AI & ML

sboghossian-mini-claude-for-legal Skill

Use when reviewing B2B copy, sales decks, LinkedIn posts, conference materials, or any content directed at lawyers, law firm partners, or in-house counsel for a legal AI assistant. Defines the specific displacement, commodification, and practice-threat framings that must never appear in professional-audience materials — because they trigger hostile rejection by the buyer audience, violate bar advertising norms, and undermine the product's partnership model with the legal profession.

sboghossian-mini-claude-for-legal Skill

Use when drafting a commercial agency agreement appointing an agent to solicit orders or sell products/services in a defined territory on behalf of a principal. Covers corporate/commercial practice across all jurisdictions, with particular attention to mandatory MENA commercial agency laws (UAE, KSA, Lebanon, Egypt) that override contractual freedom and create registration and termination obligations.

sboghossian-mini-claude-for-legal Skill

Use when drafting board resolutions for a company to approve a specific action — contract signing, officer appointment, dividend declaration, share issuance, or other corporate authority matters. Corporate governance practice area; covers the proper form, recitals, resolved clauses, and authorization language required under MENA and international corporate laws, including the critical distinction between written resolutions and meeting resolutions.

sboghossian-mini-claude-for-legal Skill

Use when drafting an escrow agreement for an M&A transaction where a portion of the purchase price is held by an escrow agent to secure the seller's indemnification or other post-closing obligations. Covers escrow amount, term, release conditions, claim procedures, investment instructions, and escrow agent fees. Applicable across MENA (UAE, KSA, DIFC, ADGM, LB, EG) and internationally. Trigger when the SPA requires an escrow arrangement as part of the deal structure.

sboghossian-mini-claude-for-legal Skill

Use when drafting a letter of intent (LOI) or heads of terms for a proposed acquisition, joint venture, partnership, or significant commercial transaction. Carefully distinguishes binding from non-binding provisions, outlines principal commercial terms, addresses exclusivity and confidentiality, and sets the path to definitive agreements. Applicable across MENA, GCC, EU, and common-law jurisdictions.

sboghossian-mini-claude-for-legal Skill

Use when a supplier and buyer need to draft a supply agreement governing the purchase and delivery of goods or materials, covering product specifications, pricing, ordering procedures, delivery terms, quality standards, warranties, rejection rights, and force majeure. MENA-specific guidance covers UAE sale of goods principles under the Civil Transactions Law, DIFC contract law, CISG applicability in MENA contexts, Incoterms 2020 selection, and Arabic-language documentation for enforcement.

sboghossian-mini-claude-for-legal Skill

Use when the product or quality team needs to measure, track, and trend the rate at which the AI assistant generates fabricated legal content — false citations, invented statute numbers, nonexistent cases, or wrong regulatory thresholds — broken down by skill, model, and jurisdiction. This is an internal quality-assurance report. Trigger on the weekly quality-review schedule or whenever a concerning spike in user-reported errors is observed.

sboghossian-mini-claude-for-legal Skill

Use when a lawyer user needs guidance on the professional-responsibility duty of competence as it applies to AI tool use in legal practice. Covers ABA Model Rule 1.1 and its analogs in MENA bars (Lebanese Bar, Saudi Bar, UAE Bar, DIFC/ADGM Rules of Professional Conduct) and European bar codes (UK SRA, French CNB/RIN). Specifically addresses what "understanding the technology" means in practice, verification obligations, hallucination risk, and how to document AI use in matter files to satisfy competence duties.

sboghossian-mini-claude-for-legal Skill

Use when migrating a French whistleblower policy (politique lanceur d'alerte) drafting or review skill into the mini-claude-for-legal format. The adapter maps French Sapin II and Waserman Law compliance logic — mandatory alert channels, protected-person scope, investigation procedures, and anti-retaliation obligations — into the standard skill model. Primary jurisdiction France; also relevant for EU Whistleblower Directive transposition in other member states and Lebanese corporate-governance best practice.

sboghossian-mini-claude-for-legal Skill

Use when migrating the Rafal Fryc statute-analysis methodology into the mini-claude-for-legal format. This adapter preserves structured legislative text analysis — section-by-section decomposition, applicability scoping, definitional chain tracing, and cross-reference mapping — mapped into the standard skill model. Strong for civil-code jurisdictions (France, Lebanon, UAE onshore, Poland) and EU regulatory instruments. Triggers on import of any statute-analysis skill attributed to the Fryc approach.

autohandai-community-skills Bundle

Compile TensorRT-LLM on a SLURM cluster. Covers submitting a batch job with a container image, monitoring the job, and verifying the build. Use when the user wants to compile TRT-LLM remotely via SLURM rather than on a local compute node.

autohandai-community-skills Bundle

Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify scheduling or request-management overhead. Supports optional inter-kernel gap, eager-vs-graph, pattern mapping, and multi-rank straggler drill-down. Use standalone or within perf-analysis. Triggers: host overhead, inter-step gap, scheduling overhead, forward step isolation, nsys iteration analysis, NVTX breakdown, request management overhead, GPU idle, host bottleneck, host prep exposed, inter-kernel gap, bubble analysis, graph coverage, eager kernel, rank imbalance, straggler detection.

autohandai-community-skills Bundle

Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability. Always use for any modification, review, refactor, or design planning that touches MoE modules, including tensorrt_llm/_torch/modules/fused_moe, ConfigurableMoE, MoE backends, MoEScheduler/moe_scheduler.py, forward execution/chunking, communication strategies, EPLB, quantization/weight handling, routing, factories, MoE docs, or MoE tests. Also use when the user asks whether a MoE design follows the current architecture or whether a MoE refactor is reasonable.

gptomics Bundle

Infer orthologous genes and gene families across species using OrthoFinder3 (HOG-based phylogenetic orthology), SonicParanoid2, Broccoli, ProteinOrtho, OMA / FastOMA hierarchical orthologous groups, eggNOG-mapper, JustOrthologs, and TOGA whole-genome-alignment orthology. Use when building single-copy ortholog sets for phylogenomics, classifying co-orthologs and in/out-paralogs after gene duplication, propagating functional annotation via orthology with awareness of the ortholog conjecture, distinguishing speciation from duplication via gene-tree species-tree reconciliation, computing Quest-for-Orthologs benchmark performance, or running synteny-aware ortholog detection in WGD-affected lineages.

gptomics Bundle

Detect positive (diversifying / episodic / pervasive) selection using codon dN/dS frameworks. Implements PAML codeml site models (M0/M1a/M2a/M7/M8/M8a), branch models, branch-site model A (Zhang 2005), and HyPhy methods (BUSTED, BUSTED-S, BUSTED-MH, BUSTED-PH, MEME, FEL, FUBAR, aBSREL, SLAC, RELAX, GARD, FUBAR-MH). Includes McDonald-Kreitman framework (asymptotic alpha, impMKT, polyDFE, DFE-alpha, GRAPES) for within-species + divergence inference, RERconverge for trait-correlated rate shifts, CSUBST for convergent substitution, and PhyloAcc for accelerated noncoding evolution. Use when testing adaptive evolution at codons, branches, or full gene; running GARD recombination pre-screen; controlling alignment-error and gBGC false positives; reconciling PAML vs HyPhy results; or performing genome-scale selection scans.

gptomics Bundle

Navigate the Bio.PDB SMCRA hierarchy (Structure-Model-Chain-Residue-Atom) safely, surfacing the heterogeneity it hides by default. Use when deciding how to handle altloc/DisorderedAtom conformers before a distance or RMSD, indexing residues insertion-code-safe with the full (hetflag, resseq, icode) tuple, choosing the ATOM/observed vs SEQRES/canonical vs UniProt sequence, selecting the right Model for an NMR ensemble, filtering waters/hetero/metals correctly, and reconciling auth vs label numbering. Keywords SMCRA, altloc, DisorderedAtom, insertion code, SEQRES, PPBuilder, auth_seq_id.

sboghossian-mini-claude-for-legal Skill

Use when a user encounters an empty state in a legal AI assistant — a screen with no prior content, no chats, no documents, no projects — and the system must provide an actionable, persona-appropriate prompt rather than a dead end. Covers the specific prompt language, CTA patterns, and personalization signals for every major empty-state screen. Eliminates "no data" dead-ends and converts them into the user's next productive action.

sboghossian-mini-claude-for-legal Skill

Use when a new user is in their first week of using a legal AI assistant and the system must surface a daily micro-prompt or featured template to build habit, expand discovered capabilities, and reduce early churn. The template-of-the-day is a lightweight daily engagement nudge — one relevant document template or legal task — displayed on the home screen or in a daily notification during the first 7 days of use.

sboghossian-mini-claude-for-legal Skill

Use when a legal ops team or in-house legal department needs to create a contract playbook for a specific agreement type — documenting the company's standard positions, acceptable fallbacks, red lines, approval requirements, and negotiation guidance for key clauses. Enables consistent, faster negotiation and reduces reliance on senior lawyer involvement for routine matters. Applicable across all agreement types and jurisdictions; MENA-aware for UAE, KSA, LB, and GCC enforcement realities.

sboghossian-mini-claude-for-legal Skill

Use when drafting a disclosure letter from a seller to a buyer in connection with a share purchase agreement (SPA) or asset purchase agreement. Covers general and specific disclosures against representations and warranties, material contracts schedules, and exceptions to warranty coverage. Relevant for corporate M&A transactions across MENA (UAE, KSA, DIFC, ADGM, LB, EG), UK, EU, and other common-law or civil-law jurisdictions. Trigger when a user needs to prepare the disclosure bundle that accompanies a signed acquisition agreement.

sboghossian-mini-claude-for-legal Skill

Use when drafting an employee handbook covering workplace policies, code of conduct, leave entitlements, anti-discrimination and harassment, disciplinary procedures, health and safety, IT acceptable use, and acknowledgment forms. Must comply with the applicable jurisdiction's employment law. Particularly important in MENA (UAE Labour Law, KSA Labour Law, LB Labour Law, EG Labour Law) where statutory entitlements differ significantly from common-law defaults. Trigger when a company is onboarding employees in a new market or updating its internal HR policies.

sboghossian-mini-claude-for-legal Skill

Use when drafting an engagement letter from a law firm to a client confirming the scope of representation, fee structure, billing practices, staffing, conflicts check status, and file retention policy. Applicable across MENA (UAE, KSA, LB, EG, DIFC, ADGM) and internationally. Engagement letters are mandatory risk management tools — they define the scope of representation and limit malpractice exposure. Trigger when a law firm is taking on a new client matter or when an existing engagement's scope changes significantly.

sboghossian-mini-claude-for-legal Skill

Use when drafting a bilateral services agreement between a service provider and client, covering scope of work, deliverables, payment terms, term, termination, limitation of liability, and governing law. Applicable across MENA and international practice; MENA-specific flags cover UAE, DIFC, KSA, Lebanon, and Egypt contract formation requirements, civil-law enforceability of limitation of liability clauses, and Arabic-language obligations.

sboghossian-mini-claude-for-legal Skill

Use when a legal team needs to draft a witness statement for court or tribunal proceedings — setting out a factual narrative, the witness's direct observations, and a jurisdiction-appropriate statement of truth. Covers chronological structure, factual vs. opinion boundaries, exhibit referencing, and form requirements across MENA (UAE, DIFC, ADGM, Lebanon, Egypt) and common-law (UK) litigation contexts. Distinct from the arbitration witness statement skill, which follows IBA Rules conventions.

sboghossian-mini-claude-for-legal Skill

Use when a newly registered user is in their first seven days on the platform and needs a structured, low-friction introduction to core capabilities. This skill governs the day-by-day progressive tour that walks all personas from their first chat through matter management, the clause library, and the NPS prompt, delivered via in-app cards and optional email drip.

autohandai-community-skills Bundle

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

autohandai-community-skills Bundle

External verl end-to-end validation workflow for Megatron-Bridge model/provider changes. Covers running a small verl Megatron backend job from a Bridge checkout, choosing LoRA/DDP plus optional save/resume and parallelism variants, setting PYTHONPATH so verl imports the local Bridge tree, and reporting pass/fail evidence.

autohandai-community-skills Bundle

Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts (configs, logs, results), or set up the MLflow MCP server. ALWAYS triggers on mentions of MLflow, experiment results, run comparison, invocation IDs in the context of results, or MLflow MCP setup.

autohandai-community-skills Bundle

Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or assessing control trade-offs. Trigger keywords - nemoclaw security best practices, sandbox security controls risk framework, nemoclaw credential storage, openshell provider, api key security, openclaw security controls, nemoclaw security boundary, prompt injection, tool access control.

autohandai-community-skills Bundle

Visualize a specific transformer decoder layer from an AutoDeploy FX graph text dump as a hierarchical DOT/PNG diagram. Optionally annotate nodes with actual GPU kernel names and durations from an nsys trace. Use when the user wants to visualize, inspect, or debug a layer in an AutoDeploy model graph dump. Triggers on: "visualize layer", "show layer", "graph of layer", "layer visualization", "dump graph layer". Assumes graph dumps already exist in a directory (produced by AD_DUMP_GRAPHS_DIR).

autohandai-community-skills Bundle

Write and implement GPU kernels using NVIDIA CuTe DSL (CUTLASS 4.x Python API) — NOT for Triton, CUDA C++, or conceptual explanations. Trigger only when the user wants to write or implement a kernel, not when asking questions about CuTe DSL concepts or layouts. CuTe DSL uses cute.jit/cute.kernel decorators and cutlass.cute imports. Covers element-wise kernels, GEMM patterns, reductions, memory hierarchy (global/shared/register/TMA), MMA tensor core operations, software pipelining, and framework integration.

autohandai-community-skills Bundle

Nsight Systems (nsys) CLI for system-level timeline profiling. Use when the user wants to run nsys profile, analyze .nsys-rep reports, use nsys stats/analyze/recipe commands, diagnose GPU idle time from timeline traces, or profile distributed training with NCCL overlap analysis. NOT for kernel-level metrics like SOL%, occupancy, or roofline (use perf-nsight-compute-analysis for ncu). NOT for writing or generating kernels. NOT for applying optimizations like CUDA Graphs.

sboghossian-mini-claude-for-legal Skill

Use when a user needs help discovering which prompts in the 152-prompt library are most relevant to their role, jurisdiction, and recent work. Produces personalized prompt recommendations with progressive disclosure (3–5 at a time), and learns from user engagement signals to improve future recommendations. Triggers on "what should I try?", "show me useful prompts", or when a user profile indicates a gap between their stated role and their actual usage patterns.

sboghossian-mini-claude-for-legal Skill

Use when migrating a French politique de confidentialité (privacy policy) drafting or review skill into the mini-claude-for-legal format. The adapter maps French-language GDPR privacy-policy templates and CNIL compliance checklists into the standard skill model, covering mandatory GDPR/CNIL disclosure requirements, the Loi Informatique et Libertés overlay, and French plain-language expectations. Primary jurisdiction France; also relevant for French-speaking MENA entities subject to GDPR.

sboghossian-mini-claude-for-legal Skill

Use when a law firm or in-house legal department needs to create or customise a client intake form for new matters. Captures client identity, matter description, conflict check data, document collection needs, urgency assessment, and initial budget estimate. Applicable across all practice areas and jurisdictions; includes MENA-specific KYC and beneficial ownership fields required under UAE, KSA, and Lebanese AML regulations.

sboghossian-mini-claude-for-legal Skill

Use when drafting a legally structured formal notice to another party — covering statement of facts, applicable legal provisions, specific demands, and consequences of non-compliance. Applicable to pre-litigation notices, contractual breach notices, demand letters, and regulatory compliance notices across MENA (UAE, KSA, LB, EG), UK, EU, and US. Trigger when a client needs to put a counterparty formally on notice before commencing legal action or exercising a contractual right.