AI & ML

sboghossian-mini-claude-for-legal Skill

Use when migrating a Data Protection Impact Assessment (DPIA) sentinel skill into the mini-claude-for-legal format. The adapter maps legacy DPIA screening logic — risk thresholds, processing-activity categories, necessity/proportionality tests, and supervisory-authority notification triggers — into the standard skill model. Relevant across EU GDPR, UK GDPR, UAE PDPL, and Lebanon data-protection contexts.

sboghossian-mini-claude-for-legal Skill

Use when dealing with arbitration clauses or proceedings under the former DIFC-LCIA Arbitration Centre, which operated from 2008 until its dissolution under Dubai Decree 34/2021. Covers legacy cases pending under DIFC-LCIA Rules, transition to DIAC, and the distinct features of the DIFC-LCIA model (LCIA-based procedural rules combined with DIFC seat and DIFC Courts supervision). Relevant to any contract signed before 2022 containing a DIFC-LCIA clause.

sboghossian-mini-claude-for-legal Skill

Internal architectural principle establishing that Louis accesses current legal data — sanctions lists, company registries, official gazettes, court databases — through live MCP-style connectors rather than relying on frozen training data. Use when designing data connectors, evaluating the currency of regulatory information, or understanding why certain legal data sources must be queried in real time.

sboghossian-mini-claude-for-legal Skill

Use as a reference guide for processing legal documents that exceed approximately 50 pages — the point at which direct full-text prompting becomes inefficient or exceeds context window limits. Covers chunked processing, outline-first strategies, targeted section analysis, vector embedding for semantic search, and tool-call patterns for agent-based document navigation. Applies to due diligence packages, M&A data rooms, long-form contracts, regulatory filings, and litigation bundles.

gptomics Bundle

Designs and analyzes in vivo CRISPR screens in animal tumor models, organoids, and immune-cell adoptive transfers. Covers bottleneck math (250x cells/sgRNA requires ~25M cells implanted; impossible for most syngeneic models, forcing focused libraries), focused library design (Manguso 2017 Nature 547:413 immune screen; Chen 2015 tumor screens), CRISPR-StAR intrinsic-control screening (Uijttewaal 2025 Nat Biotechnol 43:1848), clonal-dynamics-limited detection, tumor-explant DNA recovery, syngeneic vs xenograft vs PDX considerations, and the relationship to downstream MAGeCK / drugZ analysis. Use when designing in vivo CRISPR screens for tumor / immune / metastasis biology, choosing focused vs genome-wide for animal models, addressing bottleneck-induced clonal collapse, picking the syngeneic / xenograft / PDX model, integrating in vivo with in vitro results, or applying CRISPR-StAR for animal experiments.

sboghossian-mini-claude-for-legal Skill

Use when a task requires systematically hunting for authoritative legal data across multiple heterogeneous sources — statutes, regulations, court judgments, official gazettes, regulator bulletins — and consolidating the results into a coherent, cited dataset. Acts as an orchestrating agent that selects and sequences the right data-source tools for a given legal research query, prioritizing primary sources and flagging data gaps.

sboghossian-mini-claude-for-legal Skill

Use when asked to draft a commercial agency agreement appointing an agent to sell goods or services on a principal's behalf, particularly in MENA jurisdictions where statutory agent-protection regimes create significant termination indemnity exposure. Covers agent authority, commission, exclusivity, reporting, IP, termination compensation, and the critical decision of whether to structure as a registered commercial agency or an ordinary services contract.

oimiragieo Bundle

Automated security scanner for external skill/agent content fetched from GitHub or web sources. Runs a 7-step PASS/FAIL security gate against fetched markdown/text content.

oimiragieo Bundle

Use when generating new content that must match an established writing style profile. Loads the style profile from style-analyzer, constructs a style-constrained system prompt, generates content, and performs A/B comparison against original samples for quality verification.

gptomics Bundle

Defines cell populations in flow and spectral cytometry through manual gates (rectangle, polygon, quadrant, boolean) and reproducible automated gating (openCyto gating templates, flowDensity data-driven thresholds, flowClust model-based gates), organized as a hierarchical GatingSet (flowWorkspace) and round-tripped with FlowJo via CytoML. Covers the canonical gate order (time -> debris -> singlets -> live -> lineage), FMO-vs-isotype boundary setting, gate-order dependence and recompute semantics, rare-event/MRD gating, and per-population statistics. Use when building a gating strategy, automating a manual FlowJo scheme across samples, choosing manual vs data-driven gates, or extracting population frequencies.

gptomics Bundle

Designs and ranks guide RNAs (sgRNAs) for CRISPR-Cas9/Cas12a gene knockout by scanning a target for PAM sites (NGG SpCas9, NNGRRT SaCas9, TTTV Cas12a, NG SpCas9-NG, near-PAMless SpRY), enumerating candidate spacers, applying hard filters (Pol-III TTTT terminator, 5' G, GC), ranking on-target activity with the context-appropriate model (Rule Set 2/Azimuth for U6/lentiviral, CRISPRscan for T7/embryo, DeepHF for high-fidelity variants, DeepCpf1 for Cas12a), and predicting the indel/frameshift outcome (Bae out-of-frame score, inDelphi, FORECasT, Lindel). Use when selecting sgRNAs to knock out a gene, choosing a nuclease/PAM for a constrained locus, picking which exon to target, or shortlisting guides before an off-target check. Off-target specificity, base/prime editing, and HDR donors are separate skills.

gptomics Bundle

Infers exact amplicon sequence variants (ASVs) from demultiplexed 16S rRNA or ITS amplicon FASTQ with DADA2 - removing primers with cutadapt (--discard-untrimmed), learning a per-run error model (filterAndTrim -> learnErrors -> dada -> mergePairs), merging run-level tables with mergeSequenceTables, then one removeBimeraDenovo. Covers why primers come OFF before truncation, why the error model is per-run, truncLen as a merge-overlap detection budget (V4 vs V3-V4), DADA2 vs Deblur and q2-dada2 (denoise-paired/single/pyro/ccs), ASV vs OTU, NovaSeq binned-quality error-fit breakage, ITSxpress for variable-length ITS, and decontam removal of reagent/kit contaminants. Use when turning demultiplexed amplicon reads into an ASV/feature table, choosing truncation lengths, handling multi-run studies, or ITS. For shotgun reads see metagenomics/kraken-classification; for QIIME2 CLI mechanics see qiime2-workflow; for primer trimming theory see read-qc/adapter-trimming.

gptomics Bundle

Tests gene lists, ranked vectors, and fold-change vectors against KEGG pathways and modules with clusterProfiler enrichKEGG/enrichMKEGG (ORA), gseKEGG (GSEA), and SPIA/graphite (signed-topology perturbation) in R. Owns the third pathway-analysis generation because KEGG ships signed directed signaling topology (KGML). Covers why a KEGG result is a timestamped join against a live REST API (irreproducible unless pinned with a gson snapshot, not the stale 2012 KEGG.db), why enrichKEGG keyType is kegg/ncbi-geneid not OrgDb ENSEMBL/SYMBOL (zero hits), why organism is a KEGG code (hsa, pae) with prokaryotic locus tags, and why SPIA works only on signaling maps. Use when finding enriched KEGG pathways or modules, scoring signed pathway perturbation, analyzing prokaryotes or non-model organisms via locus tags or KO, comparing conditions with compareCluster, or overlaying data with pathview. The hypergeometric universe lives in go-enrichment; the GSEA engine in gsea.

sboghossian-mini-claude-for-legal Skill

Use when setting up or operating automated quality evaluation of legal AI skill outputs using Langfuse. Covers the evaluation dataset structure for legal domains, judge-model configuration, scoring rubrics specific to legal drafting and analysis, how to run batch evals across skill versions, and how to connect eval results to feature-flag promotion decisions. Engineering skill for legal AI quality assurance.

sboghossian-mini-claude-for-legal Skill

Use when implementing or configuring the per-tier token budget system that limits LLM usage by subscription plan. Defines the monthly token allowances per tier, enforcement logic, overage handling, BYO-key bypass rules, and the Edge Function middleware that gates requests before they reach the LLM.

gptomics Bundle

Bulk-query Ensembl BioMart (and other BioMart instances) for cross-database ID mapping, gene/transcript/exon coordinates, and ortholog tables. Use when batch-converting Ensembl IDs to other namespaces (HGNC, RefSeq, UniProt, Entrez), pulling gene coordinate tables for thousands of genes, building ortholog wide-tables across species, or replacing slow Ensembl REST loops with one-shot bulk export. Encodes BioMart's XML query format, R biomaRt vs Python pybiomart trade-off, mart-vs-dataset hierarchy, and the URL endpoint that's BioMart-specific (separate from rest.ensembl.org).

oimiragieo Bundle

fast-check patterns for JS/TS — 6 canonical property categories with worked examples targeting agent-studio utilities (path normalization, safe-json, glob-to-regex, routing logic)

oimiragieo Bundle

Dispatch code-reviewer agent for two-stage review. Use after completing implementation tasks.

oimiragieo Skill

Fixes test failures, compliance gaps, and validation issues in the agent-studio ecosystem

sboghossian-mini-claude-for-legal Skill

Use when drafting or reviewing a document and the firm's own precedents, playbooks, or prior work product should inform the output. Retrieves semantically similar passages from the e-firm tenant's internal knowledge base — NDA templates, MSA playbooks, prior transaction documents, and firm-specific positions — with hard tenant isolation. Invoked explicitly ("use our NDA template") or implicitly when drafting work exists in the firm's KB. The firm KB is always preferred over public templates or model defaults.

sboghossian-mini-claude-for-legal Skill

Use when a legal-AI workflow needs to convert any publicly accessible URL into clean, LLM-ready markdown — for example, to retrieve a regulatory authority's latest guidance, a court's published judgment, a government gazette notice, or a law firm's published article for research or analysis. Requires a per-tenant Firecrawl API key. Triggers on any request to read or summarize a web page, scrape a regulatory site, or ingest an external URL as context for legal analysis.

sboghossian-mini-claude-for-legal Skill

Use when a user asks about pricing, plan tiers, credit consumption, subscription management, or billing configuration for the legal AI platform. This is a platform documentation skill covering the per-seat plus usage-credit billing model, Stripe integration, self-serve top-up, enterprise invoice billing, and credit consumption rates for premium features.

sboghossian-mini-claude-for-legal Skill

Use when drafting a Power of Attorney (PoA / وكالة) authorizing an agent to act on a principal's behalf. Covers all PoA types (general, special, durable, springing), required inputs, precise enumeration of powers, revocation mechanics, and the critical form requirements (notarization, apostille, consular legalization) for LB, KSA, UAE, EU/UK, and cross-border use. Arabic terminology included. Triggers on "power of attorney", "poa", "وكالة", "procuration", "proxy", or "authorization letter" requests for formal legal authority.

intent-solutions-io Bundle

Generate time series forecasts using TimeGPT, StatsForecast, and MLForecast. Use when forecasting, demand planning, or model comparison is needed. Trigger with 'forecast time series' or 'run Nixtla forecast'.

intent-solutions-io Bundle

Generate comprehensive markdown benchmark reports from forecast accuracy metrics with model comparisons, statistical analysis, and regression detection. Use when analyzing baseline performance, comparing forecast models, or validating model quality. Trigger with 'generate benchmark report', 'analyze forecast metrics', or 'create performance summary'.

intent-solutions-io Bundle

Validate forecast quality by comparing MASE and sMAPE against benchmarks. Use when detecting model degradation. Trigger with 'validate forecast' or 'check forecast quality'.

gptomics Bundle

Estimate divergence times under molecular-clock models with BEAST2, MCMCTree/PAML, TreePL, and LSD2, framing a date as a product of the calibration prior and the clock model far more than of the sequence data. Covers why branch length = rate x time is nonidentifiable so only calibrations convert relative rate-time into absolute age; why the effective (marginal) prior on a calibrated node differs from the density specified, mandating a sample-from-prior run; the fossil-as-minimum rule, soft bounds, tip-dating, and the fossilized birth-death process; the temporal-signal check (TempEst root-to-tip regression + date-randomization) required before dating viruses or ancient DNA; and clock-model choice via the coefficient of variation. Use when dating nodes, calibrating with fossils or sampling dates, choosing a clock or dating engine, or routing topology to modern-tree-inference, posteriors to bayesian-inference, and rooting to tree-manipulation.

gptomics Bundle

Edit phylogenetic tree structure with Biopython Bio.Phylo, and treat rooting as a separate statistical inference rather than a display choice. Covers why most inference returns an unrooted tree so placing the root creates every ancestor/descendant and basal claim; why a distant or lonely outgroup misroots inside the ingroup via long-branch attraction; the outgroup/midpoint/MAD/MinVar/non-reversible-likelihood rooting tradeoffs; why pruning must suppress degree-2 nodes and sum their branch lengths or all patristic distances silently corrupt; and why collapsing by support makes SOFT (uncertainty) polytomies, not HARD (radiation) ones. Use when rooting, re-rooting, pruning or subsetting taxa, extracting a clade or induced subtree, collapsing low-support branches, resolving polytomies, or ladderizing. Routes clock-based rooting to divergence-dating, inference to modern-tree-inference, and reading/plotting to tree-io and tree-visualization.

intent-solutions-io Bundle

Generate production-ready forecasting experiments with StatsForecast and TimeGPT. Use when setting up model benchmarking or cross-validation. Trigger with 'scaffold experiment' or 'compare models'.

intent-solutions-io Bundle

Fine-tunes TimeGPT on custom datasets to improve forecasting accuracy. Use when TimeGPT's zero-shot performance is insufficient or domain-specific accuracy is needed. Trigger with "finetune TimeGPT", "train TimeGPT", "adapt TimeGPT".

intent-solutions-io Bundle

Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other benchmark datasets). Use when the user asks about baseline performance, model comparisons, or metric interpretation for Nixtla time-series experiments. Trigger with "baseline review", "interpret sMAPE/MASE", or "compare AutoETS vs AutoTheta".

intent-solutions-io Bundle

Generate benchmarking pipelines to compare forecasting models and summarize accuracy/speed trade-offs. Use when evaluating TimeGPT vs StatsForecast/MLForecast/NeuralForecast on a dataset. Trigger with "benchmark models", "compare TimeGPT vs StatsForecast", or "model selection".

intent-solutions-io Bundle

Performs rigorous time series cross-validation using expanding and sliding windows. Use when needing to evaluate the performance of time series models on unseen data. Trigger with "cross validate time series", "evaluate forecasting model", "time series backtesting".

oimiragieo Skill

Agent frontmatter enhancements — disallowedTools, mcpServers scoping, fork_eligible field

gptomics Bundle

Aligns sample metadata with count matrices and constructs design matrices for downstream DE, handling the alphabetical-reference-level trap (relevel BEFORE DESeq), LRT reduced-model rules, the interaction-term resultsNames trap, continuous-covariate scaling and splines, repeated measures via duplicateCorrelation or dream, high-cardinality categorical pseudo-singular designs, sample swap detection via XIST/RPS4Y1 expression and somalier/NGSCheckMate genotypes, SABV (sex-as-biological-variable) mandate, Simpson's-paradox collapsing of technical replicates, and the `~ 0 + group` parameterization for clean contrasts. Use when building a design matrix, troubleshooting reversed fold-change direction, encoding paired or repeated-measures designs, detecting sample swaps, deciding sex-as-covariate, or aggregating technical replicates.

intent-solutions-io Bundle

Automatically selects the best forecasting model between StatsForecast and TimeGPT based on time series data characteristics. Use when unsure which model performs best. Trigger with "auto-select model", "choose best model", "model selection".