Coding & Dev Tools

gptomics Bundle

Detects and removes contamination in genome assemblies via two disjoint workflows - foreign-sequence screening of a single-organism (eukaryote/isolate) assembly with NCBI FCS-GX (GenBank-submission-mandatory), FCS-adaptor, and BlobToolKit blob plots; and MAG/bin quality assessment with CheckM2 plus GUNC (chimerism) plus GTDB-Tk taxonomy, judged against MIMAG. Covers why CheckM2 alone is blind to disjoint-marker chimeras, the FCS-GX RAM wall, organelle/NUMT triage, strain heterogeneity, and the HGT-vs-contamination (tardigrade) trap. Use when screening an assembly for foreign contamination before GenBank submission, assessing MAG completeness/contamination/chimerism, deciding which contigs to remove, or distinguishing real HGT from contaminant contigs.

gptomics Bundle

Designs pegRNAs and nicking guides for prime editing (PE) -- choosing the nick/strand, tuning the primer-binding site (PBS) and reverse-transcription template (RTT) as a per-locus panel, selecting the PE system (PE2/PE3/PE3b/PE4/PE5/PEmax/PE7), adding MMR-evading and PAM-disrupting silent edits, appending epegRNA 3' motifs (tevopreQ1/mpknot), and ranking with PRIDICT/DeepPrime. Covers twinPE/PASTE for large insertions and the prime-vs-base-editing decision. Use when designing a scarless point mutation, small insertion/deletion, or any of the 12 base conversions without a double-strand break, when efficiency is low and MMR inhibition or pegRNA stabilization is needed, or when routing a large insertion to an integrase method. Generic guide scoring and base editing are separate skills.

gptomics Bundle

Quantify transcript expression from FASTQ with Salmon (selective alignment) or kallisto (pseudoalignment), bypassing genome mapping. Use when quantifying RNA-seq without alignment, deciding whether a decoy-aware index is required, detecting and verifying library strandedness, enabling GC and sequence bias correction, or choosing whether to generate inferential replicates (bootstraps/Gibbs) for transcript-level downstream testing.

sboghossian-mini-claude-for-legal Skill

Use when a user expresses interest in working at HAQQ/Louis, asks about open positions, wants to submit a CV, or inquires about internships. Routes the conversation to the careers portal or appropriate contact, captures role interest and background context, and maintains the HAQQ brand voice for talent interactions. Distinct from the A2J legal aid routing and commercial sales flows — this is a talent acquisition intent.

sboghossian-mini-claude-for-legal Skill

Use when a user (non-lawyer) describes a criminal matter — charges, arrest, detention, police investigation, bail, or criminal complaint. Immediately surfaces the criminal-defense disclaimer directing them to qualified criminal counsel, provides general procedural information only, and hard-refuses specific defense-strategy advice (what to tell police, whether to confess, pleading strategy). Switches to professional B2B mode for lawyer users handling criminal matters. Routes to emergency resources for minors or vulnerable persons.

sboghossian-mini-claude-for-legal Skill

Use when surfacing a relevant use case or success story to a user who is exploring the platform, approaching an upgrade decision, or showing signs of disengagement. Selects and presents a case study matched to the user's detected persona (role, industry, jurisdiction) to demonstrate concrete value and reduce hesitation. Invoked at empty-state moments and before upgrade prompts to show social proof specific to the user's context.

autohandai-community-skills Bundle

Uses Rekall memory forensics framework to analyze memory dumps for process hollowing, injected code via VAD anomalies, hidden processes, and rootkit detection. Applies plugins like pslist, psscan, vadinfo, malfind, and dlllist to extract forensic artifacts from Windows memory images. Use during incident response memory analysis.

autohandai-community-skills Bundle

Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive allocation.

autohandai-community-skills Bundle

Execute a structured ransomware incident response including containment, decryption assessment, recovery from backups, and eradication of ransomware persistence mechanisms.

sboghossian-mini-claude-for-legal Skill

Use when the public-facing assistant detects that a user is exploring a strategic partnership with HAQQ — bar association programs, law firm preferred-vendor agreements, technology integrations, white-label/reseller arrangements, academic partnerships, or marketplace listings. Routes to the partnership page, identifies the partnership type, captures lead details, and engages the partnerships team. Covers all jurisdictions.

sboghossian-mini-claude-for-legal Skill

Use when a matter involves marriage, divorce, property division, custody, or inheritance for non-Muslim residents of the UAE under Federal Decree-Law 41/2022 (the UAE Civil Personal Status Law) or the DIFC Wills Service Centre. Covers no-fault divorce, joint-custody default, equal-property division, testamentary freedom for non-Muslims, pre-nuptial agreement enforceability, and the parallel DIFC/ADGM wills regimes. Contrasts with the UAE Personal Status Law 28/2005 (Sharia-based) which governs Muslim residents. Triggers on non-Muslim divorce UAE, UAE civil marriage, DIFC wills, UAE prenup, or expat family law UAE questions.

sboghossian-mini-claude-for-legal Skill

Use when a copywriter, marketer, or product manager needs to make a specific, measurable outcome claim in customer-facing copy for a legal AI assistant — such as time saved, accuracy rates, or productivity improvements — and needs to know the exact conditions under which such claims are permitted. Covers required evidence standards, disclaimer language, and how to frame quantitative claims for consumer and professional audiences without creating consumer protection or bar advertising liability.

gptomics Bundle

Maps TCR/BCR receptor sequences toward candidate antigen specificity and clusters repertoires by shared-specificity signal, while enforcing that a database match or a cluster label is a HYPOTHESIS, not a specificity call. Use when deciding among database annotation (VDJdb/McPAS/IEDB+TCRMatch, requiring V-gene and HLA concordance plus a confidence score) versus sequence clustering (tcrdist3 meta-clonotypes, GLIPH2, GIANA, clusTCR, which find enrichment not per-receptor labels) versus generation-probability nulls (OLGA Pgen, IGoR, SONIA Ppost) for testing public/convergent/shared claims; and when guarding against overclaiming specificity, base-rate false positives from bare CDR3 matches, unpaired beta-only annotation, ML predictor failure on unseen epitopes, and ignored MHC restriction. TCR-focused with a BCR/antibody note (SHM, conformational epitopes, IGHV3-53/3-66 public clonotypes). Keywords CDR3, pMHC, HLA restriction, cross-reactivity, meta-clonotype, Pgen, public clonotype, convergent recombination.

gptomics Bundle

Discovers a periodic signal of UNKNOWN period in time-series omics data and puts a defensible significance on it, especially when sampling is IRREGULAR (dropped timepoints, pooled harvests) so FFT/Welch/JTK are invalid. Estimates the dominant period with Lomb-Scargle / generalized Lomb-Scargle (scipy, astropy), corroborates with autocorrelation, resolves transient/time-varying periodicity with the wavelet CWT (pywt), and screens genome-wide with false-alarm probabilities under BH FDR. Use when finding an oscillation whose period is not known a priori, analyzing cell-cycle or ultradian rhythms, or handling unevenly sampled time courses. Not for testing a KNOWN 24-hour rhythm (see temporal-genomics/circadian-rhythms).

gptomics Bundle

Classify variant clinical significance with the ACMG/AMP germline framework and its 2018-2025 ClinGen refinements (graded PVS1 decision tree, PM2 downgraded to Supporting, PP5/BP6 retired, calibrated PP3/BP4, Bayesian points), the AMP/ASCO/CAP somatic tiers and ClinGen oncogenicity system, ClinVar star-rating and gnomAD grpmax filtering-AF interpretation. Use when deciding germline-vs-somatic framework, applying current (not flat-2015) ACMG points, checking for a gene-specific VCEP specification, judging whether a ClinVar assertion or gnomAD frequency is usable evidence, calibrating a pathogenicity predictor, evaluating PVS1 on the MANE Select transcript, or building a VUS reanalysis loop. Not for functional annotation itself (see variant-calling/variant-annotation).

gptomics Bundle

Tests associations between categorical variables in clinical data using chi-square, Fisher's exact, Boschloo, Cochran-Mantel-Haenszel, and modern McNemar variants with calibrated confidence intervals (Wilson, Newcombe, Miettinen-Nurminen). Use when analyzing categorical outcomes, paired binary endpoints, or testing treatment-outcome independence in confirmatory or exploratory clinical trials.

gptomics Bundle

Performs subgroup and heterogeneous treatment effect (HTE) analyses for clinical trials. Covers Mantel-Haenszel pooling, Breslow-Day, interaction tests in regression, RERI for additive interaction, modern data-adaptive HTE methods (STEPP, SIDES, causal forests, X/R-learners), Bayesian shrinkage (Dixon-Simon, MAP, EXNEX), graphical multiplicity (Bretz-Maurer), and credibility frameworks (Sun BMJ, EMA 2019). Use when analyzing treatment effects across patient subgroups for regulatory submissions or precision-medicine claims.

gptomics Bundle

Performs time-to-event analysis for clinical trials including Cox proportional hazards regression with PH diagnostics, restricted mean survival time (RMST) under non-PH, competing risks via Fine-Gray vs cause-specific Cox, weighted log-rank and MaxCombo for non-proportional hazards, recurrent events (Andersen-Gill, PWP, WLW), and interval-censored data. Use when analyzing time-to-event endpoints (OS, PFS, DOR, TTR, TTNT) in oncology or other clinical trials.

gptomics Bundle

Handles batch effects in bulk RNA-seq via design-matrix inclusion (the correct path for DE), ComBat/ComBat-seq for visualization, SVA for unknown latent factors, RUVSeq for negative-control-gene-anchored unwanted variation, and limma::removeBatchEffect for plotting only. Encodes the Nygaard 2016 cardinal sin against testing on a batch-corrected matrix, the choice between SVA/RUVg/RUVs/RUVr, the confounding non-identifiability problem, the single-cell boundary (Harmony/MNN are NOT for bulk), and the Goh 2017 harmonization critique. Use when designing a DE analysis with batch structure, troubleshooting batch-dominated PCA, choosing ComBat vs ComBat-seq, handling unknown batch via SVA, integrating across studies, or deciding when (rarely) to subtract batch.

gptomics Bundle

Delimits putative species boundaries from molecular data within the de Queiroz 2007 unified-lineage framework using ASAP (Puillandre 2021 successor to ABGD), mPTP C++ (Kapli 2017 successor to bPTP; bPTP is Python NOT R), GMYC single/multi-threshold (Pons 2006; Fujisawa 2013), multilocus BPP v4 with prior calibration from data (NOT defaults; Yang 2015), SNAPP + BFD* for SNP delimitation, DELINEATE (Sukumaran 2021) speciation-process modeling to address Sukumaran & Knowles 2017 PNAS critique that MSC delimits structure not species, integrative-taxonomy congruence (Padial 2010; Carstens 2013), Dsuite for introgression testing before sister claims (Malinsky 2021), and Meyer & Paulay 2005 barcoding-gap-absence caveat. Use when delineating species from DNA barcoding data, resolving cryptic complexes, choosing among ASAP/mPTP/BPP/DELINEATE, calibrating BPP priors, distinguishing introgression from ILS, or applying the Sukumaran-Knowles oversplitting correction.

gptomics Bundle

Assigns isolate identity at the right resolution for the question -- ANI/Mash species triage, 7-locus MLST historical comparability, cgMLST/wgMLST outbreak resolution (chewBBACA, BIGSdb, Ridom SeqSphere, EnteroBase HierCC), in-silico serotyping (SISTR/SeqSero2 Salmonella, SerotypeFinder E. coli, Kaptive Klebsiella, SeroBA pneumococcus, spa+SCCmec S. aureus), and lineage callers (TB-Profiler/Mykrobe barcode for MTBC, Pangolin + Nextclade for SARS-CoV-2, PopPUNK GPSC for S. pneumoniae). Use when typing bacterial isolates for surveillance or outbreak investigation, choosing between cgMLST allele distance and core-SNP distance for cluster definition, harmonising calls across schemas/database versions, assigning MTBC lineage with the Napier 90-SNP barcode, calling Salmonella serovar via SISTR with monophasic Typhimurium awareness, running Pangolin UShER mode with pangolin-data version pinning, or selecting a typing resolution to match the surveillance question.

autohandai-community-skills Bundle

Parse NetFlow v9 and IPFIX records to detect volumetric anomalies, port scanning, data exfiltration, and C2 beaconing patterns. Uses the Python netflow library to decode flow records, builds traffic baselines, and applies statistical analysis to identify flows with abnormal byte counts, connection durations, and periodic timing patterns.

autohandai-community-skills Bundle

Investigate supply chain attack artifacts including trojanized software updates, compromised build pipelines, and sideloaded dependencies to identify intrusion vectors and scope of compromise.

autohandai-community-skills Bundle

Detect process injection techniques (T1055) including CreateRemoteThread, process hollowing, and DLL injection via Sysmon Event IDs 8 and 10 and EDR process telemetry

autohandai-community-skills Bundle

Detect MITRE ATT&CK T1547.001 registry Run key persistence by analyzing Sysmon Event ID 13 logs and registry queries to identify malicious auto-start entries.

autohandai-community-skills Bundle

Configure Fluentd and Fluent Bit for centralized log aggregation, routing, filtering, and enrichment across distributed infrastructure

autohandai-community-skills Bundle

PCI DSS 4.0.1 establishes 12 requirements across 6 control objectives for organizations that store, process, or transmit cardholder data. With PCI DSS 3.2.1 retiring April 2024 and 51 new requirements

gptomics Bundle

Annotates bacterial and archaeal genomes (isolates, MAGs, plasmids) with Bakta (active versioned databases, NCBI-compliant output) or Prokka (legacy), producing GFF3/GenBank/EMBL/FASTA with INSDC locus tags. Covers Bakta-vs-Prokka-vs-PGAP-vs-DFAST choice, light-vs-full database tiers, translation-table selection (11/4/25), archaeal and leaderless-gene caveats, the small-ORF blind spot, pseudogene-vs-phase-variation, the pangenome re-annotation trap, and submission compliance. Use when annotating a newly assembled prokaryotic genome, choosing an annotation tool, re-annotating a collection for pangenomics, or preparing annotations for NCBI/DDBJ submission.

gptomics Bundle

Predict peptide-MHC class I binding and natural presentation with MHCflurry, NetMHCpan-4.1, and MixMHCpred to nominate candidate CD8 T-cell epitopes. Covers the binding-affinity (BA) vs eluted-ligand (EL/presentation) distinction, why %Rank beats raw nM for cross-allele work, the MS abundance bias that misranks low-expression neoantigens, allele-coverage inequity, and length bias. Use when scanning a protein or peptide set for class I epitopes, scoring neoantigen candidates, or choosing a binding predictor. For CD4/HLA class II see mhc-class-ii-prediction.

gptomics Bundle

Build restriction maps showing enzyme cut positions and inter-site distances along DNA using Biopython Bio.Restriction. Produces text or graphical maps for linear and circular molecules, orders sites from single and double digests, and overlays GenBank features. Use when creating a restriction map of a sequence, ordering cut sites along a plasmid, or relating sites to annotated features.

gptomics Bundle

Generate reverse complements and complements of DNA/RNA sequences using Biopython, including IUPAC ambiguity codes, gapped alignments, and minus-strand features. Use when working with the opposite strand, building reverse primers, normalizing strand orientation before alignment, or extracting a coding sequence from a minus-strand feature.

sboghossian-mini-claude-for-legal Skill

Use when assessing whether a contract's liability cap is reasonable given the deal type, contract value, risk profile, and applicable jurisdiction. Covers cap structure analysis, common carve-outs, anti-patterns, and jurisdiction-specific enforceability rules. Produces a rated assessment with recommended position (ideal / acceptable / walk-away) calibrated against market norms for the contract type.

sboghossian-mini-claude-for-legal Skill

Use when drafting a press release for HAQQ Legal AI / Louis — product launches, funding announcements, partnership news, new market entries, or executive appointments. This skill defines the AP-style press release format, tone rules, headline standards, quote conventions, boilerplate language, and MENA-specific distribution considerations.

sboghossian-mini-claude-for-legal Skill

Use when an attorney needs to build and rehearse a cross-examination of a witness — identifying prior inconsistent statements, generating leading-question sequences, mapping impeachment opportunities, and preparing for non-cooperative witnesses. Louis plays the witness in cooperative, hostile, or evasive modes with realistic memory failures and lawyer-coached cleanups. Produces a cross outline, impeachment files, and a scoring rubric. Applies across DIFC, ADGM, UAE civil, Lebanese, KSA, and international arbitration forums.

sboghossian-mini-claude-for-legal Skill

Use as a post-draft quality check on any multi-party legal document. Enforces consistent use of party names and defined terms throughout a document and across schedules — correct introduction in the parties block, single consistent short-form, consistent capitalization, and cross-document alignment. Party name inconsistencies are a common drafting error that creates ambiguity, undermines enforceability, and signals low-quality drafting to opposing counsel.

sboghossian-mini-claude-for-legal Skill

Use when the public-facing assistant detects that a user wants to see Louis in action — requesting a demo, walkthrough, or trial experience. Delivers a structured in-chat demo flow, routes to the demo page, schedules a live demo via Calendly, and tailors the demo to the user's context or the feature page they arrived from. Covers all jurisdictions; triggers sales lead capture for high-intent users.