发现 Skills

서브에이전트 컨텍스트 문제를 해결하기 위한 점진적 컨텍스트 검색 개선 패턴

Automate Scrape Do tasks via Rube MCP (Composio). Always search tools first for current schemas.

This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", and "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage, then performs fixes at the source code level.

Zustand store data structure patterns for LobeHub. Covers List vs Detail data structures, Map + Reducer patterns, type definitions, and when to use each pattern. Use when designing store state, choosing data structures, or implementing list/detail pages.

Generates iOS app icons as PNG image sets for Xcode asset catalogs from SF Symbols (Apple-native, 5,000+ icons) or the Iconify API (275,000+ open-source icons from over 200 collections). Use it to generate icons, create icon assets, add icons to an asset catalog, or search for icons for an iOS project.

Japanese translation: This file requires a Japanese translation for make-interfaces-feel-better.

Japanese translation: This file requires a Japanese translation for the 'production-scheduling' feature.

Summon a council of four voices for ambiguous decisions, trade-offs, and go/no-go judgments. Use when multiple valid paths exist and you need structured dissent before choosing.

Build fully automated, AI-powered data-collection agents for any public source (job boards, pricing, news, GitHub, sports, etc.). Scrape on a schedule, enrich data with a free LLM (Gemini Flash), save results to Notion/Sheets/Supabase, and learn from user feedback. Runs 100% free on GitHub Actions. Use this when you want to automatically monitor, collect, or track public data.

Use this skill when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and optional Markdown content.

Automate Apollo.io lead generation -- search organizations, discover contacts, enrich prospect data, manage contact stages, and build targeted outreach lists -- using natural language through the Composio MCP integration.

Automate Browserbase Tool tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Bugherd tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Certifier tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Geocodio tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Screenshot Fyi tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Whautomate tasks via Rube MCP (Composio). Always search tools first for current schemas.

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202

This skill should be used when the user asks to "learn ethical hacking", "understand penetration testing lifecycle", "perform reconnaissance", "conduct security scanning", "exploit vulnerabilities", or "write penetration test reports". It provides comprehensive ethical hacking methodology and techniques.

Prisma ORM expert for schema design, migrations, query optimization, relations modeling, and database operations. Use proactively for Prisma schema issues, migration problems, query performance, relation design, or database connection issues.

Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences. Like NY Times interactives, Apple product pages, and award-winning web experiences. Makes websites feel like experiences, not just pages. Use when: scroll animation, parallax, scroll storytelling, interactive story, cinematic website.

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Agent Sessions window architecture — covers the sessions-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development guidelines. Use when implementing features or fixing issues in the Agent Sessions window.