Research

Guide for authoring effective skills. Use when creating, building, updating, designing, packaging, reviewing, evaluating, or improving skills that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations. Helps with skill structure, SKILL.md frontmatter, progressive disclosure, resource organization (scripts/assets/reference files), initialization templates, validation, and packaging. Also triggers when asking how to create a skill, what makes a good skill, learning about skill development, or troubleshooting skill issues. Includes proven design patterns for workflows and output quality.

UX design expert for user research, personas, journey mapping, information architecture, wireframing, prototyping, usability testing, and accessibility. Creates user-centered designs with WCAG 2.1 AA/AAA compliance.

Run an iterative, hypothesis-driven “debug mode” loop to diagnose and fix a bug using targeted instrumentation and log capture. Use when the user wants an interactive debug loop, when you need to quickly narrow a failure via added debug statements, or when you need a lightweight way to centralize logs from a repro run (via `agent-skills debug` server + SSE UI).

Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings

MagentaA11y accessibility acceptance criteria reference. Use this skill when users ask for accessibility criteria, acceptance criteria (AC), Gherkin tests, developer notes, or how to test components for accessibility. Supports both Web and Native (iOS/Android) platforms. Triggers on requests like "give me the Button AC", "how to test a checkbox", "accessibility criteria for modal", "native button Gherkin", "web link developer notes", or any MagentaA11y component query.

Capture Bennett Waxse's writing voice for technical communication, LinkedIn posts, research discussions, and professional correspondence. Use when drafting content that should sound like Bennett, including: (1) Research paper discussions or LinkedIn posts about academic work, (2) Technical emails to collaborators, (3) Professional communications that need his specific tone and style, (4) Any writing where maintaining his authentic voice matters.

新しいスキルを対話形式で作成するメタスキル。スキルの作成、新規スキル追加、カスタムスキル開発、スキルテンプレート生成をサポート。要件をヒアリングし、SKILL.md、scripts/、references/を自動生成する。Use when user asks to create a new skill, add custom skill, or develop agent capabilities.

Deep methodology knowledge for pairwise meta-analysis including fixed vs random effects, heterogeneity assessment, publication bias, and sensitivity analysis. Use when conducting or reviewing pairwise MA.

Elite UX agency capabilities for designing products users intuitively love. Use when creating user journeys, conducting UX research, designing flows, testing with Playwright, performing design critiques, building wireframes, writing microcopy, accessibility audits, competitive analysis, or any product design work. Triggers on UX, user journey, user experience, flow design, usability, design critique, persona creation, emotional mapping, or product design discussions.

Naming conventions for files, folders, functions, types, components, constants, and URLs. Enforces camelCase, PascalCase, SCREAMING_SNAKE_CASE, and kebab-case rules. References abbreviations skill for handling abbreviations, initialisms, and acronyms. Use when naming anything in the codebase.

Clean up stale git worktree references and metadata. Use when git shows worktrees that no longer exist, or after manually deleting worktree directories. Fixes inconsistencies.

The ONLY way to interact with existing projects. Load when user references ANY project by name, ID, or number. Includes: continue, resume, status, progress, check, review, work on [existing project]. NEVER read project files directly.

Analyzes customer behavior, needs, pain points, and sentiment through review mining, social listening, buyer persona development, and jobs-to-be-done framework. Use when the user requests customer analysis, voice of customer research, buyer personas, pain point analysis, or wants to understand customer needs and motivations.

Comprehensive IEEE PES paper review for Physics-Guided SSL GNN power grid research. Use when reviewing paper sections, checking claims against evidence, validating physics consistency (PF/Line Flow/Cascade), auditing figures/tables, checking IEEE compliance, or positioning against competing work (PPGT). Triggers on "review my paper", "check claims", "validate physics", "PES submission ready", "compare to baselines", "audit figures", or any publication preparation task.

Use when you want a second-opinion review from a different model/tool. Provide narrow, reviewable diffs.

Generate and edit images using the Gemini API (Nano Banana). 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.

This skill enriches vague prompts with targeted research and clarification before execution. Should be used when a prompt is determined to be vague and requires systematic research, question generation, and execution guidance.

Conducts web research and synthesizes findings into structured analysis

Activate when the user needs help conducting proactive threat hunting, investigating suspicious activity, or building hypothesis-driven hunts in LimaCharlie.

Professional skepticism with pattern enforcement. Verify before agreeing, challenge violations, propose instead of asking. Concise output, research before asking, answer questions literally.