Research

Generates a rigorous experiment design given a hypothesis. Use when asked to design experiments, plan experiments, create an experimental setup, or figure out how to test a research hypothesis. Covers controls, baselines, ablations, metrics, statistical tests, and compute estimates.

Professional technical documentation specialist that creates clear, comprehensive documentation including API references, user guides, READMEs, integration guides, and developer tutorials

Orchestrate multiple frontier LLMs (Claude, GPT-5.1, Gemini 3.0 Pro, Perplexity Sonar, Grok 4.1) for comprehensive research using LLM Council pattern with peer review and synthesis

AI-driven development planning skill that produces TDD-ready specifications using research-backed methodologies (Plan-then-Act, Reflexion, ToT/LATS, ReAct).USE THIS SKILL PROACTIVELY when:- User requests a feature implementation- User reports a bug that needs fixing- User asks for code refactoring- Task involves multiple files or components- Requirements need clarification before coding- You need to create a comprehensive development planThis skill implements the complete planning pipeline: repo analysis → test-first design → structured plan generation → self-critique → TDD handover specification.OUTPUT: Structured TDD Handover Spec (JSON + Markdown) ready for TDD agent consumption.

VaultCPA database schema reference with 50+ Prisma models, relationships, and query patterns. Use when working with database models, designing features, or understanding data structure.

Review, audit, and fix CLAUDE.md to ensure it meets quality standards.TRIGGERS - Use this skill when user says:- "review claude.md", "review the claude.md"- Any request to check CLAUDE.md quality or find issuesAlso use when:(1) Verifying CLAUDE.md references match actual project structure(2) Checking for stale or outdated content(3) Auditing formatting quality and consistency(4) CLAUDE.md exceeds 600 lines (MUST condense)(5) Analyzing individual section sizes and making them concise(6) Detecting content that duplicates skills in `.claude/skills/`This skill reports issues AND implements all fixes to bring CLAUDE.md to standard.

Product Management frameworks, methodologies, and best practices library. Provides PM knowledge including prioritization (RICE, MoSCoW), goal setting (OKR, SMART), customer research (JTBD, Personas), and product strategy. Use when needing PM methodology guidance or framework application.

Complete reference for all 35+ PubMed Search MCP tools. Triggers: 工具列表, all tools, 完整功能, tool reference, 有哪些工具

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

Extract text from PDF files with intelligent chunking and metadata preservation. IMPORTANT - For best results, first convert PDFs to markdown using OpenAI Codex (see pdf skill), then process the markdown. Also supports direct PDF text extraction for batch processing, technical documents, standards libraries, research papers, or any PDF collection.

Pattern for client components calling server actions to set cookies in Next.js. Covers the two-file pattern of a client component with user interaction (onClick, form submission) that calls a server action to modify cookies. Use when building features like authentication, preferences, or session management where client-side triggers need to set/modify server-side cookies.

Conversational brainstorming partner for capturing fleeting thoughts, reading notes,papers, videos, and online discoveries. Casual/collegial voice, one question at a time,routes captures to appropriate vault locations.

Documentation management skill for audit, creation, and maintenance. Enforces documentation standards, checks for staleness and broken references, auto-fixes issues, and ensures docs are created in correct locations. Use when user says "check docs", "audit docs", "fix docs", "create doc", "archive docs", or when scattered .md files are detected.

Expert guidance for writing resilient end-to-end tests that span multiple processes and components. Use this skill when reviewing, writing, or refactoring system-wide e2e tests. Covers user-facing scenarios, helper functions, data factories, ARIA-based selectors, and auto-retriable assertions. NOT for unit/integration tests - use testing-unit-integration skill instead. See references/playwright-resilience.md for detailed selector patterns.

Citation management and fact-check sources. TRIGGERS: 'citações', 'citations', 'fact-check', 'factCheckSources', 'referências', 'fontes'. Use when extracting citations from Perplexity, validating sources, storing in factCheckSources field, displaying references to users.

Generate HTML research reports with embedded data, charts, and analysis. Use when creating final research deliverables. Supports single comprehensive reports or multiple focused reports. Handles styling, structure, and output to reports/ directory.

Use when researching unfamiliar code, multiple modules involved, or external libraries referenced

Fluid typography and spacing tokens using Utopia.fyi with cqi (container query inline) units. Reference for the exact type steps and space tokens defined in this project.

Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini operations.

Comprehensive editing checklist and procedures covering grammar and style rules, fact-checking, consistency verification, and readability metrics. Use when reviewing drafts, ensuring quality, or preparing content for publication.