Back to skills
SkillHub ClubShip Full StackFull Stack
pdf-analysis
Imported from https://github.com/az9713/cerebro.
Packaged view
This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.
Stars
2
Hot score
79
Updated
March 20, 2026
Overall rating
C2.8
Composite score
2.8
Best-practice grade
S96.0
Install command
npx @skill-hub/cli install az9713-cerebro-pdf-analysis
Repository
az9713/cerebro
Skill path: .claude/skills/pdf-analysis
Imported from https://github.com/az9713/cerebro.
Open repositoryBest for
Primary workflow: Ship Full Stack.
Technical facets: Full Stack.
Target audience: everyone.
License: Unknown.
Original source
Catalog source: SkillHub Club.
Repository owner: az9713.
This is still a mirrored public skill entry. Review the repository before installing into production workflows.
What it helps with
- Install pdf-analysis into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
- Review https://github.com/az9713/cerebro before adding pdf-analysis to shared team environments
- Use pdf-analysis for development workflows
Works across
Claude CodeCodex CLIGemini CLIOpenCode
Favorites: 0.
Sub-skills: 0.
Aggregator: No.
Original source / Raw SKILL.md
---
name: pdf-analysis
description: Analyze PDF documents including reports, whitepapers, ebooks, and manuals. Use when the user mentions PDF, document, whitepaper, ebook, report file, or wants to analyze a .pdf file.
---
# PDF Document Analysis
Analyze PDF documents to generate structured reports with summaries, key points, data extraction, and insights.
## When to Use
Activate this skill when the user:
- Mentions "PDF", "document", "whitepaper", "ebook", "report"
- Provides a file path to a .pdf file
- Asks to summarize or analyze a PDF document
- Wants to extract insights from a document file
- References a downloaded report or paper
## Instructions
1. **Get the file path** - Ask the user for the PDF file path if not provided
2. **Verify the file exists** and is readable
3. **Read the PDF content** using the Read tool
- The Read tool can extract text from PDF files
4. If reading fails:
- If PDF appears to be scanned/image-based: Inform user OCR may be needed
- Suggest alternative approaches if text extraction fails
5. **Read the analysis prompt** from `prompts/pdf.md`
6. **Extract document metadata** from content:
- Title (from content or derive from filename)
- Author if mentioned
- Date if mentioned
7. **Generate analysis** following the prompt structure exactly
8. **Create output directory** `reports/pdfs/` if needed
9. **Save the report** to `reports/pdfs/YYYY-MM-DD_sanitized-title.md` where:
- YYYY-MM-DD is today's date
- sanitized-title is the title in lowercase, spaces replaced with hyphens, special chars removed, max 50 chars
10. **Update the activity log** at `logs/YYYY-MM-DD.md`:
- Create file if it doesn't exist with standard sections
- Add entry under "## PDFs Reviewed" section (create if needed)
- Format: `- [Title](../reports/pdfs/filename.md) - HH:MM`
11. **Confirm to user** what was saved and where
## Report Format
Include this header in the report:
```markdown
# [Document Title]
**Source**: [file path]
**Date**: YYYY-MM-DD
**Type**: PDF Document
---
[Analysis content following prompts/pdf.md structure]
---
## My Notes
[Empty space for user notes]
```
## Error Handling
- If file path doesn't exist: Ask user for correct path
- If file is not a PDF: Suggest using /analyze for other file types
- If text extraction fails: Suggest OCR or manual copy
- If prompts/pdf.md missing: Use prompts/default.md
## Related
- Slash command equivalent: `/pdf <filepath>`
- Prompt file: `prompts/pdf.md`
- Output location: `reports/pdfs/`