Turns any capital expenditure question — equipment, hiring, software, real estate — into a numbers-backed ROI/NPV/IRR analysis with a clear go/no-go recommendation.
Runs a 6-phase, multi-role executive deliberation on a strategic question, with a mandatory founder approval gate before decisions are logged.
Builds production-grade Playwright workflows for scraping, form filling, screenshot/PDF capture, session reuse and anti-detection.
Analyzes marketing campaigns with five attribution models, funnel drop-off detection, and full ROI/ROAS/CPA metrics via three dependency-free Python CLIs.
A blunt Marc Andreessen persona that pressure-tests ideas and ventures market-first and ends with a BUILD / DERISK / KILL verdict plus confidence level.
Interviews a founder across 12 phases and materializes the whole company as a linked, version-controllable OKF markdown bundle.
A frontend discipline skill that forbids saying "done" until the site builds, passes checks, and is visually verified in a real browser.
Plans, AI-generates, and assembles research talk decks — conference presentations, seminars, and thesis defenses — into PDF or PowerPoint.
Builds a manuscript-ready research packet — 60 verified, deduplicated references plus evidence matrix and BibTeX — using Parallel Search, Extract, and Research.
An all-in-one geospatial skill that turns satellite imagery, GIS, spatial statistics and spatial ML tasks into ready-to-run code patterns.
An Exa-powered skill for semantic web search and batch URL/PDF extraction, tuned for scientific and technical sources.
Picks the right study design and generates seeded randomization schedules and DOE matrices before any data is collected.
Guides Claude through Hugging Face Transformers work: Hub model loading, pipeline inference, text generation, and Trainer fine-tuning on transformers 5.x.
Search OpenAlex, PubMed, and Google Scholar, extract accurate metadata, and generate, clean, and validate BibTeX bibliographies.
A skill for scaling pandas/NumPy workloads beyond RAM using Dask's parallel and distributed collections.
Guides Claude in using Datamol, the Pythonic RDKit wrapper, for SMILES parsing, standardization, fingerprints, clustering, and 3D conformers.
A skill that systematically appraises scientific claims for design validity, bias, statistical soundness, and evidence quality using GRADE and Cochrane RoB.
Resolves free-text scientific labels into exact ontology IDs via EBI OLS4 and validates existing CURIEs for existence, obsolescence, and label consistency.
Guides Claude to do exact symbolic math in Python with SymPy — algebra, calculus, solvers, matrices — and export results as code or LaTeX.
Retrieve facts from 78 documented public database APIs reproducibly, with explicit endpoints, pagination, and provenance.