Research

Elite AI/ML Senior Engineer with 20+ years experience. Transforms Claude into a world-class AI researcher and engineer capable of building production-grade ML systems, LLMs, transformers, and computer vision solutions. Use when: (1) Building ML/DL models from scratch or fine-tuning, (2) Designing neural network architectures, (3) Implementing LLMs, transformers, attention mechanisms, (4) Computer vision tasks (object detection, segmentation, GANs), (5) NLP tasks (NER, sentiment, embeddings), (6) MLOps and production deployment, (7) Data preprocessing and feature engineering, (8) Model optimization and debugging, (9) Clean code review for ML projects, (10) Choosing optimal libraries and frameworks. Triggers: "ML", "AI", "deep learning", "neural network", "transformer", "LLM", "computer vision", "NLP", "TensorFlow", "PyTorch", "sklearn", "train model", "fine-tune", "embedding", "CNN", "RNN", "LSTM", "attention", "GPT", "BERT", "diffusion", "GAN", "object detection", "segmentation".

Use this whenever a user wants to add a new feature or explitly states to research a feature/API or building a plan for a new feature. It iterviews the user for feature details (if not provided), research the best API/service for their needs, confirm choice, then gather all implementation notes for their request and save them as a .claude/plans file.

This skill should be used when setting up email OTP authentication with JWT sessions, password management, rate limiting, CSRF protection, and audit logging in a Next.js application. Use this skill when implementing a production-ready authentication system that matches the reference implementation pattern with Resend email, Prisma ORM, PostgreSQL, bcrypt password hashing, and jose JWT tokens.

Build React components using @fpkit/acss library patterns. Scaffolds complete component structures (tsx, types, scss, stories, tests), validates CSS variables follow naming conventions (--component-property with rem units), enforces TypeScript patterns, accessibility standards (WCAG 2.1 AA), and Storybook documentation. Use when building new components, generating boilerplate, or refactoring to use fpkit primitives. Includes automation scripts, reference guides, and templates.

Master dialectical methodology - Socratic, Hegelian, and Marxist dialectics. Use for: dialogue, thesis-antithesis-synthesis, contradiction, development. Triggers: 'dialectic', 'dialectical', 'thesis antithesis', 'Aufhebung', 'sublation', 'Socratic', 'Hegelian', 'contradiction', 'synthesis', 'negation', 'development', 'elenchus'.

Systematic analysis framework for articles, papers, and long-form content using 5 proven thinking models (McKinsey Communication Framework, Comprehensive Task Checklist, Critical Thinking, Inversion Thinking, Systems Thinking).

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

PDF-RAG API reference. REQUIRED after any failed curl/jq to localhost:8000 (404, null, jq error). Also use when uncertain about endpoint path or response shape.

Calculate statistical power and required sample sizes for research studies. Use when: (1) Designing experiments to determine sample size, (2) Justifying sample size for grant proposals or protocols, (3) Evaluating adequacy of existing studies, (4) Meeting NIH rigor standards for pre-registration, (5) Conducting retrospective power analysis to interpret null results.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

Pine Script v5/v6 indicator scaffold and patterns. Provides structure guidance and triggers doc-researcher for current syntax verification. Use when developing TradingView indicators.

Reads and extracts content from Arxiv HTML papers for Q&A. Use when the user shares an Arxiv HTML link (arxiv.org/html/...) or asks about a paper from Arxiv.

Extract and maintain company-specific coding best practices from PR review comments. Use when the user requests to analyze PR comments from a repository to generate best practices documentation, or when implementing features and needs to reference established coding standards. Triggers include requests like "analyze PR comments and create best practices", "extract coding standards from repo X", or "check if this code follows our best practices".

Internal resource library for HeyReach integration. Contains shared API client, operation scripts, and reference documentation.

Build pre-launch landing pages for product concept validation. Use when Factory agent needs to create Astro sites for demand validation, waitlist capture, or early access signups. Reads Scout handover for market research and competitor patterns. Covers hero selection, visual system, component assembly, copy framework, and conversion optimization. NOT for product interfaces or post-launch pages.

ARCHIVE REFERENCE ONLY. Superseded by modular skills (`mds-messaging-direction-summary`, `voice-and-tone`, `product-positioning-summary`). Use as inspiration; do not invoke in orchestrated flow.

Teaches how to use Bluera Knowledge for accessing library sources and reference material. Explains two approaches - vector search via MCP/slash commands for discovery, or direct Grep/Read access to cloned repos for precision. Shows when to use each method and example workflows for querying library internals.

Comprehensive guide for writing technical books in Markdown format. Use this skill when creating new chapters, managing code examples, reviewing content for technical accuracy and consistency, or organizing book structure (TOC, cross-references). Provides templates, validation scripts, and best practices for technical writing workflows.

Format citations and bibliographies in multiple academic styles (APA, IEEE, Chicago, Harvard, MLA, Nature, Science). Use when: (1) Converting between citation styles for different journals, (2) Cleaning and standardizing bibliography entries, (3) Validating citation formatting before submission, (4) Generating properly formatted reference lists, (5) Checking citation consistency across manuscripts.

Use when creating or editing agent definitions - ensures proper frontmatter, clear structure, validation of references, and no duplication with existing agents