Handling Garbled Input

YAML
---
name: handling-garbled-input
description: Handles garbled, test, or corrupted input by creating minimal placeholder content. Use when input contains repeated nonsense strings or appears to be test data.
---

# Handling Garbled Input

Python
import re

def handle_garbled_input(text):
    # Detect garbled patterns
    if re.search(r'(\w+)\1{2,}', text) or len(set(text.split())) < 3:
        return {
            "status": "garbled_input_detected",
            "original": text[:50] + "..." if len(text) > 50 else text,
            "placeholder": "minimal-placeholder-skill",
            "description": "Placeholder for unclear input processing"
        }
    return process_normally(text)

1. Pattern Detection - Check for repeated strings, low vocabulary diversity
2. Classification - Categorize as test data, corruption, or gibberish
3. Placeholder Generation - Create minimal viable skill structure
4. Template Output - Return standardized placeholder format

Progress:

• Run regex pattern matching on input
• Calculate text entropy and vocabulary ratio
• Generate appropriate placeholder skill template
• Format as valid skill structure

Example 1: Input: testse feafatestse feafatestse feafa Output:

YAML
---
name: placeholder-skill
description: Placeholder skill for unclear input. Use when input needs clarification.
---
# Placeholder Skill

Awaiting clear input specification.

**Example 2:**
Input: `aaaabbbbccccdddd`
Output: Minimal skill template with entropy warning and character pattern analysis

• Use regex patterns: r'(\w{3,})\1+' for repetitions
• Calculate vocabulary diversity: unique_words / total_words < 0.3
• Generate valid YAML frontmatter even for gibberish
• Include original input snippet for reference

• Don't try to extract meaning from pure test strings
• Avoid complex parsing on obviously corrupted data
• Don't generate overly elaborate placeholders for simple garbled input