Research

Search web, library docs, GitHub repos, and code examples. Use for "how to", "what is", documentation lookups, or fetching URL content.

Comprehensive guide for integrating Gemini CLI as research assistant. Use when you need to delegate research to Gemini, understand its capabilities vs Claude's, or determine the right tool for a task.

Apply preferred toolchain and technology stack defaults: pnpm, Next.js, TypeScript, Convex, Vercel, Tailwind, shadcn/ui, Zustand, TanStack, Vitest. Use when setting up new projects, choosing dependencies, discussing stack decisions, or evaluating alternatives.

Expert Detection Engineer assistant for creating and testing D&R rules in LimaCharlie. Guides through understanding threats, researching event data (Schema, LCQL, Timeline), generating detection logic, testing rules against sample and historical data, and deploying validated rules. Use for building detections, writing D&R rules, testing detection logic, or when user wants to detect specific behaviors or threats.

Conducts systematic literature reviews with academic rigor. Use when you need to understand existing research on a topic, identify research gaps, trace the evolution of ideas, or build a comprehensive bibliography. Triggers on phrases like "literature review", "what does research say", "find papers on", "academic sources for", "systematic review of".

This skill performs differential DNA methylation analysis (DMRs and DMCs) between experimental conditions using WGBS methylation tracks (BED/BedGraph). It standardizes input files into per-sample four-column Metilene tables, constructs a merged methylation matrix, runs Metilene for DMR detection, filters the results, and generates quick visualizations.

Validates messaging consistency across website, GitHub repositories, and local documentation. Generates comprehensive read-only discrepancy reports showing where messaging conflicts or inconsistencies exist. Activates when user mentions "consistency check", "validate documentation", "check for mixed messaging", "audit content consistency", or before updating internal paperwork.

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

Look up examples and patterns from the official Anthropic Claude Cookbooks repository. Use when you need reference implementations, code examples, or best practices for Claude integrations, tool use, agents, prompting techniques, or API usage.

Create new PAI agents using AGENT_FACTORY.md patterns. Guides through archetype selection (Researcher, Validator, Generator, Critic, Synthesizer), validates against CONSTITUTION.md, and generates agent specifications following established templates.

Use when needing to understand requirements before implementation. Gathers context from Jira, Confluence, codebase, and docs. Produces research document with confidence scoring.

Add new learning resources (books, articles, courses, papers) to the appropriate resources.md file. Use when user mentions adding, saving, or tracking learning materials.

外部キー制約と参照整合性をC.J. Dateの理論に基づいて設計するスキル。CASCADE動作の戦略的選択、循環参照の検出・解消、ソフトデリート整合性を提供。SQLite/Turso + Drizzle ORM環境に最適化。Anchors:• An Introduction to Database Systems（C.J. Date） / 適用: FK設計 / 目的: 理論的に正しい制約設計• The Pragmatic Programmer（Hunt, Thomas） / 適用: 実装品質 / 目的: 保守性の高い設計Trigger:Use when designing foreign key relationships, selecting CASCADE behavior, detecting circular references, integrating soft delete patterns, or reviewing database schema integrity.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields.

Generates changelogs and release notes from git commits, PR titles, and issue references. Organizes changes by impact type (breaking, features, fixes, improvements), formats according to Keep a Changelog standard, and provides version tagging and semantic versioning suggestions. Use when users request "create changelog", "write release notes", "document version changes", or "prepare release".

Edit images via OpenAI gpt-image-1 API. Creates edited or extended images from source images and a prompt. Supports masks for selective editing, multiple input images for compositing, and input fidelity control for preserving facial features. Use when user wants to modify existing images, combine multiple images, remove/replace objects, extend images, or needs AI-powered image editing with reference images.

Write markdown content to file paths using the MCP markdown-writer server. Use when you need to save generated markdown content to a file, especially in contexts where (1) The Write tool is unavailable or restricted, (2) You need guaranteed atomic writes with verification, (3) Writing markdown files for documentation, reports, or research outputs, (4) An agent needs to persist markdown without user permission prompts.

Reorganize ideas so each builds naturally on what came before. Use when: (1) asked to reorder or improve flow, (2) explanation references concept before introducing it, (3) conclusion appears before supporting reasoning, (4) writing tutorial or educational content.

Execute deep research protocols using the Falcon specialized research framework.

Quick reference for Kubernetes core concepts and kubectl commands. This skill should be used as a refresher for basic K8s operations including pods, deployments, services, configmaps, secrets, and namespaces. Use this skill when working with Kubernetes clusters for Phase IV+ deployments.