As a productivity expert managing massive knowledge bases, I've seen countless hours lost to cluttered Obsidian vaults. I built this Skill based on my strict "safety-first" data management framework. Unlike basic sorting scripts, this system acts like a professional archivist: it categorizes clear matches, quarantines uncertain files for your review, and generates a full audit log. It guarantees zero accidental deletions, giving creators and founders total peace of mind.
Plan, audit, and repair a cohesive 5–20 track Suno album or playlist before spending generation credits.
Turn one music idea into a cohesive five-track outline with Album DNA, an energy curve, distinct roles, and concise production prompts.
Runs a five-axis consistency check on every turn — verifying character voice, world rules, timeline, dormant lore, and new contradictions — then proactively surfaces unused story elements, so your canon survives from chapter one to the final scene.
Turn product pages with traffic but weak conversion into a platform-aware listing copy pack. This download skill checks marketplace rules, benchmarks competitors, rewrites title, bullets, description, backend keywords or tags, localizes the buyer promise, and creates pre-listing QA in journal/listings/. Built for Amazon, Shopify, Shopee, Lazada, Etsy, TikTok Shop, and DTC sellers who need copy buyers understand in three seconds without triggering suppression.
Programmatic access to Google NotebookLM via the nlm CLI — manages notebooks, sources, queries, and artifacts with citation-quality source titles.
APA 7th citation formatter with CrossRef DOI validation, preventing LLMs from hallucinating author names on papers they didn't write.
LLMエージェントがセッションをまたいで記憶を保持するための永続メモリ層。抽象基底クラス MemoryStore ＋ LocalJSONStore 実装で、保存・取得・検索を再利用可能に。Karpathy の「LLM OS（記憶＝ディスク層）」着想。バックエンド差し替え可・Python標準ライブラリのみ・LLM呼び出しゼロ・ユニットテスト同梱。