Seqeron

Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or audit such a base, or initialize a new one. Trigger on phrases like "add this to my wiki", "ingest this paper", "compile this into the knowledge base", "what does my wiki say about X", "lint the wiki", "build a knowledge base from these documents", "research notes", "second brain", "personal knowledge base", or any reference to LLM Wiki / OmegaWiki. Trigger even when the user does not say "wiki" — if they are accumulating sources over time and want them organized, this applies. The skill scales — sharded indexes, atomic pages, YAML frontmatter, and a bundled search script keep the wiki from becoming a context bottleneck at hundreds or thousands of pages.

Ingest ONE newly-added or changed `docs/` file into the project LLM Wiki at `wiki/`, routing by ASPECT — each doc group is ingested differently. Use this whenever a single source doc is added/changed and its knowledge must land in the wiki, whatever its aspect: an algorithm spec (`docs/algorithms/**`), a validation artifact (`docs/Evidence/**`), a validation verdict (`docs/Validation/**`), a testing methodology (`docs/checklists/**`), an MCP-layer doc (`docs/mcp/**`), or a top-level/refactoring/skills/templates doc. Adding one algorithm typically drops SEVERAL such files (spec + Evidence + report + MCP tool) — run this per file; each is routed by its own group rules, not bundled blindly. Trigger phrases: "ingest this doc into the wiki", "I added <file>, update the wiki", "process the new Evidence/report/spec/tool", "reflect this validation report in the wiki", "wire the new MCP tool into the wiki". Do NOT use this for the multi-hundred-file backfill — that is the `/wiki:ingest` loop over `tools/wiki-ingest/ne

Predict and analyze RNA secondary structure with Seqeron (MCP tools OR the C# API). Use to fold an RNA / compute minimum free energy (MFE, Turner 2004 nearest-neighbour, kcal/mol), predict the secondary structure (dot-bracket + base pairs), enumerate stem-loops / hairpins, detect pseudoknots (crossing base pairs), find antiparallel complementary arms (RNA inverted repeats), classify base pairs (Watson-Crick / G-U wobble) and test if two bases can pair, parse / validate dot-bracket (WUSS) notation, and compute individual loop / stem / dangling-end / terminal-mismatch free-energy terms. Triggers: "fold this RNA", "predict secondary structure", "minimum free energy of…", "MFE of this RNA", "find stem-loops / hairpins", "detect pseudoknots", "is this dot-bracket valid", "parse this dot-bracket", "can G and U pair", "what base-pair type", "hairpin/internal/bulge/multibranch loop energy". Server: analysis (all RnaSecondaryStructure.*).

Build phylogenetic trees and compute population-genetics statistics with Seqeron (MCP tools OR the C# API). Phylogenetics: distance matrices (p-distance / Jukes-Cantor / Kimura-2P / Hamming), tree construction (Neighbor-Joining, UPGMA), Newick parse/serialize, tree stats (depth, length, leaves, MRCA, patristic + Robinson-Foulds distance), bootstrap support. Population genetics: allele/genotype frequencies, minor allele frequency (MAF) + MAF filtering, Hardy-Weinberg equilibrium test, Fst / F-statistics / pairwise Fst, nucleotide diversity (π), Watterson's θ, Tajima's D, heterozygosity, linkage disequilibrium (D'/r²) + haplotype blocks, runs of homozygosity / inbreeding, iHS, ancestry, selection scans. Triggers: "build a tree", "make a phylogeny / dendrogram from these sequences", "neighbor-joining / UPGMA tree", "distance matrix", "compute Fst", "test Hardy-Weinberg / HWE", "nucleotide diversity of this population", "Tajima's D", "linkage disequilibrium", "MAF filter". Servers: phylogenetics + population.

Design and QC molecular-biology reagents with Seqeron's MolTools server (47 tools) — PCR primer pairs and hybridization probes, CRISPR guide RNAs with off-target and specificity scoring, codon optimization of a CDS for a target organism (CAI/GC before-after), restriction-site finding and digest simulation, and melting-temperature (Tm) with salt correction. Use for "design primers for this template", "find/design CRISPR guides for this target and check off-targets", "codon-optimize this gene for E. coli / yeast / human", "where does EcoRI cut / simulate a digest", "design a qPCR/FISH probe", "compute the salt-corrected Tm", primer-dimer / hairpin / 3'-stability QC, and choosing compatible restriction enzymes. Dual-mode: MCP tool calls + equivalent Seqeron.Genomics C# Method IDs.

Annotate and characterize genomic sequences with Seqeron (MCP tools OR the C# API). Use to find ORFs / predict genes / promoters / RBS, call + annotate + classify variants (SNPs, indels, VEP-like effect, ACMG-like pathogenicity), discover and scan motifs (exact/degenerate/PROSITE/ PWM), analyze repeats & low-complexity / masking, profile k-mers & composition, plus splicing. (Read-evidence structural variants / CNVs → seqeron-structural-variants; miRNA targets / seeds / pre-miRNA hairpins → seqeron-mirna; RNA secondary-structure folding → seqeron-rna-structure; protein-feature prediction → seqeron-protein-features; methylation/epigenetics → seqeron-epigenetics; transcriptome/RNA-seq → seqeron-transcriptome; ANI/orthologs/synteny/comparative genomics → seqeron-comparative-genomics.) Triggers: "annotate this sequence", "find ORFs / genes / promoters", "call variants", "what motifs are in…", "classify this variant", "predict the effect", "mask low-complexity", "find repeats", "k-mer profile". Servers: annotation

Assemble sequencing reads into contigs and QC the result with Seqeron (MCP tools OR the C# API). Use to assemble reads via de Bruijn graph or overlap-layout-consensus (OLC), build/merge/scaffold contigs, compute read coverage over a reference, and report assembly statistics / N50; plus k-mer counting, k-mer spectrum, most-frequent / min-count / unique k-mers and clumps for assembly QC, and assembly-relevant repeat & low-complexity screening (direct/inverted/tandem repeats, palindromes, microsatellites, longest repeat). Triggers: "assemble these reads", "de Bruijn / OLC assembly", "compute N50 / assembly stats", "coverage of these reads over the reference", "k-mer spectrum of…", "most frequent k-mers", "find clumps", "screen for repeats before assembly". Servers: analysis + core (k-mer/repeat subset); the assembly-graph engine (de Bruijn/OLC/coverage/N50) is on the Alignment server.

One-time install & configuration for a freshly cloned Seqeron repo, so the bioinformatics skills are ready to solve real tasks. Use when the user says "install and configure", "set up Seqeron", "get me started", "onboard me", "prepare the repo", "why aren't the bio tools working", or asks how to make the Seqeron MCP tools / skills available. Verifies the .NET 10 SDK and Python are present, builds all 11 MCP servers into the on-demand cache (so the first real tool call is instant), and runs a live smoke test — without registering MCP anywhere (tool schemas stay out of the model's context; skills pull tools in on demand). Run this once per clone/machine; after it, just describe a biology task.

Macro-level system design — layers, dependencies, modules, and boundaries following Clean Architecture, DDD, SOLID, and hexagonal/onion patterns. Use when designing new features/modules, structuring or reviewing an architecture, planning microservices or a modular monolith, or applying the Dependency Rule, dependency inversion, ports & adapters, bounded contexts, aggregates/value objects/domain events, repositories, CQRS, screaming architecture, or vertical slices. For micro-level naming, functions, comments, and code smells, use the clean-code skill instead.

Micro-level code quality — naming, functions, classes, comments, error handling, and code smells following Robert C. Martin's Clean Code. Use when reviewing or refactoring code quality; naming variables/functions/classes; shrinking long or complex functions (cyclomatic/cognitive complexity, deep nesting); removing duplication (DRY), magic numbers/strings, or code smells; applying KISS/YAGNI; or writing self-documenting code, clean unit tests, and thread-safe async code. For macro-level layers, dependencies, modules, and boundaries, use the clean-architecture skill instead.

Find the right Seqeron bioinformatics tool or algorithm for a task WITHOUT loading all 427 MCP tool schemas. Use to answer "which Seqeron tool does X?", "is there a tool/algorithm for <biology thing>?", "find the tool for <task>", or before attaching MCP servers / writing a Seqeron C# API call and you need to pick the right tool. Covers melting temperature (Tm), primers, CRISPR guides, alignment (NW/SW/MSA), variant calling, k-mers/assembly, motifs/ORFs, phylogeny, popgen, metagenomics, restriction, codon optimization — across the 11 MCP servers and 247 algorithm docs.

Write a small Python tool/script that CALLS Seqeron algorithms over MCP. Use when the task is "wrap a Seqeron MCP tool in Python", "make a python function that calls gc_content / this Seqeron tool", "call the Seqeron algorithm from python", "generate a python wrapper for <tool>", or "build a python script / pipeline using Seqeron over MCP". The wrapper WRAPS the validated tool (never reimplement the algorithm in Python) using the repo helper scripts/skills/seqeron_mcp_client.py (call_tool / SeqeronToolClient) and the codegen scripts/skills/gen-python-stub.py. For the in-process C# API path use seqeron-dev; for tool discipline use bio-rigor.

Chromosome- and assembly-scale genome analysis with Seqeron (MCP tools OR the C# API). Use for karyotype & ploidy / aneuploidy (trisomy, monosomy) from depth or chromosome descriptors, centromere / telomere / heterochromatin and G-band prediction, arm-ratio classification (metacentric/acrocentric), synteny blocks & large structural rearrangements (inversion/translocation/ deletion/duplication), assembly QC (N50/L50, auN, Nx curve, contiguity, gaps, contig extraction, completeness/BUSCO-like, assembly comparison), and chromosome-scale composition/GC-skew profiling. Triggers: "analyze this karyotype", "detect aneuploidy / ploidy", "find the centromere / telomeres", "N50 of this assembly", "assembly stats", "find synteny blocks", "detect rearrangements", "GC-skew of this chromosome", "predict the replication origin", "sliding-window GC / composition". Server: chromosome (+ analysis for GC-skew/origin).

microRNA (miRNA) analysis with Seqeron (MCP tools OR the C# API). Use for canonical miRNA target-site prediction (8mer / 7mer-m8 / 7mer-A1 / 6mer, Bartel/TargetScan hierarchy) with AU/positional context and local structure accessibility, seed extraction / seed-family grouping / similar-miRNA search / single-nucleotide seed variants, miRNA→target antiparallel duplex alignment, pre-miRNA hairpin detection (mature/star arms + dot-bracket + Turner energy), and RNA base-pairing / G-U wobble tests. Triggers: "find miRNA target sites", "predict miRNA targets in this 3'UTR/mRNA", "what's the seed of this miRNA", "miRNA seed family", "group these miRNAs by seed", "find similar miRNAs", "generate seed variants", "align this miRNA to its target", "find pre-miRNA hairpins", "is this a G-U wobble pair in a miRNA duplex", "can these two miRNA/target bases pair", "reverse-complement a seed to get its target motif", "miRNA target accessibility / context score". A context-free base-pairing / G-U question with no miRNA framing

Cancer-genomics analysis with the Seqeron.Genomics C# API — tumor purity / ploidy (ASCAT-like), allele-specific copy number, mutational signatures (SBS96 + NMF/NNLS fitting), gene fusions, tumor mutational burden (TMB), microsatellite instability (MSI), neoantigen candidate peptides + MHC-binding classification, clonal / subclonal structure and tumor phylogeny, HRD / LOH, ctDNA / MRD. C#-API ONLY — there is NO MCP oncology server. Triggers: "estimate tumor purity / ploidy", "fit purity and ploidy (ASCAT)", "allele-specific copy number", "extract mutational signatures", "SBS96 catalog", "fit signature exposures", "call gene fusions", "is this fusion in-frame", "compute TMB", "TMB status", "MSI status / score", "predict neoantigens", "MHC-peptide binding", "classify clonal vs subclonal", "cancer cell fraction / CCF", "reconstruct tumor phylogeny", "HRD score", "LOH", "ctDNA fraction / tumor fraction", "MRD / minimal residual disease". (Germline SNP / indel calling → bio-annotation; germline read-evidence SV / C

Detect germline structural variants (SVs) and copy-number variants (CNVs) from sequencing read evidence with Seqeron (MCP tools OR the C# API). Use to flag discordant read pairs and split reads (breakpoint signatures), cluster them into SV candidates / breakpoints, assemble the breakpoint-junction sequence and find microhomology at it, segment copy-number probes and call CNVs (deletion / duplication), and genotype / filter / merge / gene-annotate SVs. Triggers: "find structural variants", "find discordant pairs / split reads", "cluster reads into SV candidates", "assemble the breakpoint", "microhomology at this junction", "call CNVs / segment copy number", "genotype this SV", "filter / merge / annotate SVs", "deletion / duplication / inversion / translocation from reads". (Tumor allele-specific copy number / ASCAT → seqeron-oncology; chromosome-arm-scale amplification / aneuploidy → bio-chromosome; SNP / indel calling → bio-annotation.) Server: annotation (all StructuralVariantAnalyzer.*).

Compare whole genomes / gene sets with Seqeron (MCP tools OR the C# API). Use to compute Average Nucleotide Identity (ANI / genome identity, ANIb species boundary ~0.95), detect orthologs and reciprocal best hits (RBH) between two genomes, find syntenic blocks (collinear runs of orthologous genes), detect whole-genome rearrangements (inversions / transpositions from the signed gene-order permutation), estimate reversal (inversion) distance, find conserved gene clusters (common intervals), generate a dot-plot of shared k-mers, and run the end-to-end genome-comparison pipeline (core/dispensable partition). Triggers: "compute ANI between these genomes", "how similar are these two genomes", "find orthologs / RBH between genome A and B", "syntenic blocks between these genomes", "detect rearrangements between gene orders", "reversal distance", "dot-plot of these two sequences", "conserved gene clusters", "compare these two genomes". Server: analysis (all ComparativeGenomics.*). Chromosome-scale synteny/SV → bio-chr

Analyze DNA methylation and chromatin state with Seqeron (MCP tools OR the C# API). Use to find CpG sites / CpG islands (Gardiner-Garden & Frommer) and CpG observed/expected ratio, classify CpG/CHG/CHH methylation contexts, call per-CpG methylation from bisulfite sequencing reads (Bismark-style) or forward-simulate bisulfite conversion, aggregate a weighted methylation profile, find differentially methylated regions (DMRs) between two samples (methylKit tiling windows + Fisher exact), estimate epigenetic age (Horvath DNA-methylation clock), predict chromatin state / annotate histone modifications (ChromHMM-style H3K4me3/H3K4me1/H3K27ac/H3K36me3/H3K27me3/H3K9me3), find accessible (ATAC-seq-like) chromatin regions, and predict imprinted genes from allele-specific methylation. Triggers: "find CpG islands", "CpG O/E ratio", "call methylation from bisulfite", "bisulfite-convert this sequence", "methylation profile", "find DMRs between groups", "hyper/hypomethylated regions", "epigenetic age / DNAm age / methylatio

Analyze RNA-seq / transcriptome expression matrices with Seqeron (MCP tools OR the C# API). Use to quantify expression (TPM / FPKM from counts + gene lengths), normalize a multi-sample expression matrix (quantile-normalize, log2-transform), run two-group differential expression (log2 fold change + t-test + BH-adjusted p), PCA / k-means clustering / Pearson correlation / co-expression networks of samples or genes, pathway over-representation (ORA) and GSEA-like enrichment, alternative & differential splicing (PSI / deltaPSI, skipped-exon events), isoform switching + dominant isoforms, and RNA-seq library QC metrics. Triggers: "compute TPM / FPKM", "differential expression between conditions", "PCA of these samples", "cluster genes by expression", "isoform switching", "differential splicing / PSI", "co-expression network", "quantile normalize / log2 transform expression", "RNA-seq QC metrics", "which pathways are enriched in my DE genes". Server: annotation (TranscriptomeAnalyzer.*).

Predict features of a PROTEIN sequence with Seqeron (MCP tools OR the C# API). Use for intrinsic disorder / IDRs (TOP-IDP) and MoRFs, signal-peptide prediction + cleavage site, transmembrane helices & membrane topology, coiled-coil regions, protein domains, PROSITE / common protein motifs, protein low-complexity (SEG) regions, and Kyte–Doolittle hydrophobicity profiles. Triggers: "predict disorder in this protein", "find the intrinsically disordered regions", "find the signal peptide / where is it cleaved", "transmembrane regions of this protein / membrane topology", "coiled-coil prediction", "what domains / PROSITE motifs are in this protein", "hydrophobicity plot", "is this residue disorder-promoting". Input is an AMINO-ACID sequence. Server: analysis.

Enforce scientific rigor whenever you compute or derive a biological result from real data with the Seqeron library — via MCP tools OR the C# API. Use whenever a task involves parsing FASTA/FASTQ/GenBank/GFF/VCF/BED, computing GC%, Tm, distances, k-mers, alignments, variant calls, primers/CRISPR, phylogeny, or popgen metrics, or when asked "is this result reliable/valid?". Enforces tool-only computation (no manual parsing or mental math), a validated operating envelope (LimitationPolicy / LIMITATIONS.md), a provenance chain, cross-checking, unit/coordinate checks, and the alpha / not-for-clinical-use disclaimer.

Use the Seqeron.Genomics C# API directly (not via MCP) with the library's real conventions and guardrails. Triggers — "call Seqeron from C#", "write code using Seqeron.Genomics", "use the Seqeron library / API in code", "why does this throw LimitationPolicy / SeqeronLimitationException", "how do I set the limitation mode", "TryCreate vs the DnaSequence constructor", "bootstrap the policy in a test", "which C# method backs this MCP tool / Method ID", "guarded unit / MinimumMode in code". Developer-profile counterpart to bio-rigor: the CODE mechanics of construction, the 3-tier LimitationPolicy, the guarded-unit exception, and mapping MCP Method IDs to real calls.

Align biological sequences and quantify how similar they are with Seqeron (MCP tools OR the C# API). Use for pairwise alignment (global/Needleman-Wunsch, local/Smith-Waterman, semi-global/fitting/overlap), multiple sequence alignment (MSA) + consensus/conservation, percent identity / similarity / gap %, edit (Levenshtein) and Hamming distance, k-mer similarity, longest common region, approximate matching, and prompts like "align these sequences", "how similar are X and Y", "find the conserved region", "does this query fit in that reference". Servers: alignment + core.

Profile and compare microbial communities with Seqeron (MCP tools OR the C# API). Use for taxonomic classification of reads/contigs (Kraken k-mer/LCA), community/abundance profiling, alpha diversity (Shannon, Simpson, inverse Simpson, Chao1, Pielou evenness), beta diversity between samples (Bray-Curtis, Jaccard), differential abundance, metagenomic binning into MAGs + completeness/ contamination, functional prediction, antibiotic-resistance gene detection, and pan-genome analysis (core/accessory, Heaps' law, phylogenetic markers). Triggers: "classify these reads", "what's the community composition", "profile this metagenome", "compute Shannon/Simpson diversity", "compare these two samples", "bin these contigs", "build a pan-genome". Server: metagenomics.

Parse and QC biological sequences and files with Seqeron (MCP tools OR the C# API). Use to parse/validate FASTA, FASTQ, GenBank, GFF, VCF, BED, EMBL; validate DNA/RNA/protein; compute sequence composition (GC%, base/AA counts, Tm/melting temperature, molecular weight, hydrophobicity, pI); measure complexity/entropy (Shannon, DUST, linguistic, k-mer, compression); FASTQ quality stats (Q20/Q30, mean quality, encoding); and transcribe / translate / reverse-complement. Prompts like "parse this file", "extract features from GenBank/GFF", "validate this sequence", "GC content of…", "is this valid DNA/RNA/protein", "quality stats for this FASTQ", "translate this ORF", "reverse complement", "mask low-complexity". Servers: sequence + parsers.