Document Skills

Document Skills

When to Use This Skill

Use this skill when implementing document skills patterns in your codebase.

How to Use This Skill

1. Review the patterns and examples below
2. Apply the relevant patterns to your implementation
3. Follow the best practices outlined in this skill

Collection of document processing skills for various file formats.

Sub-Skills

Skill	Format	Purpose
docx	Microsoft Word	Word document processing
pdf	PDF	PDF document handling
pptx	PowerPoint	Presentation processing
xlsx	Excel	Spreadsheet processing

Usage

Individual sub-skills are invoked based on file type:

skill: "pdf"      # For PDF files
skill: "xlsx"     # For Excel files
skill: "docx"     # For Word documents
skill: "pptx"     # For PowerPoint files

See Also

• skills/README.md - Skills overview

---

Success Output

When successful, this skill MUST output:

✅ SKILL COMPLETE: document-skills

Completed:
- [x] Document operation completed using [docx|pdf|pptx|xlsx] sub-skill
- [x] Output file(s) created at [path(s)]
- [x] Format-specific validation passed
- [x] File integrity verified

Outputs:
- [path/to/output.docx|pdf|pptx|xlsx]

Delegated to: [sub-skill name]

Completion Checklist

Before marking this skill as complete, verify:

• Correct sub-skill selected based on file format
• Sub-skill completed successfully (see sub-skill's checklist)
• Output file exists and is valid for the format
• Format-specific standards followed (see sub-skill requirements)

Failure Indicators

This skill has FAILED if:

• ❌ Wrong sub-skill selected for file format
• ❌ Sub-skill execution failed (see sub-skill's failure indicators)
• ❌ Output file not created or corrupted
• ❌ Format standards not followed

When NOT to Use

Do NOT use this skill when:

• Plain text is sufficient (use .txt or markdown)
• Data only needs CSV format (use pandas directly)
• No document processing needed (wrong skill entirely)
• Web content is better format (use HTML/markdown)

Use alternatives:

• Simple text: Use .txt or markdown files
• Data tables: Use CSV with pandas
• Web content: Use HTML or markdown
• Source code: Use appropriate language files

Anti-Patterns (Avoid)

Anti-Pattern	Problem	Solution
Using wrong format	PDF for editable content	Choose right format: DOCX (editable), PDF (final)
Not checking dependencies	Sub-skill fails on missing tools	Verify dependencies before invoking sub-skill
Ignoring format limitations	Trying to edit PDF like DOCX	Understand format constraints
Bypassing sub-skill validation	Corrupted outputs undetected	Always follow sub-skill completion checklist

Principles

This skill embodies:

• #3 Right Tool for Job - Delegate to appropriate format-specific sub-skill
• #6 Clear, Understandable, Explainable - Each sub-skill specializes in one format
• #7 Separation of Concerns - Format logic isolated in sub-skills
• #10 First Principles - Understand document formats and their use cases

Reference Standards:

• DOCX: Editable documents with tracked changes
• PDF: Final distribution format, forms, archival
• PPTX: Visual presentations with design principles
• XLSX: Spreadsheets with formulas and data analysis