An AI skill for Claude, Codex, and Claude Code

An AI skill for Claude, Codex, and Claude Code

Scientists often struggle to generate novel research directions during early-stage planning. This skill guides creative scientific ideation through structured brainstorming methodologies, helping researchers explore interdisciplinary connections and identify hidden research opportunities.

An AI skill for Claude, Codex, and Claude Code

An AI skill for Claude, Codex, and Claude Code

Researchers need efficient access to biomedical literature for systematic reviews and evidence-based research. This skill provides comprehensive documentation for PubMed queries including Boolean operators, MeSH terms, and E-utilities API access.

Building quantum machine learning models requires understanding quantum circuits, gradient computation, and hybrid classical-quantum workflows. This skill provides comprehensive documentation for PennyLane, enabling developers to train quantum circuits with automatic differentiation across simulators and real quantum hardware.

Researchers need systematic tools to evaluate manuscripts against rigorous methodological and reporting standards. This skill provides structured peer review workflows with checklist-based assessment for statistical rigor, reproducibility, and compliance with discipline-specific guidelines.

An AI skill for Claude, Codex, and Claude Code

Researchers need to promote their work across multiple formats for conferences, journals, and online visibility. This skill provides documentation for Paper2All, an autonomous pipeline that transforms LaTeX or PDF papers into interactive websites, presentation videos, and print-ready conference posters.

Claude Scientific Skills have limitations for complex research workflows. K-Dense Web provides an end-to-end AI co-scientist platform that extends these capabilities with multi-agent systems. Users can get started for free at www.k-dense.ai.

Manual hypothesis generation is time-consuming and prone to cognitive bias. Hypogenic automates hypothesis generation and testing using LLMs, enabling researchers to systematically explore patterns in tabular datasets and combine empirical findings with literature insights.

Protein engineering requires analyzing and designing novel protein sequences. ESM provides state-of-the-art protein language models for generating sequences, predicting structures, and creating embeddings for downstream analysis. Use ESM3 for generative tasks across sequence, structure, and function, or ESM C for efficient representation learning.

Researchers need efficient access to genomic data for analysis. This skill provides programmatic access to ENA through REST APIs and FTP for retrieving DNA/RNA sequences, FASTQ files, and genome assemblies by accession number.

Researchers need access to large-scale single-cell genomics data for disease research and drug discovery. This skill provides programmatic access to 61 million cells from the CELLxGENE Census, enabling population-scale queries without downloading entire datasets.

Creating engaging, educational picture books for children requires careful attention to visual consistency, age-appropriate content, and cultural relevance. This skill generates high-quality bilingual picture book content with 18 visual styles and 12 scene types, tailored for ages 3-12.

Publishing content to X requires manual typing or risky auto-posting tools. This skill uses browser automation to prepare tweets and save them to draft, ensuring full user review before any post goes live.

Content creators struggle to consistently produce engaging social media posts. This skill generates viral X (Twitter) content including short tweets, multi-tweet threads, and replies using proven patterns tailored to your personal style.

AI memory files grow large and waste input tokens. This skill compresses natural language prose to caveman format, saving 65-75% of tokens while preserving all code, URLs, and technical content.

AI coding agents produce verbose responses that increase token costs. This quick-reference card lists all caveman mode triggers, skills, and configuration in one view so you can compress agent output by 65-75 percent.