agentsclimarketplace

Nano pdf

Skill Orkas-AI/Orkas-Awesome-AgentSkills/office/skills/nano-pdf

Curated Orkas agents and skills for education, product development, content creation, data analysis, office automation, and e-commerce workflows.

Install
npx -y skills add Orkas-AI/Orkas-Awesome-AgentSkills --skill nano-pdf

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 12 stars12 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.9 KB, 523 tokens by cl100k_base, as published. Nobody here has run it

Nano PDF

When to Use

Use when the user asks to edit a PDF and the local nano-pdf CLI is available.

Good fits:

  • change text on a specific page
  • add a watermark
  • remove or redact a small visible element
  • apply a narrow natural-language edit to a page

Do not use when the task requires full document re-layout, legal-grade redaction guarantees, OCR-heavy reconstruction, form extraction, or arbitrary PDF generation.

Preflight

Before editing:

command -v nano-pdf
nano-pdf --help

If the CLI is unavailable, do not claim the edit was completed. Return a fallback plan or ask whether the user wants to install/configure the tool.

Workflow

  1. Confirm the source PDF path and requested output behavior.
  2. Create a backup or work on a copy. Never overwrite the only source PDF.
  3. Confirm the intended page number with the user-facing page label if possible.
  4. Run a small test or inspect output when page indexing may be ambiguous. Some versions/configurations may treat page numbers as 0-based while users expect 1-based.
  5. Run the edit.
  6. Open, render, or visually inspect the affected pages before delivery.
  7. If the edit landed on the wrong page, restore from backup and retry with the corrected index.

Command Pattern

nano-pdf edit <input.pdf> <page> "<natural language instruction>"

Example:

nano-pdf edit deck.pdf 3 "Change the title to Q3 Results and add a Confidential watermark"

Prefer working-copy names such as:

source.pdf
source.working.pdf
source.edited.pdf

Return Format

Return:

  • output PDF path
  • backup path
  • affected pages
  • command summary
  • visual verification status
  • known risks or manual checks

If the CLI is missing or the edit cannot be verified, return:

  • ok: false
  • reason
  • suggested fallback
  • any prepared but unexecuted instruction

Limits and Known Issues

  • Page numbering may be 0-based or 1-based depending on the installed CLI version/configuration. Verify before final delivery.
  • Natural-language edits may not preserve exact typography or layout.
  • PDF redaction is high risk. For sensitive redaction, require visual verification and consider a specialized redaction workflow.
  • Scanned PDFs may require OCR and may not be editable as text.
  • Always inspect output pages; a successful CLI exit is not enough.

Gives 0 of the 12 instructions most pdf office docs skills give in 523 tokens

Counted across 635 of the 690 authors here whose files we hold, read 2026-08-06

  • extract text using pdfplumberin 92 of 635, across 25 files
  • create PDFs using reportlabin 83 of 635, across 16 files
  • read FORMS.md to fill out PDF formsin 80 of 635, across 13 files
  • OCR scanned PDFs using pytesseractin 77 of 635, across 10 files
  • merge or split PDFs using qpdfin 70 of 635, across 3 files
  • use Excel formulas instead of hardcoded calculated valuesin 68 of 635, across 12 files
  • unpack edit xml and repack existing documentsin 63 of 635, across 8 files
  • document sources for hardcoded valuesin 61 of 635, across 9 files
  • write minimal python code without unnecessary commentsin 59 of 635, across 7 files
  • run the recalculation script after adding or modifying formulasin 58 of 635, across 6 files
  • fix all identified formula errors and recalculatein 58 of 635, across 6 files
  • format years as text stringsin 57 of 635, across 5 files

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.