メニュー
Prepare for US medical licensing exams with progress tracking, weak area analysis, question bank management, and residency match planning.
Convert raw Nanopore signal data (FAST5/POD5) to nucleotide sequences using Dorado basecaller. Covers model selection, GPU acceleration, modified base detection, and quality filtering. Use when processing raw Nanopore data before alignment. Guppy is deprecated; use Dorado for all new analyses.
Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation.
Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
Analyze protein-protein interaction networks using STRING, BioGRID, and SASBDB databases. Maps protein identifiers, retrieves interaction networks with confidence scores, performs functional enrichment analysis (GO/KEGG/Reactome), and optionally includes structural data. No API key required for core functionality (STRING). Use when analyzing protein networks, discovering interaction partners, identifying functional modules, or studying protein complexes.
Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm. For QC thresholds, use protein-qc.
End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate. For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.
| name | usmle |
| slug | usmle |
| version | 1.0.1 |
| description | Prepare for US medical licensing exams with progress tracking, weak area analysis, question bank management, and residency match planning. |
User is preparing for USMLE (United States Medical Licensing Examination). Agent becomes a comprehensive study assistant handling scheduling, tracking, practice, and match planning for US MDs, DOs, and IMGs.
| Topic | File |
|---|---|
| Exam structure and scoring | exam-config.md |
| Progress tracking system | tracking.md |
| Study methods and resources | study-methods.md |
| Stress management and wellbeing | wellbeing.md |
| Residency targeting | targets.md |
| User type adaptations | user-types.md |
User data lives in ~/usmle/:
~/usmle/
├── profile.md # Goals, target score, exam dates, user type
├── steps/ # Per-step progress (step1, step2ck, step3)
├── sessions/ # Study session logs
├── assessments/ # NBME, UWorld self-assessments, practice tests
├── qbank/ # Question bank tracking (UWorld, Amboss, etc.)
└── feedback.md # What works, what doesn't
Before study planning, gather:
~/usmle/