Results for “quality”

Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis.

Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis.

Build production-quality user interfaces that are accessible, performant, and visually polished, with guidance on component architecture, state management, design system adherence, and accessibility.

Runs a multi-phase verification pipeline including build, type-check, lint, tests, security scan, and diff review to ensure code quality before creating a PR.

Evaluates Power BI data model architecture, relationships, storage modes, and performance to identify optimization opportunities and ensure adherence to best practices.

Integrate Trivy vulnerability scanning into CI/CD pipelines to detect container image CVEs, Dockerfile misconfigurations, and enforce severity-based quality gates.

Review AI agent skills using a dual-axis method: deterministic code-based checks and LLM deep review, with weighted scoring and improvement recommendations.

Applies universal TypeScript, JavaScript, React, and Node.js quality conventions for this repo. Use when reviewing or writing TS/TSX, refactoring for clarity, or enforcing naming, immutability, and error-handling patterns.

Search scientific papers via the BGPT MCP server and retrieve structured experimental data — methods, results, conclusions, quality scores, and 25+ metadata fields per paper.

Create interactive, publication-quality visualizations with 40+ chart types, hover, zoom, pan, and web embedding. Choose between Plotly Express and Graph Objects for dashboards, exploratory analysis, and presentations.

Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis.

Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.

Configure Maven, Gradle, and static analysis for Java projects. Use for Java-only build and quality tooling such as Spotless, Checkstyle, SpotBugs, SonarLint, JDK versions, and Java service Dockerfiles; defer Kotlin, Android, Flutter, and GitHub Actions-specific configuration.

Build or upgrade web forms to production quality: accessible structure, schema-driven validation, client↔server parity. Use when "improve this form", "form validation", "accessible form", "multi-step form", "form error handling", or "the form UX is bad".

Use when profiling, diagnosing, or improving Three.js or WebGL game performance without regressing gameplay—frame-time drops, CPU/GPU pressure, draw calls, texture/geometry budgets, animation loops, adaptive quality, mobile performance, and browser performance verification.

Enrich CRM records with firmographic and contact data, filling gaps in company and person profiles to improve segmentation, routing, and outreach quality. Use when the user requests crm data enrichment or provides relevant inputs for this workflow.

Run multiple AI agents against a product, SDK, or docs site to score setup friction, speed, efficiency, error recovery, and doc quality from a minimal prompt.

Uses a multi-agent generator-evaluator feedback loop to build high-quality applications from a single prompt, inspired by GANs and Anthropic's harness design.

Write high-quality YARA-X detection rules for malware identification, covering naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction.

Reduces SOC alert fatigue by tuning detection rules, consolidating duplicate alerts, implementing risk-based alerting, and measuring alert quality metrics to maintain analyst effectiveness.

Model software around the business domain using bounded contexts, aggregates, and ubiquitous language, with scoring and diagnostic tools for evaluating domain model quality.

Guides the creation of high-quality MCP servers that let LLMs interact with external services through well-designed tools, covering planning, implementation, testing, and evaluation.

Takes raw whole-genome sequencing FASTQ files or a pre-existing VCF through variant calling, quality control, and polygenic risk score computation using the PGS Catalog.

Analyzes a single webpage's SEO across on-page elements, content quality, technical meta tags, schema, images, and performance, producing a scored report with prioritized issues and recommendations.

Audit project and global memory for bloat, stale decisions, duplicates, contradictions, unsafe content, missing provenance, broken routing, and over-budget global files. Load when the user asks to audit memory, clean memory, check memory health, or verify memory quality.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Retrieval-Augmented Generation pipelines — ingestion, chunking, embedding, vector stores, retrieval, evaluation. Use when building a RAG pipeline, choosing chunking strategies or embedding models, debugging retrieval quality or hallucinations, evaluating an existing RAG system, or scaling/migrating vector stores.

Create Beamer-style academic PPTX presentations using python-pptx. Produces publication-quality .pptx files with navy-blue Metropolis theme (16:9, frame title bars, progress bar) for conference talks, job market presentations, and seminar slides. Called by /present command.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Create interactive, publication-quality visualizations with 40+ chart types, including scatter, bar, line, 3D, maps, and financial charts, with support for hover, zoom, pan, subplots, and export to HTML or static images.

Review PostgreSQL code for best practices, anti-patterns, and quality standards including JSONB, arrays, custom types, schema design, functions, and security features like Row Level Security.

Provides production-grade techniques for evaluating LLM outputs using LLMs as judges, covering direct scoring, pairwise comparison, bias mitigation, rubric generation, and confidence calibration.

Generate high-quality sentence and text embeddings for semantic similarity, clustering, and retrieval using 5000+ pre-trained models. Supports multilingual and domain-specific embeddings for RAG and semantic search.

Creates interactive, publication-quality visualizations in Python with 40+ chart types, including scatter, bar, heatmap, 3D, and financial charts, plus subplots, styling, and export to HTML or static images.

Creates a GitHub pull request with an auto-generated summary, running mandatory pre-commit and code-quality review gates, plus optional deep-review subagents, and posts findings into the PR body.