Results for “pre-pr”

Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs.

Use when incorporating information from research, references, or external sources. This skill provides verification procedures to ensure information used in deliverables is accurate, current, and from authoritative sources, preventing hallucination and misinformation.

Serve LLMs and VLMs on NVIDIA Jetson devices using vLLM or SGLang with optimized Docker containers and quantization presets.

Submits TAO container jobs as single-pod Kubernetes Jobs with NVIDIA GPU scheduling on EKS, GKE, AKS, or on-prem clusters.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than relying on arbitrary auto-compaction.

Build and evaluate machine learning models using scikit-learn for classification, regression, clustering, dimensionality reduction, and preprocessing.

Formulate testable hypotheses from observations, design experiments, and generate predictions using a structured scientific method framework.

Generate PPTX presentations, DOCX documents, XLSX spreadsheets, and PDF reports from structured JSON input using PaperJSX.

Enforces a strict efficiency ladder—YAGNI, reuse, stdlib, native platform, existing deps—before writing any new code, preventing over-engineering and unnecessary dependencies.

Validates observable behavior of apps, CLIs, APIs, and generated artifacts against a prewritten contract without inspecting source code.

Runs meetings effectively: classifies meeting types, prepares agendas, facilitates discussions, captures decisions and actions, and audits recurring meetings to fix poor meeting culture.

Construye pipelines ETL/ELT con Pandas: extracción, transformación y carga de datos con logging, manejo de errores, idempotencia y opciones de orquestación.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Translates a Chinese article into English Markdown, generates bilingual detailed summaries, and writes the results back to LanceDB while preserving structure.

Installs and configures MariaDB Connector/C++ across Linux, Windows, and source builds, covering prerequisites, linking, and runtime plugin setup.

Sends email messages via Gmail with support for attachments, CC/BCC, HTML content, send-as aliases, drafts, and dry-run previews.

Reference for SOC 2, PCI-DSS, HIPAA, and GDPR compliance requirements, including control checklists, evidence collection, and audit preparation guidance.

Explains how Agent Script instruction resolution works across three phases, with patterns for pre-LLM setup, LLM reasoning, and post-action loops.

Reduce high-dimensional data with UMAP for visualization, clustering preprocessing, and supervised or semi-supervised learning, including parameter tuning guidance.

Evaluates how well internal model representations (hidden states) predict token-level information importance in summarization tasks, using NDCG@10 and Spearman's rank correlation.

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

Interactive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualization.

Runs a relentless interview that sharpens a plan or design. Use when the user wants to be grilled on an idea, pressure-test a plan, or refine a design through questioning.

Build educational TypeScript vanity-address tooling for Pump.fun/Solana wallets with @solana/web3.js, async generators, event-loop yielding, prefix/suffix matching, batch search, and best-effort memory zeroization.

Build, preview, and deploy websites, web apps, and APIs using Vercel, Railway, GitHub Pages, or local Canvas environments. Use when a user needs general web deployment guidance across common hosting targets.

Interactive onboarding wizard that generates agency.config.json for any B2B agency. Asks structured questions about the agency, services, ICP, tools, outreach preferences, and CRM setup. Outputs a complete config file.

Legacy-project style inheritance skill. Use when the user types /inherit-legacy-style, or when onboarding an AI coding agent onto a hand-written legacy project and you need to prevent "style drift" (the model imposing its pretrained mainstream idioms onto the project). Language- and framework-agnostic — it aligns meta-architecture only, not syntax. Once run, it becomes a behavioral constraint on all subsequent coding tasks. Do NOT use for pure research or one-off questions unrelated to code-style alignment.

Query the STRING API for protein-protein interactions (59M proteins, 20B interactions across 5000+ species), building interaction networks, discovering functional partners, and running GO/KEGG/Pfam enrichment on protein lists. Use when constructing a protein-protein interaction network, expanding from seed proteins to functional partners, or running PPI-based enrichment for systems biology; for curated metabolic pathway maps and reactions prefer alterlab-kegg, and for protein sequences, annotations, or accession ID mapping prefer alterlab-uniprot instead. Part of the AlterLab Academic Skills suite.

Integrate FIRST's Exploit Prediction Scoring System (EPSS) API to prioritize vulnerability remediation based on real-world exploitation probability within 30 days.

Hardens code against vulnerabilities by applying threat modeling, OWASP Top 10 prevention patterns, and secure coding practices for web applications.

Guides completion of development work by verifying tests, detecting the environment, and presenting structured options for merging, creating a PR, or discarding changes.

Write, review, and migrate code using NVIDIA DALI's imperative dynamic-mode API for efficient data loading and preprocessing.

Intercepts responses to let users choose the depth and token budget before answering, with heuristic token estimation and preset depth levels.

Builds production-ready frontend pages with premium UI design, cinematic animations, AI-generated media assets, persuasive copywriting, and generative art.

Maps FHIR R4 clinical resources (Patient, Observation, Condition, CarePlan, CodeableConcept) to Salesforce Health Cloud objects, including prerequisite configuration and cardinality handling.

Audits hidden assumptions in decisions by classifying them, ranking by fragility and impact, and rebuilding conclusions from verified premises. Auto-detects Chinese or English input.