FASTA Database Curator

Overview

Automate the curation and standardization of biological sequence databases. This skill handles the tedious work of processing FASTA/FAA files, ensuring consistent header formats, removing duplicates, and preparing databases for downstream analysis.

Supplementary version-grounded tool notes: tools.md.

Key Capabilities:

• Header format standardization (pipe separators, prefixes)
• Duplicate detection and removal (by sequence or ID)
• Format conversion (GenBank → FASTA, multi-line → single-line)
• Database merging with conflict resolution
• Statistics generation (counts, lengths, taxonomy, GC content)
• Validation (no whitespace in headers, proper formatting)
• Taxonomy label extraction and standardization

When to Use This Skill