Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nimadorostkar/Claude-Skills-collection --skill pdfgit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/pdf)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/pdf"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/pdf/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/pdf"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/pdf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.01200 |
| Opus 5.5 | $0.00033 | $0.00480 |
| Sonnet 5.5 | $0.00016 | $0.00240 |
| Haiku 4.5 | $0.00008 | $0.00120 |
Grade A, and why
pdf scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Read, manipulate, and produce PDFs — including the scanned ones that contain no text at all and the ones whose tables are drawn rather than structured.
When to Use
- Extracting text or tables from a PDF.
- Merging, splitting, or rotating pages.
- Filling a PDF form.
- OCR on a scanned document.
- Generating a PDF report or invoice.
Capabilities
- Text extraction, with layout preservation where it matters.
- Table extraction.
- Page operations: merge, split, rotate, reorder, watermark.
- Form field reading and filling.
- OCR for scanned or image-only PDFs.
- Generation with proper typography and pagination.
Inputs
- The source PDF, and whether it contains real text or images of text.
- The target: extracted data, a modified PDF, or a new one.
Outputs
- Extracted text or structured tables.
- A valid modified or generated PDF.
Workflow
- Determine whether it has text at all — Extract from the first page. If nothing comes out, it is a scan, and every text-based approach will silently return nothing. That is the single most important check.
- Choose the extractor by the task — Simple text extraction for prose; a layout-aware extractor for anything where column position carries meaning; a dedicated table extractor for tables.
- OCR only when necessary — It is slow and imperfect. If the PDF has a text layer, use it.
- Preserve what matters when editing — Merging PDFs drops bookmarks, form fields, and annotations unless you carry them across deliberately.
- Verify the output — Open it. A PDF that a library writes without error can still be structurally broken.
Best Practices
- A PDF that returns an empty string from text extraction is not empty; it is a scan. Check for this before concluding the file is corrupt.
- Tables in PDFs are usually drawn lines and positioned text, not structured tables. A general text extractor will interleave the columns into nonsense. Use a table-specific tool.
- Text extraction order follows the PDF's internal content stream, not the visual reading order. A two-column layout will frequently extract as interleaved lines.
- OCR quality depends overwhelmingly on the input image. Deskew and increase the contrast before OCR; it is worth more than any tuning of the OCR engine.
- Do not use
pypdffor text extraction quality — it is fine for page operations and poor at text. UsepdfplumberorPyMuPDF. - A generated PDF needs embedded fonts, or it will render differently on every machine that lacks them.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 17d ago Changed · +48 tokens per session f266be2808ef
- 1mo ago First seen · 121 lines · 34 tokens per session scan A 4eadd1356791
pdf is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (33 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 1,200 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Summarize document text and identify its main claims, evidence, and unanswered questions.
ape-write-paper
Writes a polished, standard two-column research paper (LaTeX to PDF) from any source material -- code, docs, experiment logs, benchmark files, notes -- optimising for correctness, readability, structure, figures, tables and references. Supports both standalone papers and conference templates (ACM SIGMOD/VLDB, IEEE…
LaTeX工具
A tool for creating, compiling, and checking mathematical modelling papers written in LaTeX, a document system often used for technical writing.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
tutor-setup
Transforms knowledge sources into an Obsidian StudyVault. Two modes: (1) Document Mode — PDF/text/web sources → study notes with practice questions. (2) Codebase Mode — source code project → onboarding vault for new developers. Mode is auto-detected based on project markers in CWD.
huashu-md-to-pdf
Convert Markdown documents into professional Apple-style PDF white papers. Supports full Markdown syntax (code blocks, tables, blockquotes, lists, etc.). Auto-generates cover page, table of contents, and headers/footers. Use cases: technical documentation, white papers, tutorials, reports — any Markdown document…