Education

Turns Claude into a Feynman-style thinking advisor that uses 5 mental models and 8 heuristics to test whether you truly understand something or just memorized its name.

An official skill that answers Claude how-to questions first, then quietly suggests at most two genuinely matching courses or tutorials from the live Claude Academy catalog.

Runs developmental, evidence-traceable reviews of papers, protocols and research ideas, plus local audits of low-stakes assessment rubrics.

Builds a manuscript-ready research packet — 60 verified, deduplicated references plus evidence matrix and BibTeX — using Parallel Search, Extract, and Research.

Search OpenAlex, PubMed, and Google Scholar, extract accurate metadata, and generate, clean, and validate BibTeX bibliographies.

A skill that systematically appraises scientific claims for design validity, bias, statistical soundness, and evidence quality using GRADE and Cochrane RoB.

Guides an authorized reviewer through evidence-bounded, confidential peer-review drafting for manuscripts, protocols, preprints, and proposals.

Runs evidence-aware research ideation with independent generation, transparent scoring, adversarial review, and an auditable decision log.

Turns observations into evidence-bounded candidate hypotheses, rival explanations, discriminating predictions, and preregistration-ready analysis plans.

A persona skill that analyzes AI tech, learning methods, and industry trends through Andrej Karpathy's mental models and voice.

An interactive assessment that tells you whether your product org is merely "AI-first" (faster tasks) or truly "AI-shaped" (redesigned work), and which of five competencies to build next.

Runs a systematic literature review across PubMed, arXiv, bioRxiv and Semantic Scholar, then verifies every citation and exports a publication-ready markdown/PDF.

A three-role pipeline (modeler → coder → paper writer) that solves math-modeling competition problems end to end with independent QA gates.

A three-role pipeline that takes a math-modeling contest problem from analysis to runnable code, figures, and a full Word/LaTeX paper.

A persona skill that answers education, career, and social-mobility questions in the blunt, data-first voice of Chinese admissions guru Zhang Xuefeng.

A hands-on guide to nanoGPT: train a tiny Shakespeare model on CPU or reproduce GPT-2 (124M) on multi-GPU, step by step.

A reference framework that diagnoses the PM-to-Director transition along two axes — Altitude (how wide you zoom out) and Horizon (how far ahead you look) — and shows how to cascade vague strategy into team clarity.

Runs PaperOrchestra's four LLM-as-judge autoraters — Citation F1, 6-axis literature-review quality, and two side-by-side comparisons — on your paper drafts.

A thinking-advisor skill that reviews your ideas, decisions and explanations through Richard Feynman's mental models.

Analyzes your recent Claude Code chat history to surface coding patterns and skill gaps, then delivers a personalized growth report with curated resources to Slack.