Work with PDF files using the environment's built-in PDF and document tools. Use when the user wants to inspect, summarize, split, merge, compress, or convert PDFs.
Scanned 9/4/2026
Install to Claude Code
Skills Directorynpx -y skills add LFTPadilla/agent-dev-kit --skill pdf --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Pdf?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/lftpadilla-pdf)More formats (shields.io, HTML) on the badges page.
---
name: pdf
tags: ['skill']
description: Work with PDF files using the environment's built-in PDF and document tools. Use when the user wants to inspect, summarize, split, merge, compress, or convert PDFs.
---
# PDF
Use this skill when a user asks to work with a PDF or another document format that needs PDF conversion.
## Preferred path
Use the environment's built-in document and PDF tooling first. Prefer:
- reading and summarizing PDFs,
- extracting specific pages,
- merging PDFs,
- compressing PDFs,
- converting common document formats to or from PDF.
## Guidance
- If the user wants information from a PDF, inspect the file and answer directly.
- If the user wants a document operation, use the available PDF/document toolchain instead of inventing shell pipelines.
- Keep page references explicit when summarizing or extracting.
- Confirm before destructive operations like overwriting or replacing a file.
## Notes
- If the environment already exposes richer built-in PDF tools, treat this skill as routing guidance, not as a custom implementation.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
