Coding & Dev Tools

sboghossian-mini-claude-for-legal Skill

Use when computing statutory or contractual interest on overdue payments, debt claims, or court-awarded sums across MENA and European jurisdictions. Covers Lebanon (Art 766 OCC), UAE (Federal Law 18/1993, 9%/12%), KSA (Sharia-compliant profit-margin approach), France (arrêté bi-annual rate), UK (Late Payment Act 1998, base+8%), and EU (Directive 2011/7/EU). Returns principal, period, rate, computation method, total interest, and jurisdiction-specific warnings.

sboghossian-mini-claude-for-legal Skill

Use when computing legal deadlines — filing deadlines, response periods, statutes of limitations, contractual notice periods — with full awareness of jurisdiction-specific court rules, public holidays (including Eid al-Fitr and Eid al-Adha with variable lunar dates), court vacation periods, and weekend conventions (Friday-Saturday in pre-2013 KSA; Saturday-Sunday in UAE and most GCC). Returns the due date, intermediate milestones, and a list of holidays handled.

sboghossian-mini-claude-for-legal Skill

Use when a user asks what the Clause Library contains, how to find a specific clause, how to compare clause variants across jurisdictions or negotiating positions, or how the clause library differs from the document template library. Covers vetted contractual clauses organized by jurisdiction, language (AR/EN/FR), position (seller/buyer/neutral), and risk tier, with side-by-side comparison and drafting notes. Triggers on queries for standard DIFC/ADGM/KSA/UAE/Lebanese clauses, Arabic-version clause requests, or "show me alternatives" moments.

sboghossian-mini-claude-for-legal Skill

Use when a legal document must be drafted in both Arabic and English with parallel clause numbering and a controlling-language declaration. Governs layout choices (two-column table vs sequential), the RTL/LTR rendering rules, controlling-language conventions by jurisdiction (Arabic controls onshore in UAE/KSA/LB; English controls in DIFC/ADGM if stated), defined-term consistency, numeral and currency formatting, and translation quality standards for legal-register Arabic.

sboghossian-mini-claude-for-legal Skill

Use when writing, deploying, or debugging Supabase Edge Functions (Deno runtime) for the legal AI backend. Covers authentication patterns, CORS configuration, structured error handling, JWT validation, calling external APIs (Anthropic, PostHog), and patterns specific to multi-tenant legal AI workloads.

autohandai-community-skills Bundle

Create GitHub pull requests that follow the NemoClaw PR template. Use when the user wants to create a new PR, submit code for review, open a pull request, or push changes for review. Trigger keywords - create PR, pull request, new PR, submit for review, open PR, push for review.

autohandai-community-skills Bundle

Execute web cache deception attacks by exploiting path normalization discrepancies between CDN caching layers and origin servers to cache and retrieve sensitive authenticated content.

autohandai-community-skills Bundle

Parse Windows Prefetch files using the windowsprefetch Python library to reconstruct application execution history, detect renamed or masquerading binaries, and identify suspicious program execution patterns.

sboghossian-mini-claude-for-legal Skill

Use when performing KYC, due diligence, or counterparty verification for a Saudi Arabian entity. Queries the KSA Ministry of Commerce (MOC) commercial registration (Sijil Tijari) database to retrieve entity name, activities, authorized signatories, corporate form, and share encumbrances. Essential before signing any commercial contract with a Saudi party or conducting KYC under Saudi AML frameworks.

sboghossian-mini-claude-for-legal Skill

Use when performing KYC, counterparty verification, or due diligence on a UAE mainland company. Queries the Department of Economic Development (DED) trade license database of the relevant emirate to verify entity name, license type, expiry, permitted activities, shareholders, and authorized signatories. Critical before signing any commercial contract with a UAE onshore entity. Note that DIFC, ADGM, and free zone companies have separate registers — this tool covers mainland only.

sboghossian-mini-claude-for-legal Skill

Use when a user asks about software testing methodologies, quality assurance for legal-tech products, AI evaluation frameworks, hallucination detection, or how to test legal AI outputs. Provides a reference on the full spectrum of software testing — unit through chaos — with specific coverage of AI-specific evaluation techniques including eval suites, hallucination tests, and output drift detection applicable to legal AI systems.

sboghossian-mini-claude-for-legal Skill

Use when drafting a prenuptial (premarital) agreement governing property division and financial obligations before marriage. Covers jurisdictional recognition rules (strong in DIFC, ADGM, UK, France; variable in LB by confession; Sharia-constrained in KSA; expanded for non-Muslims in UAE under Federal Law 41/2022), recommended content, procedural enforceability requirements (full disclosure, independent counsel, voluntariness, notarization), and what a prenup cannot override (child support, Sharia inheritance). Triggers on "prenup", "prenuptial", "premarital agreement", "contrat de mariage", or "marriage settlement" requests.

sboghossian-mini-claude-for-legal Skill

Use when the platform needs to surface a personalized blog and content RSS feed for a Louis user. Aggregates legal blog posts, thought-leadership articles, and practice-relevant content from selected MENA and global legal publishers, filtered by user role, practice area, and jurisdiction preferences. Pairs with churn-risk signals to prioritize re-engagement content.

gptomics Bundle

Phases small variants, SVs, and methylation from Oxford Nanopore and PacBio long reads (read-backed/physical phasing) with WhatsHap, LongPhase, or HiPhase, and haplotags the BAM (HP/PS tags) for allele-resolved downstream analysis. Covers why phase blocks break at het-sparse gaps (read length x heterozygosity), why phasing the VCF is useless until the BAM is haplotagged, the GT-pipe/PS and read HP/PS tag spec, reporting block N50 with switch error, the diploid-assumption/CNV/haploid-region traps, trio phasing as the gold standard, and the boundary to statistical panel phasing. Use when phasing long-read variants, haplotagging reads for allele-specific methylation/expression or phased SVs, choosing WhatsHap vs LongPhase vs HiPhase, trio phasing, or assessing phasing quality.

gptomics Bundle

Aligns bisulfite-converted (WGBS, RRBS, PBAT) and enzymatic (EM-seq) short reads to an in-silico C->T/G->A-converted reference with Bismark (Bowtie2 or HISAT2), preparing the genome index, choosing the directional vs non-directional vs PBAT strand flag, deduplicating WGBS/EM-seq (never RRBS), and bounding bisulfite conversion efficiency with unmethylated lambda and methylated pUC19 spike-ins. Covers why the library protocol (not the aligner) decides whether calls are meaningful, why incomplete conversion masquerades as methylation, the 3-letter reduced-complexity mapping bias (50-70% efficiency is normal), and M-bias end-clipping. Use when aligning bisulfite or EM-seq reads, preparing a bisulfite genome, choosing the strand flag, or diagnosing low mapping efficiency. For methylation extraction see methylation-calling; for long-read MM/ML modification calling see long-read-sequencing/nanopore-methylation.

gptomics Bundle

Predict restriction digest fragment sizes and gel patterns using Biopython Bio.Restriction. Computes fragment lengths and sequences for single and double digests on linear or circular DNA, and interprets them against an agarose gel. Use when predicting the fragments from a digest, planning a diagnostic digest to verify a clone, or matching observed gel bands to an expected pattern.

gptomics Bundle

Find restriction enzyme cut sites in DNA sequences using Biopython Bio.Restriction. Searches single enzymes, batches, or commercial enzyme sets and returns cut positions for linear or circular DNA. Use when locating where one or more restriction enzymes cut a sequence, screening a sequence for the presence or absence of a site, or counting how often an enzyme cuts.

gptomics Bundle

Slice, extract, and concatenate biological sequences and annotated records using Biopython. Use when extracting subsequences by position, splicing exons into a transcript, joining sequences, or carrying a sub-region of an annotated record (with quality scores and features) into a new record.

gptomics Bundle

Segments cells/nuclei and extracts image features from imaging spatial transcriptomics (Xenium, MERFISH/MERSCOPE, CosMx) and H&E/IF tissue images using Cellpose, StarDist, Baysor, and Squidpy. Use when choosing a segmentation strategy (DAPI nucleus + expansion vs membrane-stain whole-cell vs transcript-aware Baysor/proseg vs segmentation-free SSAM) given the available stain; judging whether transcript spillover is fabricating false co-expression and short-range cell-cell signal; and deciding whether the derived cell-by-gene matrix is trustworthy before downstream typing, DE, or ligand-receptor analysis.

gptomics Bundle

Reconstructs B-cell clonal families, quantifies somatic hypermutation and selection, and builds antibody lineage trees with the Immcantation R suite (alakazam, shazam, scoper, dowser, tigger) on AIRR-format BCR data. Use when deriving the clonal-clustering threshold from the distToNearest bimodal valley (never a hardcoded 0.15); choosing hierarchicalClones vs spectralClones (vj vs novj) for SHM-diverged repertoires; personalizing the germline with TIGGER before mutation counting; reconstructing D-masked germlines with createGermlines; measuring R/S mutation frequency by CDR and FWR region; testing antigen-driven selection with BASELINe; comparing Hill-number diversity at equal sampling depth; and inferring IgPhyML lineage trees for affinity maturation, class-switch, and ancestral-antibody analysis.

gptomics Bundle

Test whether two or more traits share a causal variant at a locus using Bayesian colocalization (coloc.abf, coloc.susie, HyPrColoc, moloc, eCAVIAR, SMR/HEIDI, PWCoCo, SharePro). Use when integrating GWAS with eQTL/sQTL/pQTL/mQTL, distinguishing shared causal variants from LD-driven coincidence, handling allelic heterogeneity, choosing between single-causal vs multi-causal methods, picking PP.H4 thresholds, running sensitivity over p12, or harmonising summary statistics for colocalization.

gptomics Bundle

Estimate causal effects of an exposure on an outcome from GWAS summary statistics using genetic instruments. Implements IVW (fixed/random), MR-Egger, weighted median/mode, MR-RAPS, CAUSE, GSMR-HEIDI, MR-PRESSO, MVMR, MR-Clust, LCV, and LHC-MR via TwoSampleMR, MendelianRandomization, MR-PRESSO, cause, and lhcMR. Use when testing causal direction between traits, evaluating drug-target effects via cis-pQTL/cis-eQTL, performing multivariable mediation MR, distinguishing causation from correlated horizontal pleiotropy, or producing STROBE-MR-compliant sensitivity batteries.

gptomics Bundle

Runs cis-pQTL Mendelian randomization for drug-target validation using UKB-PPP (Olink), deCODE (SomaScan), Fenland, INTERVAL, ARIC, and FinnGen-PPP proteomes plus colocalization triangulation, phenome-wide on-target adverse-effect scans, cross-platform Olink/SomaScan replication, and PAV (protein-altering variant) sensitivity. Use when nominating or de-risking a drug target from plasma-proteome GWAS, mimicking pharmacological inhibition via cis-pQTL instruments, separating shared-causal from LD-confounded signal under the Schmidt 2020 cis-MR framework, screening on-target adverse phenotypes pheWAS-style, or producing publication-grade STROBE-MR plus PP.H4 evidence for a target gene.

gptomics Bundle

Designs adaptive clinical trials including group-sequential (O'Brien-Fleming, Pocock, Lan-DeMets spending), sample-size re-estimation (blinded Friede-Kieser, unblinded Cui-Hung-Wang, Mehta-Pocock promising zone), seamless Phase 2/3 with treatment-arm selection, population enrichment, and response-adaptive randomisation. Covers FDA 2019 Final Adaptive Designs Guidance, FDA 2022 Master Protocols, and ICH E20 Step 2b/3 draft (June 2025, NOT final). Use when planning interim analyses, sample-size re-estimation, or master/platform-trial designs.

autohandai-community-skills Bundle

Perform Kerberoasting attacks using Impacket's GetUserSPNs to extract and crack Kerberos TGS tickets for Active Directory service accounts.

autohandai-community-skills Bundle

Detect domain fronting C2 traffic by analyzing SNI vs HTTP Host header mismatches in proxy logs and TLS certificate discrepancies using pyOpenSSL for certificate inspection

autohandai-community-skills Bundle

Detect T1547.001 startup folder persistence by monitoring Windows startup directories for suspicious file creation, analyzing autoruns entries, and using Python watchdog for real-time filesystem monitoring.

sboghossian-mini-claude-for-legal Skill

Use when a user submits images, audio, or video as litigation evidence and asks whether it is authentic, or when a legal team needs to assess the integrity of digital media before relying on it in proceedings. Flags media for forensic review using metadata analysis, visual/audio anomaly heuristics, and reverse-image techniques — but never asserts authenticity or inauthenticity definitively. Maps court admissibility frameworks (US FRE 901/Daubert, UK Civil Evidence Act, DIFC/ADGM, MENA civil-law expert appointment) and routes to certified digital forensic examiners.

sboghossian-mini-claude-for-legal Skill

Use when sizing the MENA legal services and legal AI market for investor materials, product prioritisation, or market-entry decisions. Covers total addressable market by country and sub-segment, competitive density by tier, and Louis's targeted share thesis. Internal use only.

sboghossian-mini-claude-for-legal Skill

Use when signals indicate the user is in evaluation mode — researching the platform, asking broad capability questions, or making competitor comparisons — rather than doing active legal work. This skill governs how to detect evaluation behavior and what supporting content (whitepapers, comparison guides, case studies) to surface in response, with the goal of converting an evaluator into an active user or buyer.

sboghossian-mini-claude-for-legal Skill

Use when a lawyer needs to retrieve and instantiate a firm-branded document template — populated with firm identity, approved standard clauses, and jurisdiction-specific disclosures — as the starting point for a new draft. The skill connects to the internal KB, applies the firm's visual and language standards, and prevents lawyers from drafting from blank or using unapproved external templates. Part of the eFirm firm-management product suite.

autohandai-community-skills Bundle

Identify ransomware network indicators including C2 beaconing patterns, TOR exit node connections, data exfiltration flows, and encryption key exchange via Zeek conn.log and NetFlow analysis

gptomics Bundle

Infer integer allele-specific copy number, tumor purity, and ploidy from tumor sequencing by jointly modeling read depth (logR) and B-allele frequency (BAF) with ASCAT, Sequenza, FACETS, PURPLE, and PureCN (tumor-only). Covers the purity-ploidy identifiability problem, the diploid-baseline (dipLogR) anchor, major/minor copy number, loss of heterozygosity, sunrise/contour fit diagnostics, and reconciliation of conflicting fits. Use when tumor analysis needs absolute copy number rather than relative log2, when estimating purity and ploidy, calling LOH or copy-neutral LOH, resolving whole-genome doubling, running tumor-only allele-specific calling, or choosing among ASCAT, Sequenza, FACETS, and PureCN.

gptomics Bundle

Classify constitutional (germline) copy number variants for clinical reporting using the 2019 ACMG/ClinGen technical standards points-based framework, with ClassifyCNV and AnnotSV for semi-automated scoring. Covers the separate copy-number-loss and copy-number-gain rubrics, the five-tier classification, ClinGen haploinsufficiency/triplosensitivity and dosage-sensitive regions, de novo and segregation evidence, and population-frequency benign evidence. Use when assigning pathogenic/likely-pathogenic/VUS/likely-benign/benign to a constitutional CNV, scoring a CNV against ACMG/ClinGen criteria, or distinguishing the automatable evidence from the case-specific evidence requiring manual input.

gptomics Bundle

Build volcano and MA plots from differential-expression / association results with LFC shrinkage, FDR-adjusted thresholds, sensible label placement, and axis-truncation conventions. Covers EnhancedVolcano, ggplot2, matplotlib, and the apeglm/ashr/normal shrinkage decision. Use when visualizing differential-expression results (RNA-seq, ChIP-seq, ATAC-seq, proteomics) or any per-feature effect-size + p-value table.

gptomics Bundle

Assigns GO terms, Pfam/InterPro domains, KEGG orthologs, EC numbers, and product names to predicted proteins using eggNOG-mapper (orthology), InterProScan (domain signatures), and KofamScan (KEGG), routing specialized functions to dbCAN/antiSMASH/AMRFinderPlus/SignalP. Covers the orthology-vs-domain-vs-homology paradigms, the annotation-error percolation cascade, domain-presence-is-not-function, GO IEA circularity in enrichment, evidence tiering, and bit-score/coverage thresholds. Use when adding functional annotation to predicted genes, choosing between eggNOG-mapper and InterProScan, or judging how much to trust a functional label.