Research

User preferences learned by slipstream

Intelligent revenue opportunity discovery system for financial advisors. Extracts structured revenue scenarios from publications and matches them to client books of business to identify high-value opportunities. Use when analyzing industry articles to discover new scenarios, or when scanning client data to find revenue opportunities and generate Top 25 opportunity reports.

Generate JSON schemas and Python handlers for Qdrant-based retrieval tools used by the RAG agent to search sitemap-crawled textbook content with URL citations.

Systematic architecture analysis following Understand → Research → Specify → Decompose → Plan workflow. Use for system design, solution evaluation, build vs buy decisions, and task decomposition. Activate when users say "design", "architect", "break down", "best approach", or "should I build".

Use when encountering errors, investigating library APIs, troubleshooting issues, or needing up-to-date documentation. Prioritizes Context7 and WebSearch over outdated training data.

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.