
--- name: interactive-research description: Multi-source research orchestrated across a persistent agent team. Use for queries asking for research-style investigation of a topic — comparing, contrasting, surveying, investigating, evaluating, deeply researching, doing a literature review, or any similar research intent — or that ask what people are saying publicly about a topic (discourse, expert opinion, industry consensus, and related framings). Example phrasings (illustrative, not exhaustive):
Expert-level guidance for creating high-quality Claude Code skills. Use alongside Anthropic's skill-creator when creating new skills, improving existing skills, or needing guidance on skill content quality. Complements basic skill mechanics with research-driven content development, XML tag structuring, decision frameworks over mechanics, cross-references between skills, and systematic validation.
--- name: deep-research description: Deprecated name; the skill formerly here is now opinionated-research:interactive-research. Retained as a context-level notice because Claude Code now ships a built-in deep-research workflow that runs one-shot, non-interactive fan-out research (no conversation after the report). interactive-research instead runs a persistent agent team you can keep questioning once the report lands. Guidance for Claude: when the user makes a research request, ask whether they
Fish shell scripting judgment frameworks and critical idioms. Use when writing Fish scripts or shell automation. Focuses on when to use Fish vs bash, macOS/Fedora compatibility requirements, and Fish-specific patterns that prevent bugs (universal variable anti-patterns, wrapper functions, interactive guards).
Logic programming thinking patterns and relational design principles. Use when working with logic languages (Prolog, miniKanren, Datalog, OWL2, Answer Set Programming) or applying declarative, constraint-based approaches in multi-paradigm systems.
macOS-specific development patterns, platform APIs, and decision frameworks. Use when developing Mac apps, macOS applications, Cocoa/AppKit code, or making SwiftUI vs AppKit decisions. Covers NSWindow management, NSDocument architecture, sandboxing, code signing, notarization, and macOS UI patterns. Applies to Mac Catalyst considerations.
Python-specific idioms, philosophy, and expert-level patterns. Use when working with Python code, including Jupyter notebooks (.ipynb). Covers Pythonic thinking, common pitfalls from other language backgrounds, testing ecosystem navigation, type hints trade-offs, and when to use modern Python features.
Pedagogical framework for teaching programming through Socratic dialogue. Use when a learner wants to LEARN programming rather than have code written for them. Triggers include "teach me", "help me understand", "I'm learning", "tutor mode", or requests to not provide solutions. Emphasizes productive struggle, graduated hints, metacognitive scaffolding, and emotional support.
Swift-specific idioms, tooling, and philosophy. Use when working with Swift code. Emphasizes protocol-oriented programming, value semantics, strict concurrency (Swift 6+), and compile-time safety guarantees.
Systematic framework for rigorous, situationally-grounded decision analysis. Use when evaluating options with competing benefits where stated values may diverge from actual situational worth, when structural constraints rule out entire categories of value, or when the user wants a documented analytical process rather than a quick answer. Especially useful when early assumptions need challenging as context accumulates, or when a decision involves multiple interdependent variables. Load alongside opinionated-software-engineering:software-engineer for technical and architectural decisions.
SWI-Prolog-specific tooling, standards, and idioms. Use when working with SWI-Prolog code. Emphasizes relational thinking, steadfastness, DCGs, constraints, and mandatory testing with PlUnit.
Git commit standards, branch strategy, and LLM-assisted development workflows. Use when making commits, managing branches, or working in high-velocity LLM-assisted development contexts. Covers atomic commits, conventional commits, branching strategies (trunk-based, GitHub flow), merge vs rebase decisions, and recovery patterns.
Object-oriented design principles, patterns, and practices. Use when working with object-oriented languages (Java, C#, C++, Python, Ruby, Swift, etc.) without language-specific skills available, or when applying OOP in multi-paradigm codebases.
Core TDD philosophy and testing principles. Use when writing tests interactively or need testing guidance. Emphasizes tests as contracts, mock boundaries not internals, and implementation fixes over test changes.
Java-specific tooling, documentation standards, testing practices, and modern idioms. Use when working with Java code or Java-based projects on the JVM.
Racket-specific tooling, libraries, idioms, and language-oriented programming philosophy. Use when working with Racket code. Emphasizes LOP, contracts, macros, and design methodology.
Core software engineering philosophy and design principles based on Structure and Interpretation of Computer Programs (SICP). Use for all software development tasks including writing code, designing systems, refactoring, or making architectural decisions. MUST ALWAYS be loaded when working on any kind of software development or design task!
Clojure-specific philosophy, idioms, and judgment frameworks. Use when working with Clojure code. Emphasizes data-oriented design, runtime validation with spec, REPL-driven development, and the philosophy of simplicity over ease.
Functional programming principles, patterns, and practices. Use when working with functional languages (Racket, Clojure, Erlang, Haskell, Idris, Scheme, OCaml, F#, Elixir, etc.) without language-specific skills available, or when applying functional paradigms in multi-paradigm languages.