Discovers and applies curated Hugging Face datasets, models, and Spaces across 17 scientific domains, from protein design to climate modeling.
Turns observations into evidence-bounded candidate hypotheses, rival explanations, discriminating predictions, and preregistration-ready analysis plans.
Reads any text and maps the author's thinking style across 12 cognitive dimensions into a 'cognitive fingerprint' profile.
Lets Claude read, create, and update Zotero libraries and export citations through the pyzotero Python client.
Plans studies by computing required sample size, minimum detectable effect, and power curves via closed-form formulas or Monte Carlo simulation.
Runs ORA and (pre)ranked GSEA on gene lists or ranked gene tables across GO, KEGG, Reactome and MSigDB, then interprets and visualizes the results.
Creates and validates animated GIFs that fit Slack's emoji and message requirements using Python/PIL.
Auto-detects any knowledge source — docs site, GitHub repo, PDF, video, codebase — and turns it into a packaged AI skill.
Assembles a role-based AI team of doers, directors, and critics to run meetings, debates, and system design end to end.
Diagnoses and strips AI writing tells from web-fiction drafts with minimal, plot-preserving edits.
Drive Chrome over the DevTools Protocol so automation reuses your existing logged-in session.
Drive Chrome over the DevTools Protocol to reuse existing logins — open pages, run JavaScript, click elements, and pull auth tokens.
Generates, syncs, validates and publishes editable .drawio diagrams from plain requests or from code, IaC, SQL and OpenAPI sources.
Captures your in-session corrections via hooks and applies them to CLAUDE.md through a reviewed /reflect command.
A symptom-driven debugging guide for tool/function calling: no tool call, wrong arguments, runaway ReAct loops, or schema design from scratch.
Give it a book title and pen name; it infers the genre and uses GPT-Image-2 to produce a professional web-novel cover with the title and author name already rendered.
Diagnoses and strips AI writing tells from web-novel prose with minimal, function-preserving edits.
Cross-references git diffs or PRs against your project's knowledge graph to report changed components, blast radius, and risk.
Explains a specific file, function, or module in depth by combining a pre-built knowledge graph with the actual source code.
Turns raw meeting transcripts into complete, evidence-backed structured minutes using parallel multi-pass generation and retrieval verification.