Research

Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction design across any domain (portfolios, e-commerce, SaaS, adult content, technical showcases). This skill should be used when users need exhaustive design research, pattern recognition across large example sets, or systematic visual analysis for competitive positioning.

Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.

Read, send, and manage Gmail emails. Load when user mentions 'gmail', 'email', 'send email', 'check email', 'inbox', 'draft', or references sending/reading emails.

Create best-in-class newsletters that people actually want to read. Use when someone needs to write a newsletter edition, develop a newsletter format, or improve their newsletter game. Covers multiple formats - roundup, deep-dive, personal essay, curated links, news briefing. References patterns from Lenny Rachitsky, Morning Brew, Greg Isenberg, Sahil Bloom, The Hustle, and top AI newsletters. Triggers on: write newsletter, newsletter format, help with my newsletter, newsletter edition about X, weekly roundup. Outputs publication-ready newsletter content or format templates.

Research and discover programmatic SEO opportunities for your app. Use this skill to identify high-value page types, validate search demand, analyze competition, and prioritize opportunities before building.

This skill should be used when conducting bioinformatics research, planning experiments, running analyses, or managing scientific projects. Triggers include requests like "研究を始める", "実験する", "新しい実験を計画", "Start research", "Plan experiment", "Run analysis", or "What's the current research status?".

A tiered approach to answering research questions with clear stop rules, evidence capture, and escalation to Tavily/Playwright only when needed.

MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows

Creates text-based visualizations and reports showing the relationship between spelling errors and semantic distance. Use when you need to visualize experimental results.

Deploy and manage AI permit research agents in E2B cloud sandboxes. Use when deploying permit research agents, running distributed AI research, scaling cloud-based compliance analysis, or building SaaS permit platforms. Supports 21 specialized agents with 92% grounding quality.

Linux VM bootstrap verification skill. MUST BE USED when setting up new VMs or verifying environment.Supports modes: check (warn-only), install (operator-confirmed), strict (CI-ready).Enforces Linux-only + mise as canonical; honors preference brew→npm (with apt fallback).Verifies required tools: mise, node, pnpm, python, poetry, gh, railway, bd, tmux, jq, rg.Handles optional tools as warnings: tailscale, playwright, docker, bv.Never prints/seeds secrets; never stores tokens in repo/YAML; Railway vars only for app runtime env.Safe on dirty repos (refuses and points to dirty-repo-bootstrap skill, or snapshots WIP branch).Keywords: vm, bootstrap, setup, mise, toolchain, linux, environment, provision, verify, new vm

Synchronize documentation with codebase - updates AUTO-GEN sections in CLAUDE.md, validates cross-references, and reports stale documentation

Reference guide for generating Underware cable management channel OpenSCAD code. Provides channel type selection, parameter quick reference, and QuackWorks integration. Use when generating OpenSCAD files for Underware cable routing systems.

Validate generated experimental procedures against LA-Bench evaluation criteria. This skill orchestrates formal validation (via script) and semantic evaluation (via subagent) to ensure compliance with LA-Bench standards. Use this skill after generating procedures to assess quality before submission.

Research-driven Cube semantic layer development. Injects research steps for data modeling, dbt integration, metrics, dimensions, REST API, GraphQL API, and SQL API (Postgres wire protocol). Use when building semantic layer, consumption APIs, metrics layer, Cube integration tests, or working with Cube MEASURE() syntax and psycopg2 connections.

Explore external reference source code to understand implementations, draw inspiration, debug issues, or answer questions. Use when exploring repos like InstantDB, Trigger.dev, Vercel AI SDK, HeroUI Native, or any external codebase. Handles two modes - "inspiration" (adaptive, translating concepts to user's stack) or "understanding" (direct, definitive answers about the source). Always cite file:line references.

Generate and edit images using the Gemini API (Nano Banana Pro). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Complete command reference for the ClickUp Framework CLI (cum) with all shortcuts, options, examples, and usage patterns

Manages a structured knowledge base of patterns, troubleshooting guides, best practices, and workflows. Activates when discovering reusable insights, solving technical problems, or establishing new standards. Records knowledge in categorized files for future reference without bloating global CLAUDE.md.

Synthesize research, data, and insights to create a rich, actionable buyer persona with demographics, psychographics, jobs-to-be-done, pain points, motivations, buying journey, and channel preferences. Use when the user needs to understand their target customer deeply or create a customer persona for marketing strategy.