This skill takes a rough idea through three phases: expanding it with variations and sharpening questions, evaluating and narrowing the options, and writing a one-page summary. The summary states the problem, the direction it recommends, the assumptions still to test, the MVP scope, what is out of scope, and open questions. It is meant as an interactive conversation, started with an idea or a request to refine it or stress-test a plan.
AI Research ExploreExplores AI research repos and papers systematically before reproduction or training runs.Research
Build a personal wiki that an LLM maintainsThis skill sets up and maintains a personal knowledge base from your sources, using two folders: raw for untouched source material and wiki for compiled articles. You ask it to ingest a source, answer a question from the wiki, or check the wiki for problems. On ingest it saves the source, then writes or updates articles, an index, and an operation log. Any figure, date, or quotation in an article has to appear word for word in its linked raw files, and a script checks this during the lint pass.ResearchKnowledge baseNotes
Environment and Assets BootstrapPrepares a conservative environment and assets bootstrap for README-first machine-learning reproduction.ResearchResearchOps
Find every company or person that fits a descriptionThis skill uses the Parallel FindAll API to list every company, person, product, or other item that matches a plain-language description. You can ask for extra fields on each match, and every result comes with evidence. It returns a list, not web pages or a narrative report. The Parallel CLI is required.ResearchEntity SearchWeb Research
Hugging Face LLM TrainerFine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs.ResearchResearchData
Jupyter NotebookCreates and edits Jupyter notebooks for analysis, demos, and reproducible research workflows.Research
