bhaveshpabnani/humungousaur/pdf-operations
Claude Code and agent skill by bhaveshpabnani/humungousaur
- community
Checking that the SKILL.md file is still in the repository.
List, read, summarize, save browser PDFs, and plan richer PDF work using Humungousaur-native PDF, browser, file, and approved interpreter tools.
Install
npx vskill@latest install bhaveshpabnani/humungousaur/pdf-operationsSKILL.md
PDF Operations
Purpose
Handle PDF knowledge work with clear evidence. Humungousaur has native PDF listing, reading, summarization, merge, page extraction, live-browser PDF save, and OCR readiness checks.
When To Use
Use for reading PDFs, summarizing document sets, extracting key points, saving browser pages as PDFs, or planning PDF creation/editing.
Inputs And Evidence
- PDF path or directory, requested summary depth, page limits, extraction target, and output format.
- Browser session ID for saving pages as PDF.
Tool Map
list_pdfsread_pdfsummarize_pdfspdf_mergepdf_extract_pagesocr_provider_statusbrowser_live_save_pdfpython_interpreterwrite_note
Workflow
- Confirm the PDF path is inside allowed roots.
- Use
read_pdffor a specific PDF orsummarize_pdfsfor a folder. - Preserve page/source references where possible.
- Use
pdf_mergewhen the user wants a combined local PDF artifact. - Use
pdf_extract_pagesfor split/extract page-range workflows. - Use
ocr_provider_statusbefore OCR claims; if OCR is not ready, report the exact local provider gap. - Use browser PDF save for live pages only after approval.
- Save summaries or notes when requested.
Native Implementation Boundaries
- Use Humungousaur PDF/browser tools.
- Do not import Anthropic PDF or external reference nano-pdf scripts directly.
- Add future fill/OCR extraction operations as native tools with tests before claiming support.
Safety And Approval
- Do not read PDFs outside allowed roots.
- Avoid reproducing long copyrighted text.
- Treat scanned/OCR results as uncertain.
Verification
- Report PDF path, page count/limits when available, and extraction errors.
- Generated PDFs require output path verification.
- Unsupported operations should be labeled clearly; OCR readiness is not the same as OCR extraction.
Failure Modes
- Treating a scanned PDF as successfully read text.
- Missing extraction errors.
- Claiming fill or OCR extraction support when no native tool ran.
References
- Shortlist item:
pdf-operations.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/office-productivity/pdf-operations/SKILL.md
Popularity
- Repository stars
- 8
- 7-day trend score
- 16
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/bhaveshpabnani/humungousaur/pdf-operations)