Research

Apply systematic four-phase debugging methodology (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures thorough understanding before attempting solutions, preventing random fixes and reducing debugging time from hours to minutes. Use this skill when encountering any test failures in test suites (Jest, pytest, RSpec, JUnit, Go testing), when production bugs are reported or discovered, when code produces unexpected output or behavior different from requirements, when experiencing build failures or compilation errors, when integration tests fail due to component interaction issues, when performance problems or slowdowns are detected, when encountering race conditions, timing issues, or intermittent failures, when error messages or stack traces appear in logs or console output, when refactoring causes existing tests to fail, when you've already attempted one or more fixes that didn't resolve the issue, when deployment or CI/CD pipelines fail, when you're tempted to make a

Expert assistant for using litdb - a literature and document database for scientific research

Standards and guidelines for organizing, structuring, and maintaining documentation in the PRPM repository - ensures consistency across user docs, development docs, and internal references

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Applies the Diataxis framework to create or improve technical documentation. Use when being asked to write high quality tutorials, how-to guides, reference docs, or explanations, when reviewing documentation quality, or when deciding what type of documentation to create. Helps identify documentation types using the action/cognition and acquisition/application dimensions.

Move or rename a file while automatically updating all references in source code and documentation

Post-process LaTeX project prose to improve readability through varied sentence and paragraph lengths. Removes filler phrases and unnecessary transitions while preserving all citations and semantic meaning.

Write LaTeX ML/AI review articles for arXiv using the IEEEtran template and verified BibTeX citations.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

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.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Use this skill when the user asks to add documentation, add docs, add references, or install documentation about Neon. Adds Neon best practices reference links to project AI documentation (CLAUDE.md, AGENTS.md, or Cursor rules). Does not install packages or modify code.

Product discovery and requirements analysis specialist. Conducts stakeholder interviews, market research, problem discovery, and creates product briefs. Use for product brief, brainstorm, research, discovery, requirements gathering, problem analysis, user needs, competitive analysis, and setting foundation before product planning. Hands off to product manager when analysis complete.

Brainstorming and research automation specialist

Facilitates structured brainstorming sessions, conducts comprehensive research, and generates creative solutions using proven frameworks. Trigger keywords - brainstorm, ideate, research, SCAMPER, SWOT, mind map, creative, explore ideas, market research, competitive analysis, innovation, problem solving, feature generation

Example skill demonstrating secure file reference resolution with supporting files

Validate blog posts for quality, consistency, en-GB spelling, and ScottInk style. Use when reviewing posts before publication.

Lint content for spelling errors, en-GB compliance, and writing quality. Use when checking markdown files before publication.