Research

MCP-powered domain research for requirements elicitation. Uses perplexity, context7, firecrawl, and other MCP servers to research domain knowledge, best practices, and industry requirements.

Complex research requiring deeper analysis, multi-step reasoning, and sophisticated source evaluation for technical, academic, or specialized domain queries needing expert-level analysis, high-stakes decisions, or multi-layered problem solving.

Structured reasoning tools for complex problem analysis with observation, hypothesis, analysis, and conclusion steps. Use when analyzing complex problems, debugging difficult issues, or making important decisions.

Implement AI/ML research papers from scratch when no official code exists. Use when the user wants to reproduce a paper, implement an algorithm from a PDF, build a model architecture from a research paper, or create working code from academic publications. Handles papers from arXiv, NeurIPS, ICML, ICLR, CVPR, and other venues. Produces UV-managed, GPU-ready Python projects with tests, demos, and documentation.

Search GitHub issues, pull requests, and discussions across any repository. Activates when researching external dependencies (whisper.cpp, NAudio), looking for similar bugs, or finding implementation examples.

Create educational documents that build understanding progressively with citations

The complete Swift Programming Language book by Apple, covering syntax, features, concurrency, and the formal language reference.

SwiftUI UI component catalog. Use when implementing NavigationStack, Swift Charts, PhotosPicker, TipKit, ScrollView enhancements, animations, layouts, WebView, Liquid Glass and other UI components. Organized by feature category with OS version compatibility info. Reference for discovering available components and implementation patterns.

Provides Jobs-to-be-Done and psychographic research frameworks for brand identity work. Auto-activates during brand positioning, voice development, messaging, and strategy phases. Use when discussing target audience, customer research, JTBD, jobs to be done, four forces, push pull anxiety habit, emotional jobs, social jobs, functional jobs, limbic types, VALS segments, psychographics, or customer motivations.

This skill should be used when validating whether a specific word or phrase is appropriate, commonly used, and correct in academic technical contexts. Use for checking terminology in research papers targeting top-tier computer science conferences.

Index of Mechanic documentation with summaries and links. Load this to understand what documentation exists and where to find detailed information on specific topics. Triggers: docs, documentation, reference, guide, help.

Add a research paper to the maxpool research-papers collection. Use when the user provides an ArXiv URL, PDF link, or asks to add/summarize a research paper for the website. Handles paper fetching, insight extraction, HTML generation, and index updates.

研究與資訊蒐集。觸發：research, investigate, compare, evaluate, analyze, explore, 研究, 比較, 分析, 調查

Expert guidance for Design of Experiments (DOE) in Python - interactive goal-driven design selection, classical DOE (factorial, response surface, screening), Bayesian optimization with Gaussian processes, model-driven optimal designs, active learning, and sequential experimentation; includes pyDOE3, pycse, GPyOpt, scikit-optimize, statsmodels

Comprehensive LaTeX reference with commands, templates, and troubleshooting for document typesetting

Use GitHub CLI (gh) to interact with GitHub repositories, pull requests, issues, and workflows. Use when: (1) Reading PR details, diffs, or metadata, (2) Listing or filtering PRs and issues, (3) Creating PR comments or linking to issues, (4) Checking CI status or mergeability, (5) Extracting issue references from PR descriptions, or (6) Any GitHub repository operation via command line. Requires GitHub CLI installed and authenticated.

This skill should be used when suggesting word or phrase alternatives for placeholders in academic research papers. Use when the author needs help selecting appropriate technical terminology for top-tier computer science conferences.

Central authority for Gemini CLI Checkpointing. Covers git-based file snapshots, automatic state saving, /restore command, and rollback. Use when enabling checkpointing, restoring previous states, undoing changes, or planning experimental workflows with Gemini. Delegates 100% to gemini-cli-docs for official documentation.

Complete Git expertise system for ALL git operations. PROACTIVELY activate for: (1) ANY Git task (basic/advanced/dangerous), (2) Repository management, (3) Branch strategies and workflows, (4) Conflict resolution, (5) History rewriting/recovery, (6) Platform-specific operations (GitHub/Azure DevOps/Bitbucket), (7) Advanced commands (rebase/cherry-pick/filter-repo). Provides: complete Git command reference, safety guardrails for destructive operations, platform best practices, workflow strategies, reflog recovery techniques, and expert guidance for even the most risky operations. Always asks user preference for automatic commits vs manual control.

Research external topics, create comprehensive analysis, determine project applicability, and incorporate learnings into Serena and Forgetful memory systems. Transforms knowledge into searchable, actionable project context.