Latest Agent Skills

Use when converting CSV-style tabular data into XML for downstream EDirect or XML-based processing.

Use when aligning short reads to a reference genome or indexed sequence database. Suitable for mapping FASTQ/FASTA reads in paired-end or single-end mode to produce SAM output.

Use when converting compatible BLAST annotation XML/ASN streams into a compact gene-markup-style table for downstream EDirect interval helpers.

Use when converting NCBI-style ASN.1 payloads into XML for downstream EDirect or XML-based processing.

Use when converting `Seq-entry` ASN.1/XML-like citation content into compact `CITATION` XML blocks for EDirect-style matching workflows.

Use when masking columns or coordinate ranges in multiple-sequence alignments before downstream HMMER or alignment-processing steps.

Use when converting ACE assembly files into SAM while preserving legacy ACE-specific padded or contig-sequence behavior.

Use when parsing, extracting, or converting XML data from NCBI Entrez or other bioinformatics sources into tab-delimited tables. Use for selecting specific elements, filtering records, and restructuring hierarchical XML into flat formats for downstream analysis.

Use when retrieving records from a local EDirect archive via the `x*` local-cache stack, not when calling the remote NCBI `efetch` service directly.

Use when working with FASTA or FASTQ files for statistics, filtering, transformation, format conversion, searching, or set operations.

Use when summarizing an RNA folding landscape by counting how many structures fall into each energy band, rather than enumerating individual folds one by one.

Use when paired-end reads need to be reordered so mates appear consecutively, or when preparing BAM files for featureCounts by adding dummy reads for singletons.

Use when building, indexing, or querying local XML record archives from NCBI Entrez databases, creating inverted indices, or managing PubMed local caches.

Use when searching one or more protein query sequences against a protein sequence database with HMMER's one-pass sequence-vs-sequence searcher.

Use when making raw HTTP, E-utilities, PubChem, datasets, or FTP requests through the low-level EDirect transport wrapper.

Use when searching DNA or RNA queries against nucleotide sequence databases with HMMER's nucleotide homology search engine.

Use when performing multiple sequence alignment of FASTA inputs, generating alignment ensembles, or calculating alignment confidence metrics.

Use when inferring maximum-likelihood phylogenies from aligned sequences, performing automated model selection, or assessing branch support with bootstrap or aLRT methods

Use when you need to characterize score distributions of a profile HMM on random sequences, such as calibration checks, benchmarking, or filter-behavior experiments.

Use when aligning RNA-seq reads to a reference genome using graph-based indexing for fast and sensitive spliced alignment.

Use when you need to perform quality control analysis on high-throughput sequencing data (fastq, bam, sam, or fast5 files) to identify potential problems before downstream analysis.

Use when you need to fetch records or data from NCBI Entrez databases (PubMed, nucleotide, protein, gene, SRA, etc.) by ID or accession

Use when converting PubMed `DocumentSummary` XML into `Pubmed-entry` ASN.1 text, or into the intermediate XML form before final ASN.1 flattening.

Use when comparing translated nucleotide query sequences against protein databases to identify homologous proteins and potential protein-coding regions.

Use when comparing protein sequences against protein databases for similarity searches, homology detection, or functional annotation.

Use when performing nucleotide-nucleotide similarity searches to identify homologs, annotate sequences, or compare query sequences against nucleotide databases.

Use when working from the local Biomni repository to run agent-style biomedical tasks or inspect Biomni's biomedical tool modules and examples.

Use when following local EDirect link relations such as PubMed `CITED`, `CITES`, or `PMCID` from an incoming UID stream or `ENTREZ_DIRECT` message.

Use when inspecting fields, indexed terms, or term counts from a local EDirect postings index rather than the remote `einfo` endpoint.

Use when simulating paired-end short reads from a reference FASTA for testing, benchmarking, or pipeline validation

Use when you need to index or query tab-delimited genomic files for fast region-based retrieval.

Use when doing lightweight FASTA/FASTQ transformations such as conversion, subsampling, subsequence extraction, trimming, or quick QC with seqtk.

Use when calculating thermodynamics of RNA-RNA interactions, including accessibility and binding energy predictions for RNA duplex formation.

Use when hashing FASTA records and comparing ordered versus order-insensitive sequence digests instead of taking a single whole-file MD5.

Use when performing multiple sequence alignment on nucleotide or protein sequences, such as preparing alignments for phylogenetic analysis or comparative genomics.

Use when processing raw FASTQ files for quality control, adapter trimming, length or complexity filtering, polyG tail trimming, or generating QC reports before downstream analysis.

Use when you need to post unique identifiers or accession numbers to NCBI Entrez databases for subsequent retrieval operations

Use when you need to navigate relationships between records in NCBI Entrez databases, find related articles, track citations, or link records across different databases such as PubMed to Protein.

Use when you need to discover available NCBI Entrez databases, explore searchable fields within a specific database, or identify cross-database links for building EDirect queries.

Use when invoking the top-level `easel` dispatcher to discover or run Easel sequence-analysis subcommands from the HMMER toolchain.

Use when converting RNA connectivity-table (`.ct`) files into extended FASTA with dot-bracket structures, optionally removing pseudoknots or modified bases.

Use when you need to compress or decompress files using BGZF (Blocked GNU Zip Format), create BGZF indexes for random access, or prepare bioinformatics files for tabix indexing.

Use when aligning spliced RNA-seq reads to a reference genome, generating genome indices, or performing splice-aware alignment for transcriptome analysis.

Use when filtering `RNAsubopt -s` output to keep p-optimal RNA structures in a ViennaRNA post-processing pipeline.

Use when working from the local Evo 2 repository for DNA-sequence scoring, embeddings, generation, or phage-genome design experiments.

Use when converting ViennaRNA-style sequence-plus-dot-bracket records on stdin into RNA connectivity-table output.

Use when aligning low-divergence DNA sequence reads to a reference genome

Create Request for Information templates for construction. TRIGGERS - Use when user needs help with rfi-template related tasks.

Create release plans with scope and deployment strategy. TRIGGERS - Use when user needs help with release-plan related tasks.

Design reading plans with retention strategies. TRIGGERS - Use when user needs help with reading-plan related tasks.

Build quizzes with question types and scoring. TRIGGERS - Use when user needs help with quiz-builder related tasks.

Design pulse surveys for rapid employee feedback. TRIGGERS - Use when user needs help with pulse-survey related tasks.

Write policy briefs with analysis and recommendations. TRIGGERS - Use when user needs help with policy-brief related tasks.

Design product-led growth strategies with self-serve funnels and expansion revenue. TRIGGERS - Use when user needs help with plg-strategy related tasks.

Create performance improvement plan templates. TRIGGERS - Use when user needs help with pip-template related tasks.

Design personal CRM systems for networking. TRIGGERS - Use when user needs help with personal-crm related tasks.

Write op-ed pieces with arguments. TRIGGERS - Use when user needs help with op-ed-writer related tasks.

Design NFT strategies with creation and marketplace. TRIGGERS - Use when user needs help with nft-strategy related tasks.

Create meme concepts with trending formats, captions, and brand alignment. TRIGGERS - Use when user needs help with meme-creator related tasks.

Write leave policies covering PTO, sick, and family leave. TRIGGERS - Use when user needs help with leave-policy related tasks.