Pure socratic interrogation with NO project artifacts at all — no codebase, no CONTEXT.md, no ADRs to reference. One question at a time, walk the decision tree, recommend an answer for each branch. Rare edge case — most grilling happens inside a project, so use grill-with-docs by default (it handles the no-CONTEXT.md case by creating one lazily). Use grill-me ONLY when the user is brainstorming entirely outside a codebase (a fresh idea before any code exists, a hypothetical, a non-software design problem).

Rank functions by CRAP score (complexity × lack of real test coverage) on the current branch, then propose either a refactor or missing tests for the worst offender. Use when the user runs /crap or asks to find risky, complex, poorly-tested code.

DuckDuckGo를 사용한 웹 검색. 텍스트, 뉴스, 이미지 검색을 지원. 빌트인 WebSearch가 제한적이거나, 뉴스/이미지 검색, 지역/기간 필터가 필요할 때 사용. "검색해줘", "찾아줘", "search", "뉴스 검색", "이미지 검색" 등의 요청 시 활성화.

Use when designing domain error handling. Keywords: domain error, error categorization, recovery strategy, retry, fallback, domain error hierarchy, user-facing vs internal errors, error code design, circuit breaker, graceful degradation, resilience, error context, backoff, retry with backoff, error recovery, transient vs permanent error, 领域错误, 错误分类, 恢复策略, 重试, 熔断器, 优雅降级

Migrate existing Algolia API client code to a newer major version. Triggers on: upgrading algoliasearch, moving from initIndex to client methods, fixing "initIndex is not a function", updating imports after a version bump, handling breaking changes from v3→v4 or v4→v5, replacing .wait() chaining, or any mention of "migrate Algolia client", "upgrade Algolia SDK", or a specific old-to-new version (e.g. "Python v3 to v4", "JS v4 to v5"). Covers JavaScript, Python, Go, PHP, Java, C#, Ruby, Kotlin, Scala, Swift. Dart is a new client and is excluded from scope. Do NOT use for new project setup (use algolia-cli or algolia-mcp instead), InstantSearch / frontend frameworks, analytics queries, or recommendations.

Take a list of ideas, features, or initiatives and quickly prioritize them using an effective framework. Use when you have too many things and need to decide what to do first.

Turn messy ideas into a clear, structured PRD. Use when you have rough notes, Slack threads, or half-formed ideas that need to become a product requirements document.

Write a PR/FAQ for a product idea using Amazon's Working Backwards process. Start from the customer press release and work backward to what needs to be built. Use when validating whether an idea is worth building before committing to a spec.

Read your Slack mentions, calendar events, and recently modified Drive documents from the last 7 days and synthesize them into a short personal PM summary. Use at the end of each week to capture what happened before it fades.

Designs A/B tests with proper metrics and variants, analyzes running or completed experiments, and interprets results with statistical rigor. Use when setting up experiments, checking experiment status, analyzing results, or making ship decisions.

Performs deep analysis of a specific Amplitude chart to explain trends, anomalies, and likely drivers. Use when a metric looks unusual, investigating a spike or drop, or understanding the "why" behind numbers.

Automates the process of posting to an already logged-in Instagram account using a browser-capable agent. Use this skill when the user requests to post, upload, publish, or share a video or image to Instagram with provided content and tags.

Write marketing copy for pages, campaigns, product launches, ads, and email sequences. Use when the user asks for `/copywriting`, landing page copy, launch copy, ad variations, direct-response frameworks, AIDA, PAS, BAB, or refreshing existing marketing content.

Use when the user asks to research, investigate, look up, or understand something — orchestrates MCP servers (perplexity/exa/deepwiki/context7), agy-agent, and OMO agents (explore/librarian/oracle/multimodal-looker) with optional Max Mode for parallel multi-lane synthesis

Use when the user wants a complex input (file, function, directory, PRD, plan, spec, URL, pasted prose, or vague feature name) explained step by step in a comprehension-gated walkthrough — produces a persistent .x-guide/<slug>/GUIDE.md with full TOC and walks the user one part at a time, supports resume across sessions

Create hero visuals — animated GIF, static PNG, or animated SVG — for GitHub repositories. Runs a structured discovery conversation (scan repo → recommend format → propose creative scenarios → agree on a brief), then designs bespoke HTML/SVG, previews it in the browser, and exports. Use when the user asks for a README hero, repo banner, README image, GitHub header, social preview card, repo demo GIF, hero image, OG image, project screenshot, repository showcase, or any "image at the top of the README".

Creates a DTO (Data Transfer Object) class for an entity. Use this skill when a DTO class needs to be created, either standalone or as part of a larger task (e.g. REST controller, service layer, replacing entity usage with a DTO).

When the user wants to create UGC ad campaigns, recruit UGC creators, generate AI UGC content, or scale with user-generated content. Also use when the user mentions 'UGC,' 'user-generated content,' 'creator ads,' 'Spark Ads,' 'whitelisting,' 'AI UGC,' 'Arcads,' 'Creatify,' 'creator brief,' or 'UGC testing.' This skill covers the UGC growth framework from creator recruitment through AI-powered scaling. Do NOT use for technical implementation, code review, or software architecture.

When the user wants to build data enrichment workflows, score leads against ICP, set up Clay waterfalls, or improve contact data quality. Also use when the user mentions 'enrichment,' 'data enrichment,' 'Clay,' 'waterfall enrichment,' 'ICP scoring,' 'lead scoring,' 'intent data,' 'contact verification,' 'Apollo,' 'ZoomInfo,' or 'data quality.' This skill covers lead enrichment waterfalls, ICP scoring frameworks, and contact verification systems. Do NOT use for technical implementation, code review, or software architecture.

Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Use when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting. Covers general Figma data fetching and exploration. Do NOT use when the goal is specifically pixel-perfect code implementation from a Figma design (use figma-implement-design instead).