raghulpasupathi skills on Claude Market

smart-cache

SmartCache is a JavaScript class implementing in-memory caching with LRU and LFU eviction strategies. It supports configurable max size, per-entry TTL, and returns hit/miss metadata on every read. Cache stats including hit rate and current size are available via getStats().

nlp-toolkit

Analyzes text using statistical NLP measures to estimate whether it was written by a human or generated by AI. Computes perplexity, burstiness, and Shannon entropy scores, then combines them into a confidence rating.

rate-limit-pro

Rate Limit Pro is a JavaScript class that enforces per-user request quotas using sliding time windows and configurable tiers. It tracks request timestamps in memory and returns remaining quota, reset timing, and denial reasons on each check.

image-detection

A collection of three sub-skills for detecting AI-generated images: local EXIF and artifact analysis, ML-based classification using pre-trained HuggingFace models, and cloud-based detection via the Hive Moderation API. Each sub-skill runs independently or in combination using a majority-voting strategy. Supports detection of images from Stable Diffusion, Midjourney, and DALL-E.

gpt-analyzer

Analyzes text for GPT-generated content using phrase matching, structural patterns, and sentence uniformity checks. Attempts to distinguish between GPT-4 and GPT-3.5 outputs based on model-specific phrase signatures. Returns a confidence score, detected model, and a plain-language recommendation.

hash-toolkit

Provides MD5, SHA1, SHA256, and SHA512 hashing via Node.js built-in crypto, plus a simplified perceptual hash for content similarity. Includes duplicate detection by comparing against a known hash set and a similarity score between two hashes.

age-verification

Age Guard verifies user age through document scanning, face-based estimation, or third-party APIs. It includes age gate UI components and parental consent workflows for enforcing age restrictions in apps.

text-detection

A set of tools for detecting AI-generated text, particularly content produced by GPT models. It analyzes perplexity, burstiness, sentence patterns, and structural signatures to classify text as AI-written, human-written, or mixed.

geo-blocking

Country-based content filtering with IP geolocation, VPN/proxy detection, and Tor exit node identification. Supports regional compliance rules including GDPR, Germany's hate speech laws, and government-mandated blocks.

parental-controls

A guardian interface for monitoring and controlling children's internet activity. Provides weekly activity reports, real-time alerts for high-risk content categories, and screen time management. Settings are PIN-locked so children cannot disable protections.