social-science-claude-scholar

Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, and Socratic guided modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review.

Use ONLY when creating NEW registrable components in ML projects that require Factory/Registry patterns. ✅ USE when: - Creating a new Dataset class (needs @register_dataset) - Creating a new Model class (needs @register_model) - Creating a new module directory with __init__.py factory - Initializing a new ML project structure from scratch - Adding new component types (Augmentation, CollateFunction, Metrics) ❌ DO NOT USE when: - Modifying existing functions or methods - Fixing bugs in existing code - Adding helper functions or utilities - Refactoring without adding new registrable components - Simple code changes to a single file - Modifying configuration files - Reading or understanding existing code Key indicator: Does the task require @register_* decorator or Factory pattern? If no, skip this skill.

This skill should be used when the user asks to "debug this", "fix this error", "investigate this bug", "troubleshoot this issue", "find the problem", "something is broken", "this isn't working", "why is this failing", or reports errors/exceptions/bugs. Provides systematic debugging workflow and common error patterns.

Use when the user asks to "implement DID", "run difference-in-differences", "set up IV regression", "instrumental variables", "run RDD", "regression discontinuity", "synthetic control", "staggered treatment", "Callaway-Sant'Anna", "Sun-Abraham", "event study", "parallel trends test", "first stage", "Bartik instrument", "shift-share IV", "write Stata regression code", "convert Stata to Python", "use statsmodels", "use linearmodels", "use econml", "panel data regression", "fixed effects", "two-way fixed effects", "cluster standard errors", or any causal inference methodology in Python or Stata.

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

Daily coding assistant that auto-triggers when writing/modifying code, providing a core checklist. ✅ Trigger scenarios: - Implementing new features, adding code, modifying existing code - User requests "write a...", "implement...", "add...", "modify..." - Any coding task involving Edit/Write tools ❌ Does not trigger: - Pure reading/understanding code (no modification intent) - Already covered by specialized skills (bug-detective, architecture-design, tdd-guide) - Configuration file changes, documentation writing

Use when the user asks to "generate daily paper", "find recent papers", "search NBER working papers", "find new econ papers", "find new polisci papers", "search arXiv economics", "check journal updates", "what's new in political economy", "find papers on causal inference", "find papers on text as data", or wants paper summaries in comparative politics, political economy, political institutions, public economics, or economic history.

This skill should be used when the user asks to "run data analysis", "analyze this dataset", "regress Y on X", "run the main regressions", "produce tables and figures", "end-to-end analysis", "write analysis script", "set up panel regression", "exploratory data analysis", or "produce publication-ready output". Provides end-to-end data analysis workflow for social science research in Python (primary) or Stata, from data loading through publication-ready tables and figures.

This skill should be used when the user asks to "play devil's advocate", "challenge my identification", "what are the weaknesses in my paper", "adversarial critique", "stress test my argument", "find holes in my research design", "what would a hostile referee say", or "challenge my empirical strategy". Produces 5-7 specific adversarial challenges targeting the identification strategy, theoretical mechanism, and empirical design of a research project.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", "version control for research", "git for data analysis", "how to track analysis scripts", "version analysis code", "commit Stata do files", "commit Python scripts", "research project git structure", or asks about git branching strategies, version control best practices, pull request workflows.

Use this skill when the user asks to "research background on", "find background information about", "search web for context on", "look up policy history of", "find grey literature on", "research institutional context", "find government reports on", "background research for introduction section", "research country context", "web research on", "autonomous web search", "deep research on", "find sources about", or needs web-sourced background context for academic writing (political economy, comparative politics, economic history, public policy). Complements Zotero/arXiv for web-accessible grey literature and policy documents.

This skill should be used when the user asks to "interview me about my research", "help me formalize my research idea", "ask me questions about my project", "Socratic research discussion", "help me develop my research question", or "research spec". Conducts a structured Socratic interview to formalize a research idea into a specification document with hypotheses, identification strategy, and data plan.

This skill should be used when the user asks to "review paper quality", "self-review before submission", "check paper completeness", "score my paper", "validate paper structure", "check identification strategy", "pre-submission review", or "run quality check on paper". Provides systematic 0-100 scored review for economics and political science papers before advisor review or journal submission.

Use when the user asks to "prepare replication package", "create replication files", "AER replication standards", "APSR replication requirements", "organize code for submission", "data availability statement", "make research reproducible", "package data and code", "openICPSR submission", "dataverse upload", "write data README", "code README for replication", "clean up code for publication", or "submit replication materials".

This skill should be used when the user asks to "analyze empirical results", "generate results section", "interpret regression output", "create regression tables", "visualize DID results", "plot event study", "check pre-trends", "first stage F-statistic", "run robustness checks", "interpret causal estimates", or mentions connecting empirical analysis to social science paper writing. Covers DID, IV, RDD, and Synthetic Control designs.

This skill should be used when the user asks to "review this paper", "give referee report", "simulate peer review", "what would a referee say", "critique this manuscript", "review paper for AER/APSR", "manuscript review", or "find weaknesses in this paper". Produces a detailed structured referee report covering identification, econometrics, literature, and writing — the kind a top-5 journal referee would write.

This skill should be used when the user asks to "analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", or "generate quality report". Evaluates local skills across description quality, content organization, writing style, and structural integrity.

Use when the user asks to 'write a political science paper', 'draft an economics paper', 'write intro/theory/empirics/conclusion section', 'write for APSR', 'write for AER', 'write for JOP', 'draft identification strategy section', 'write robustness section', 'write theory section with hypotheses', 'write data section', 'write results section', 'write paper for top journal', 'polish academic writing', 'improve paper structure', 'APSR submission', 'AER submission', 'draft literature review', or 'write abstract'. Supports two tracks: Economics (AER/QJE/JPE style) and Political Science (APSR/AJPS/JOP style).

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.