Product & Planning

gptomics Bundle

Decision-grade statistical analysis for metabolomics intensity tables. Covers transformation and scaling (Pareto vs unit-variance as a hidden hypothesis), unsupervised structure (PCA/HCA for QC), permutation-validated PLS-DA/OPLS-DA (R2 vs Q2, double CV, VIP as heuristic), univariate testing (Welch/Mann-Whitney/ANOVA/LMM with covariate adjustment), and dependence-aware multiple testing. Use when testing which metabolites differ, building or validating a discriminant model, choosing a scaling, or correcting many correlated tests. For sample-wise normalization/drift correction see metabolomics/normalization-qc; for ML classifiers and selection-inside-CV leakage see machine-learning/biomarker-discovery and machine-learning/model-validation; for pathway interpretation see metabolomics/pathway-mapping; for design/power/multiplicity regime see experimental-design/multiple-testing.

intent-solutions-io Skill

This skill enables Claude to analyze capacity requirements and plan for future growth. It uses the capacity-planning-analyzer plugin to assess current utilization, forecast growth trends, and recommend scaling strategies. Use this skill when the user asks to "analyze capacity", "plan for growth", "forecast infrastructure needs", or requests a "capacity roadmap". It is also useful when the user mentions specific capacity metrics like CPU usage, memory, database storage, network bandwidth, or connection pool saturation. This skill is ideal for proactive infrastructure planning and preventing performance bottlenecks.

autohandai-community-skills Bundle

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger.

autohandai-community-skills Bundle

Discover and inventory shadow API endpoints that operate outside documented specifications using traffic analysis, code scanning, and API discovery platforms.

gptomics Bundle

Builds diagnostic and prognostic classifiers on omics feature matrices with regularized logistic regression, random forest, and gradient-boosted trees, handling the p>>n regime, batch shortcut learning, class imbalance, and probability calibration. Use when building a classifier from expression, methylation, or variant data, choosing an algorithm for high-dimensional small-n data, or diagnosing a suspiciously perfect AUC. For unbiased evaluation see machine-learning/model-validation; for feature selection see machine-learning/biomarker-discovery; for time-to-event outcomes see machine-learning/survival-analysis.

sboghossian-mini-claude-for-legal Skill

Use when a user in a legal AI chat session expresses a desire for a new feature, capability, or improvement. Guides the assistant through detecting feature-request language, gathering structured context, tagging by category and persona, submitting to the product backlog (Linear), and aggregating requests for weekly prioritization — distinct from bug reports which go to the bug collector.

intent-solutions-io Skill

This skill enables Claude to provide comprehensive, prioritized performance optimization recommendations for software projects. It is triggered when the user requests performance improvements, optimization suggestions, or asks for a performance review. The skill analyzes frontend, backend, and infrastructure aspects of the project to identify bottlenecks and anti-patterns. It then provides actionable advice, estimates potential performance gains, and suggests a phased implementation roadmap. Use this skill when the user mentions "optimize performance", "performance recommendations", "performance review", "improve speed", or asks about "bottlenecks".

sboghossian-mini-claude-for-legal Skill

Use when generating, selecting, or configuring push notification copy for the Louis mobile and web app. Provides a complete library of notification templates organized by type — re-engagement, matter-specific, skill discovery, credit warnings, and collaboration — along with channel specifications, frequency rules, and personalization guidance. Ensures notifications are specific, timely, and non-intrusive, respecting user preferences and quiet hours.

autohandai-community-skills Bundle

Audit service accounts across enterprise infrastructure to identify orphaned, over-privileged, and non-compliant accounts. This skill covers discovery of service accounts in Active Directory, cloud pl

sboghossian-mini-claude-for-legal Skill

Use when a site visitor navigates to the prompt library, searches for AI prompts for legal work, or uses the in-product prompt discovery feature. Manages the 152-prompt library — filterable by practice area, jurisdiction, and document type — with per-prompt actions (copy, share, save, try-in-product CTA). Helps lawyers and legal teams discover and reuse high-quality prompts for common legal AI tasks.

freedomintelligence Bundle

Galaxy tool discovery, intelligent recommendation, and execution — 8,000+ bioinformatics tools from usegalaxy.org with multi-signal scoring and workflow suggestions

sboghossian-mini-claude-for-legal Skill

Use when a prospect or user asks "what can Louis do?" or "how is your AI different from generic AI tools?" Explains the core AI features of the Louis legal AI platform — skill router, clause library, citations engine, risk scanner, document workspace, drafting board, and legal flows — with MENA-first jurisdictional awareness and Arabic-native capability as key differentiators. Routes to this skill for product discovery, competitive positioning, and in-product onboarding moments.

gptomics Bundle

Tests and estimates rhythmicity at a PRE-SPECIFIED period (canonically 24h) in time-series omics using cosinor regression (CosinorPy), JTK_CYCLE/ARSER/Lomb-Scargle meta-analysis (MetaCycle meta2d), and non-parametric tests for asymmetric waveforms (RAIN, DiscoRhythm); estimates phase (acrophase), amplitude, and MESOR, and controls FDR with an effect-size (rAMP) filter against over-detection. Use when testing for 24-hour or other known-period oscillations in a single condition (circadian, feeding-fasting, or light-dark experiments) and estimating their phase/amplitude. Not for unknown-period discovery (see temporal-genomics/periodicity-detection) or comparing rhythms between conditions (see temporal-genomics/differential-rhythmicity).

gptomics Bundle

Controls error rates across thousands of simultaneous tests in genomics discovery using false-discovery-rate methods (Benjamini-Hochberg 1995; Benjamini-Yekutieli 2001 for arbitrary dependence; Storey q-value with pi0 estimation; local FDR; independent filtering Bourgon 2010; covariate-weighted FDR via IHW Ignatiadis 2016), plus family-wise error control (Bonferroni, Holm) and the GWAS genome-wide threshold. Covers the FDR-versus-FWER choice as the discovery-versus-confirmatory distinction, the dependence assumptions behind BH (PRDS) versus BY, pi0 estimation, the independent-filtering and false-coverage-rate traps, and reproducibility ranking via IDR (Li 2011). Use when correcting p-values from genome-wide tests, choosing between BH/BY/q-value/Bonferroni, setting an FDR threshold, applying IHW or independent filtering, or interpreting q-values. For confirmatory trials with few pre-specified endpoints (closed testing, graphical/gatekeeping), see clinical-biostatistics/multiplicity-graphical.

gptomics Bundle

Selects biomarker features from high-dimensional omics data using Boruta all-relevant selection, mRMR, LASSO/elastic-net, and stability selection, while controlling the leakage, irreproducibility, and correlated-feature traps that make most published signatures fail to replicate. Use when identifying candidate biomarkers, deciding between an all-relevant and a minimal-optimal selector, or judging whether a selected gene set is reproducible. For unbiased performance estimation of the resulting model see machine-learning/model-validation; for interpreting a trained model see machine-learning/prediction-explanation.

freedomintelligence Bundle

Local Scanpy pipeline for single-cell RNA-seq QC, clustering, marker discovery, and optional two-group differential expression from raw-count .h5ad.

autohandai-community-skills Bundle

Runs the morning maintainer standup for NemoClaw. Triages the backlog, determines the day's target version, labels selected items, surfaces stragglers from previous versions, and outputs the daily plan. Use at the start of the workday. Trigger keywords - morning, standup, start of day, daily plan, what are we shipping today.

autohandai-community-skills Bundle

Perform coverage-guided fuzzing of compiled binaries using AFL++ (American Fuzzy Lop Plus Plus) to discover memory corruption, crashes, and security vulnerabilities. The tester instruments target binaries with afl-cc/afl-clang-fast, manages input corpora with afl-cmin and afl-tmin, runs parallel fuzzing campaigns with afl-fuzz, and triages crashes using CASR or GDB scripts. Activates for requests involving binary fuzzing, crash discovery, coverage-guided testing, or AFL++ fuzzing campaigns.

gptomics Bundle

Infer or annotate TCR antigen specificity by unsupervised clustering (TCRdist/tcrdist3, GLIPH2, clusTCR, GIANA) and database lookup (VDJdb, IEDB, McPAS-TCR), and rank candidates with supervised predictors (ERGO-II, NetTCR-2.x, pMTnet) under explicit caveats. Encodes the central truth that general TCR-epitope prediction for UNSEEN epitopes essentially does not work (collapses to near-random; IMMREP22, Grazioli 2022) because labeled data is dominated by a few immunodominant epitopes and there is no true negative set — so clustering for discovery is the honest task and de-novo binding needs wet-lab validation. Use when annotating TCR specificity or grouping a repertoire. Epitope/MHC context lives in mhc-binding-prediction.

sboghossian-mini-claude-for-legal Skill

Use when a user, prospect, or developer wants to browse, filter, or understand the full public catalog of Louis's 982-skill library — filterable by category, jurisdiction, language, and priority. Serves transparency, competitive comparison, and developer/integration discovery purposes. Routes to this skill for "what skills does Louis have?", "do you cover [jurisdiction/practice area]?", or "show me what's available in your skill library" queries.

sboghossian-mini-claude-for-legal Skill

Use when a user asks about recent product updates, feature releases, what's new in Louis, the development roadmap, known issues, or the current status of a requested feature. Handles changelog queries, roadmap transparency, feature-request acknowledgment, and bug/issue status updates. Routes to the appropriate channel (public changelog, status page, GitHub issues) and provides a structured, honest update within the bounds of what can be disclosed.

sboghossian-mini-claude-for-legal Skill

Use as a catch-all topic discovery skill when a user asks about a subject domain that may not yet have a dedicated skill, or when the router cannot confidently match the user's question to an existing skill. Surfaces relevant existing skills and reference packs for any new domain, and provides a methodology for scoping the legal dimensions of unfamiliar topics.

sboghossian-mini-claude-for-legal Skill

Use when discussing growth strategy, acquisition models, or retention mechanics for a legal-AI product. Covers product-led growth (PLG), marketing-led, and sales-led motions; funnel metrics; retention and expansion frameworks; and the specific challenges of growing in MENA legal markets where trust-based referral dominates over self-serve discovery. Reach for this skill when the user asks about growth strategy, funnel metrics, retention, or go-to-market model selection.

sboghossian-mini-claude-for-legal Skill

Use when planning or executing content publication on Medium or Substack for a legal-tech product — covering content formats, audience considerations, SEO and algorithmic discovery, cross-posting strategy, and the specific fit of each platform for reaching legal professionals. Reach for this skill when the user asks about using Medium or Substack for legal-tech content distribution, thought leadership, or newsletter audience building.

sboghossian-mini-claude-for-legal Skill

Use when a student or junior lawyer is preparing for moot court, appellate oral argument, or any structured advocacy performance. This skill simulates the judicial bench (hot, cold, or hostile), coaches the opening roadmap, critiques argument structure and citation accuracy in real time, tracks time, and prepares rebuttal. Jurisdiction-agnostic; adapts to common-law (DIFC, ADGM, UK, US) and civil-law (Lebanon, UAE onshore, KSA, Egypt) court styles.

sboghossian-mini-claude-for-legal Skill

Use when discussing core product management fundamentals — discovery, product requirements documents (PRDs), OKRs, Jobs-to-be-Done (JTBD) frameworks, the Wedge model for market entry, and how these apply to building a legal-AI product. Reach for this skill when the user asks about product management methodology, how to write a PRD, how to apply OKRs, or how to think about product-market fit for a legal-AI product.

sboghossian-mini-claude-for-legal Skill

Use when a lawyer or litigant needs a structured checklist of procedural requirements for a specific court and matter type — covering initial filings, fees, service of process, response deadlines, discovery regime, witness rules, cost frameworks, and appeal tracks. Covers DIFC Courts, ADGM Courts, UAE onshore civil courts, Saudi courts (General, Commercial, Labor, Administrative), Lebanese courts, English High Court, and leading MENA arbitration institutions (DIAC, LCIA, SCCA). MENA-first; distinguishes civil-law from common-law procedure.

autohandai-community-skills Bundle

Performs API inventory and discovery to identify all API endpoints in an organization's environment including documented, undocumented, shadow, zombie, and deprecated APIs. The tester uses passive traffic analysis, active scanning, DNS enumeration, JavaScript analysis, and cloud resource inventory to build a comprehensive API catalog. Maps to OWASP API9:2023 Improper Inventory Management. Activates for requests involving API discovery, shadow API detection, API inventory audit, or attack surface mapping.

gptomics Bundle

Analyze spatial cell-cell interactions, neighborhoods, and niches in IMC/MIBI data with squidpy and imcRtools, covering neighborhood-enrichment permutation nulls, the abundance-vs-density confound, inhomogeneous Ripley's K, cellular-neighborhood discovery, graph-construction (contact vs proximity), and edge effects. Use when testing whether cell types co-locate, choosing a spatial null, building a neighbor graph, discovering tissue niches, or deciding whether a spatial pattern is real or a density/segmentation artifact.

gptomics Bundle

Explains ML predictions on omics data with SHAP, LIME, and permutation importance, handling the correlated-feature trap, the conditional-vs-interventional Shapley choice, and the attribution-is-not-causation boundary. Use when interpreting an omics classifier, debugging shortcut/batch learning, or deciding whether an attribution ranking can be trusted as biology. For validated feature selection see machine-learning/biomarker-discovery; explanations are not a selection method.

sboghossian-mini-claude-for-legal Skill

Use when drafting discovery requests — interrogatories, requests for production of documents, and requests for admission — for civil litigation proceedings. Covers proportionality, relevance standards, and compliance with procedural rules across jurisdictions. Relevant for disputes practitioners in UAE courts, DIFC/ADGM courts, Lebanon, Egypt, KSA, UK, EU, and US proceedings. Trigger when a client needs formal discovery instruments to compel disclosure of evidence from the opposing party.

autohandai-community-skills Bundle

Discover and inventory all privileged accounts across enterprise infrastructure including domain admins, local admins, service accounts, database admins, cloud IAM roles, and application admin account

sboghossian-mini-claude-for-legal Skill

Use when an attorney wants to model opposing counsel's strategy, predict their likely motions and tactical moves, understand their settlement posture, and build a playbook to pre-empt attacks. Calibrated by firm reputation, counsel personality, and case type. Covers aggressive, collaborative, and dilatory strategies; likely motions (MTD, MSJ, discovery disputes); forum-shopping and parallel proceedings. Output is a structured opposing-counsel playbook for negotiation leverage, settlement strategy, and hearing preparation.

gptomics Bundle

Nominates and assesses CRISPR off-target sites genome-wide. Enumerates candidate sites by mismatch and bulge tolerance with Cas-OFFinder/CRISPRitz, ranks them with the published CFD score (SpCas9-only, relative ranker) or MIT/CRISTA/energy models, runs variant-aware screening against gnomAD/individual genomes (CRISPRme), and frames the empirical genome-wide discovery assays (GUIDE-seq, CIRCLE-seq, CHANGE-seq, DISCOVER-seq, Digenome-seq) and high-fidelity nuclease choice (HiFi Cas9, Sniper-Cas9, eSpCas9, SpCas9-HF1). Use when assessing guide RNA specificity, choosing among candidate guides, screening a therapeutic guide against population variation, or planning empirical off-target validation. Distinguishes predicted vs detected vs validated. On-target activity scoring and deaminase (Cas-independent) base/prime-editor off-targets are separate skills.

sboghossian-mini-claude-for-legal Skill

Use when the platform needs to surface relevant features to a newly onboarded user based on their persona (partner, associate, in-house counsel, law student, or consumer). This skill governs the pacing, sequencing, and content of per-persona feature reveals during the first 28 days, ensuring each user type encounters the capabilities most relevant to their work without being overwhelmed.

sboghossian-mini-claude-for-legal Skill

Use when generating show notes for a podcast episode featuring HAQQ Legal AI content, legal tech topics, MENA legal market commentary, or founder conversations. This skill defines the exact structure, word count, SEO requirements, timestamp format, pull-quote selection, and subscribe CTAs for podcast show notes that drive discovery and return listeners.