — on non-white slide backgrounds the mask may be visible; test and adjust --mask-* values as needed. 5) No network: the code contains no network calls or credential usage. 6) Review code: if you have concerns, inspect the included Python file before running to confirm there are no modifications. Overall the skill is coherent and narrow in scope; installing/running it in a contained environment with the declared Python packages is a reasonable next step.

Use this skill for NotebookLM slide-deck PDFs that contain the small visible NotebookLM footer badge in the bottom-right corner.

Default behavior

The default behavior is intentionally narrow and safe:

• keep the original PDF unchanged
• write a new *-clean.pdf copy
• mask the small bottom-right NotebookLM footer area on each page

It does not remove arbitrary watermarks or redesign slides.

Script

python3 {baseDir}/scripts/clean_notebooklm_pdf.py /path/to/input.pdf

By default it writes:

/path/to/input-clean.pdf

Useful flags

# Explicit output path
python3 {baseDir}/scripts/clean_notebooklm_pdf.py in.pdf --out out.pdf

# Inspect only (no output file written)
python3 {baseDir}/scripts/clean_notebooklm_pdf.py in.pdf --inspect

# Tune the bottom-right footer mask in PDF points (origin = bottom-left)
python3 {baseDir}/scripts/clean_notebooklm_pdf.py in.pdf --mask-x 1208 --mask-y 0 --mask-w 168 --mask-h 32

# Optional advanced hygiene flags
python3 {baseDir}/scripts/clean_notebooklm_pdf.py in.pdf --strip-metadata --strip-annots

Safety checks

• Refuse non-PDF input
• Refuse overwrite of the source file
• Refuse overwrite of an existing output unless --force is used
• Keep metadata/annotation stripping off by default

Defaults

The default mask is tuned for common 16:9 NotebookLM slide-deck exports:

• mask-x = 1208
• mask-y = 0
• mask-w = 168
• mask-h = 32

These values are scaled automatically for each page size.

Recommended workflow

1. Keep the original PDF
2. Create *-clean.pdf
3. Spot-check page 1 and one later page
4. If needed, adjust the mask values and rerun
5. Share or email the cleaned copy