AI & ML

sboghossian-mini-claude-for-legal Skill

Use when investigating the behavior of a legal AI skill by inspecting its LLM traces in Langfuse — understanding which prompts were sent, what the model returned, how long each span took, what scores were assigned, and how to diagnose regressions or quality issues. Engineering and QA skill for legal AI observability and debugging.

sboghossian-mini-claude-for-legal Skill

Use when running the NDA benchmark that tests drafting, review, intake, and edge-case handling across LB/KSA/UAE/DIFC/FR/UK. Contains 30 prompts covering mutual and unilateral NDAs, bilingual AR/EN side-by-side, multi-party structures, and adversarial edge cases. Primary benchmark for confidentiality-related AI capabilities.

intent-solutions-io Skill

This skill optimizes deep learning models using various techniques. It is triggered when the user requests improvements to model performance, such as increasing accuracy, reducing training time, or minimizing resource consumption. The skill leverages advanced optimization algorithms like Adam, SGD, and learning rate scheduling. It analyzes the existing model architecture, training data, and performance metrics to identify areas for enhancement. The skill then automatically applies appropriate optimization strategies and generates optimized code. Use this skill when the user mentions "optimize deep learning model", "improve model accuracy", "reduce training time", or "optimize learning rate".

intent-solutions-io Skill

This skill enables Claude to design and visualize database schemas. It leverages normalization guidance (1NF through BCNF), relationship mapping, and ERD generation to create efficient and well-structured databases. Use this skill when the user requests to "design a database schema", "create a database model", "generate an ERD", "normalize a database", or needs help with "database design best practices". The skill is triggered by terms like "database schema", "ERD diagram", "database normalization", and "relational database design".

intent-solutions-io Skill

This skill enables Claude to track and manage AI/ML model versions using the model-versioning-tracker plugin. It should be used when the user asks to manage model versions, track model lineage, log model performance, or implement version control for AI/ML models. Use this skill when the user mentions "track versions", "model registry", "MLflow", or requests assistance with AI/ML model deployment and management. This skill facilitates the implementation of best practices for model versioning, automation of model workflows, and performance optimization.

intent-solutions-io Skill

This skill empowers Claude to perform regression analysis and modeling using the regression-analysis-tool plugin. It analyzes datasets, generates appropriate regression models (linear, polynomial, etc.), validates the models, and provides performance metrics. Use this skill when the user explicitly requests regression analysis, prediction based on data, or mentions terms like "linear regression," "polynomial regression," "regression model," or "predictive modeling." This skill is also helpful when the user needs to understand the relationship between variables in a dataset.

gptomics Bundle

Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when batch-mapping gene IDs across species, or when comparing the resources for consensus calls. Encodes confidence-level semantics, 1:1 vs 1:many vs many:many, HomoloGene deprecation, and when to defect to de novo computation.

intent-solutions-io Skill

This skill automates the setup of machine learning experiment tracking using tools like MLflow or Weights & Biases (W&B). It is triggered when the user requests to "track experiments", "setup experiment tracking", "initialize MLflow", or "integrate W&B". The skill configures the necessary environment, initializes the tracking server (if needed), and provides code snippets for logging experiment parameters, metrics, and artifacts. It helps ensure reproducibility and simplifies the comparison of different model runs.

intent-solutions-io Skill

This skill enables Claude to provide interpretability and explainability for machine learning models. It is triggered when the user requests explanations for model predictions, insights into feature importance, or help understanding model behavior. The skill leverages techniques like SHAP and LIME to generate explanations. It is useful when debugging model performance, ensuring fairness, or communicating model insights to stakeholders. Use this skill when the user mentions "explain model", "interpret model", "feature importance", "SHAP values", or "LIME explanations".

intent-solutions-io Skill

This skill automates the adaptation of pre-trained machine learning models using transfer learning techniques. It is triggered when the user requests assistance with fine-tuning a model, adapting a pre-trained model to a new dataset, or performing transfer learning. It analyzes the user's requirements, generates code for adapting the model, includes data validation and error handling, provides performance metrics, and saves artifacts with documentation. Use this skill when you need to leverage existing models for new tasks or datasets, optimizing for performance and efficiency.

autohandai-community-skills Bundle

Contribution conventions for NeMo-RL. Covers PR title format, commit sign-off, and CI triggering.

autohandai-community-skills Bundle

Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task. Use when discovering NemoClaw capabilities, choosing the right skill, or orienting in the project. Trigger keywords - skills, capabilities, what can I do, help, guide, index, overview, start here.

autohandai-community-skills Bundle

Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.

autohandai-community-skills Bundle

Guide for adding a new benchmark or training environment to NeMo-Gym. Use when the user asks to add, create, or integrate a benchmark, evaluation, training environment, or resources server into NeMo-Gym. Also use when wrapping an existing 3rd-party benchmark library. Covers the full workflow: data preparation, resources server implementation, agent wiring, YAML config, testing, and reward profiling (baselining). Triggered by: "add benchmark", "new resources server", "integrate benchmark", "wrap benchmark", "add training environment", "add eval".

autohandai-community-skills Bundle

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.

autohandai-community-skills Bundle

Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory.

sboghossian-mini-claude-for-legal Skill

Use when monitoring token and cost consumption per tenant, user, or matter across all connected LLM providers. Tracks burn rate trends, alerts when a tenant is projected to hit their plan limit within 7 days, flags abnormal per-turn costs driven by inefficient model selection or prompt bloat, and generates optimization suggestions — covering Claude, Gemini, GPT-4, and other providers.

sboghossian-mini-claude-for-legal Skill

Use when retrieving from an individual user's personal knowledge store — documents they have personally uploaded, notes they have taken, or matter-linked files associated with their account. Distinct from the firm-wide knowledge base (which is shared across the tenant) and from the public legal corpus. Invoked when a user refers to something they personally uploaded or when context suggests a personal document is relevant.

intent-solutions-io Skill

This skill enables Claude to execute clustering algorithms on datasets. It is used when the user requests to perform clustering, identify groups within data, or analyze data structure. The skill supports algorithms like K-means, DBSCAN, and hierarchical clustering. Claude should use this skill when the user explicitly asks to "run clustering," "perform a cluster analysis," or "group data points" and provides a dataset or a way to access one. The skill also handles data validation, error handling, performance metrics, and artifact saving.

intent-solutions-io Skill

This skill empowers Claude to perform feature engineering tasks for machine learning. It creates, selects, and transforms features to improve model performance. Use this skill when the user requests feature creation, feature selection, feature transformation, or any request that involves improving the features used in a machine learning model. Trigger terms include "feature engineering", "feature selection", "feature transformation", "create features", "select features", "transform features", "improve model performance", and similar phrases related to feature manipulation.

intent-solutions-io Skill

This skill enables Claude to construct and evaluate classification models using provided datasets or specifications. It leverages the classification-model-builder plugin to automate model creation, optimization, and reporting. Use this skill when the user requests to "build a classifier", "create a classification model", "train a classification model", or needs help with supervised learning tasks involving labeled data. The skill ensures best practices are followed, including data validation, error handling, and performance metric reporting.

autohandai-community-skills Bundle

Monitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters. Use when the user asks "check job status", "is my job done", "monitor my evaluation", "what's the status of the PTQ", "check on a SLURM job id", or after any skill submits a long-running job. Also triggers on "nel status", "squeue", or any request to check progress of a previously submitted job.

autohandai-community-skills Bundle

Use when creating, validating, or documenting Nemo Gym pivot datasets from rollout, trajectory, chat-completion, Responses API, or tool-call artifacts. Covers Gym Responses-style row conversion, pivot selection, single-step tool-use configs, agent_ref alignment, verifier knobs, expected-action row contracts, and train/eval usage.

gptomics Bundle

Identifies non-coding RNAs (tRNA, rRNA, snoRNA, snRNA, riboswitches, sRNAs) using Infernal covariance-model search against Rfam, tRNAscan-SE 2.0 for tRNA, barrnap for rRNA, and ARAGORN for tmRNA, plus the small-RNA-seq boundary for miRNA and the transcript-assembly boundary for lncRNA. Covers the structure-conserved-not-sequence-conserved principle (why BLAST fails), GA-threshold and clan-competition correctness, tRNAscan-SE domain modes and pseudogene flags, rDNA copy-number collapse, and why homology annotation is a recall floor. Use when performing genome-wide ncRNA annotation, choosing the right tool for an RNA class, or interpreting ncRNA counts.

gptomics Bundle

Decides whether and how to polish a draft genome assembly to raise consensus accuracy (QV) with read-type-matched tools - Racon and medaka (ONT consensus), dorado polish, Polypolish and pypolca (Illumina, repeat-aware), Pilon (legacy short-read), NextPolish/NextPolish2, Hapo-G (haplotype-aware), ntEdit, and DeepPolisher/PEPPER-Margin-DeepVariant for human. Covers the do-not-polish-HiFi rule, the medaka basecaller-model footgun, held-out Merqury QV as the only honest stop signal, and the haplotype-collapse trap. Use when correcting homopolymer indels or residual SNPs in a long-read assembly, deciding if a HiFi assembly needs polishing, or choosing an ONT vs hybrid vs short-read polishing chain.

gptomics Bundle

Builds and validates predictive time-to-event models on clinical and omics data with penalized Cox, random survival forests, gradient-boosted and deep survival models, and prediction-grade evaluation (Uno's C, time-dependent AUC, integrated Brier, calibration, competing risks). Use when building an individualized risk predictor or prognostic omics signature, choosing a survival model, or evaluating one beyond the C-index. For Kaplan-Meier, log-rank, and classical Cox hazard-ratio inference in a trial see clinical-biostatistics/survival-analysis.

gptomics Bundle

Detects differentially methylated regions (DMRs) from short-read bisulfite (WGBS/RRBS), array, and long-read methylation count tables using dmrseq (permutation region-FDR over the region selection), DSS callDMR (beta-binomial), methylKit tiles, bsseq BSmooth, DMRcate Gaussian-kernel smoothing, metilene, and comb-p. Covers why a DMR is DEFINED by arbitrary thresholds (min-CpGs, max-gap, delta-beta, q) and a smoothing bandwidth, why selecting extreme runs of CpGs then testing them on the same data is post-selection inference, why region q-values are not comparable across tools, and a single-sample domain-segmentation section (PMD, UMR/LMR, MethylSeekR, solo-WCGW) that must run before focal calling on cancer/aging genomes. Use when calling region-level methylation differences, choosing a DMR caller, controlling region-level FDR, or segmenting megabase methylation domains. For per-site testing see differential-cpg-testing; for the methylKit object model see methylkit-analysis.

sboghossian-mini-claude-for-legal Skill

Use when assessing whether AI-generated legal output may constitute unauthorized practice of law (UPL) in a given jurisdiction, or when configuring the appropriate output mode (consumer-informational vs. lawyer-supervised) for a given user. Covers ABA Model Rule 5.5 and its analogs in US states, Lebanon, Saudi Arabia, UAE (onshore and DIFC/ADGM), UK, and France. Defines the line between permissible legal information and impermissible legal advice, and the acts AI must never perform (court appearance, pleading filing, client representation).

sboghossian-mini-claude-for-legal Skill

Use when retrieving from the indexed corpus of public legal texts — court judgments (DIFC, ADGM, UK, US, EU), statutes, official gazettes, and regulatory instruments — to support legal research, precedent finding, or statute verification. Organized as per-jurisdiction indexes. Lower precedence than firm KB and personal KB; complements premium databases. Best for DIFC/ADGM case law, GCC statutes, and curated public corpora not fully covered by Westlaw or LexisNexis.

yongjianwan Skill

通用深度研究Agent。类似ChatGPT Deep Research / MiroThinker的Interactive Scaling模式。适用于任何需要"搞清楚"而非"快速回答"的问题：企业分析、产品调研、合同条款、技术评估、舆情调查、冷门问题等。会消耗大量token，换取结论可靠性。触发词："深度研究"、"帮我查清楚"、"详细调查"、"认真分析一下"、"用research模式"。

gptomics Bundle

Tests whether a proposed or predicted RNA secondary structure is supported by evolutionary covariation using R-scape, which scores compensatory substitutions against a phylogeny-aware null and estimates the statistical power of the alignment. Use when validating a conserved-structure claim before trusting it (the test that found no support for HOTAIR/Xist/SRA lncRNA structures); separating real covariation from phylogenetic correlation; deciding whether an alignment even has the power to test structure; or building a covariation-supported consensus (CaCoFold) to seed a covariance model or folding.

gptomics Bundle

Integrate multimodal single-cell data (CITE-seq RNA+protein, 10x Multiome RNA+ATAC, unpaired/diagonal RNA+ATAC) and choose the right joint method. Use when classifying an integration task by anchor structure (paired vs unpaired), denoising CITE-seq ADT background before joint embedding, picking between WNN, totalVI, MultiVI, MOFA+, GLUE, or Seurat v5 bridge integration, or diagnosing why a modality dominates a joint clustering.

sboghossian-mini-claude-for-legal Skill

Use when building or configuring the PII redaction layer that sanitizes user-submitted text before it is sent to an LLM or stored in a database. Covers entity detection patterns, redaction strategies, audit logging, and reconstruction for legal AI pipelines where client-confidential data must never leak into training or third-party model calls.

sboghossian-mini-claude-for-legal Skill

Use when migrating a GDPR personal-data breach sentinel skill into the mini-claude-for-legal format. The adapter maps legacy breach-detection logic — severity scoring, the 72-hour supervisory-authority notification clock, data-subject communication triggers, and cross-border lead-authority routing — into the standard skill model. Covers EU GDPR, UK GDPR, UAE PDPL, and analogous MENA data-breach regimes.

sboghossian-mini-claude-for-legal Skill

Use when migrating the Jamie Tso NDA review methodology into the mini-claude-for-legal format. This adapter preserves structured NDA review logic — mutual vs unilateral framing, confidentiality scope analysis, residuals clauses, permitted disclosures, and enforceability traps — mapped into the standard skill model. Particularly strong for technology-sector NDAs in DIFC, ADGM, UK, and US-influenced common-law drafting contexts.

sboghossian-mini-claude-for-legal Skill

Use when migrating an NDA triage skill originally built for the Anthropic Claude API into the mini-claude-for-legal format. The adapter maps legacy NDA intake logic — mutual vs unilateral detection, risk-level scoring, accept/negotiate/reject routing, and expedited-review flags — into the standard skill model. Triggers on import of any Anthropic-native NDA screening or intake workflow.