morsechimwai

Removes signs of AI-generated writing from text, making it sound more natural and human-written. Based on Wikipedia's 'Signs of AI writing' guide, it detects and fixes patterns like inflated symbolism, promotional language, and passive voice.

Use when working with large-scale data, similarity search, deduplication, top-K / heavy-hitters, streaming analytics, cardinality estimation, embeddings, recommender systems, signal/image processing, polynomial or big-integer arithmetic, convolution, graph distance, computational geometry, randomized algorithms, or any problem with n >= 10^6 where exact computation is wasteful.

Use when refactoring existing code with poor Big-O, such as nested loops, O(n^2)+ scans, repeated work, redundant allocations, or blown memory.

Use this skill when writing or reviewing code that calls paid AI/inference APIs in a loop, queue, retry path, agent step, webhook handler, or background job. It treats dollar cost as a third complexity dimension alongside time and space, enforcing a per-run cost cap.

Use this skill when developing or reviewing algorithms where the straightforward implementation might be subtly incorrect, such as with strong postconditions, in-place mutations using read/write pointers, complex recursive states, or potential off-by-one errors.

Use for code involving loops, collections, lookups, searches, joins, recursion, graphs, or queries over many items. It enforces algorithmic thinking by identifying time/space complexity, data structures, and algorithm families, catching inefficiencies like O(n^2) loops or N+1 queries.

This skill is for writing, editing, or reviewing code involving loops, collections, lookups, searches, joins, recursion, graphs, queries, or any computation over many items. It forces algorithmic thinking by identifying time/space complexity, data structures, and algorithm families, catching inefficiencies like O(n^2) loops or N+1 queries.

Ideal for large-scale data tasks such as similarity search, deduplication, streaming analytics, and cardinality estimation. It's also useful for embeddings, recommender systems, signal/image processing, and problems with n >= 10^6 where exact computation is inefficient.

Use to refactor existing code with poor Big-O, addressing issues like nested loops, O(n^2) complexity, repeated work, or excessive memory usage. It focuses on optimizing the time and space complexity of already implemented code.

Use this skill when writing or reviewing algorithms where the obvious implementation is subtly wrong, such as those with strong postconditions, in-place mutations, complex recursion, or potential off-by-one errors.

Transform AI-generated text into natural, human-like content that bypasses AI detectors like GPTZero, Turnitin, and Originality.ai. Uses credits based on word count.