AI Skills
Installable SKILL.md packages that extend AI coding agents with reliable workflows and domain-specific judgment — ranked by installs, sourced from skills.sh.
test-scenario
Generates structured usability test scenarios with realistic tasks, success criteria, and facilitation notes — ready to run with real participants or in a moderated session.
torchcode-pytorch-interview-practice
LeetCode-style PyTorch interview practice environment with auto-grading for implementing softmax, attention, GPT-2 and more from scratch.
tools-page-generator
When the user wants to create, optimize, or audit free tools pages. Also use when the user mentions "free tools," "tools page," "toolkit," "free [X] tool," "free [X] calculator," "free [X] checker," "lead magnet tool," "programmatic tools," or "tools hub." For content strategy, use content-strategy.
fda-consultant-specialist
FDA regulatory consultant for medical device companies. Provides 510(k)/PMA/De Novo pathway guidance, QMSR (21 CFR 820, which incorporates ISO 13485:2016 by reference since 2026-02-02; formerly QSR) compliance, HIPAA assessments, and device cybersecurity. Use when user mentions FDA submission, 510(k), PMA, De Novo, QMSR, QSR, ISO 13485 for FDA, premarket, predicate device, substantial equivalence, HIPAA medical device, or FDA cybersecurity.
web-search
Search the web using the agent's built-in WebSearch tool. Use when you need to find current information, verify facts, or research topics. No API key required. Keywords: search, web, internet, lookup, find, research, current events, facts.
migrate-xml-views-to-jetpack-compose
Provides a structured workflow for migrating an Android XML View to Jetpack
muapi-youtube-thumbnail
Design a high-CTR YouTube thumbnail — striking imagery, bold text placement, and emotional face/subject if needed.
polymarket-copy-trading-bot
TypeScript bot that monitors a Polymarket wallet and mirrors BUY trades to your own account via the Polymarket CLOB API on Polygon.
do-in-steps
Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.
rabbitmq-development
Best practices and guidelines for RabbitMQ message queue development with AMQP protocol
handoff-spec
Create developer handoff specifications with measurements, behaviors, assets, and edge cases.
Review Changes
Perform a structured code review using change detection and impact
design-sprint-plan
Plan and facilitate design sprints from challenge framing through prototype testing.
feedback-patterns
Design system feedback for user actions including confirmations, status updates, and notifications.
core-web-vitals
When the user wants to optimize Core Web Vitals, fix LCP, INP, or CLS issues. Also use when the user mentions "Core Web Vitals," "CWV," "LCP," "INP," "CLS," "FID," "page speed," "page performance," "Largest Contentful Paint," "Interaction to Next Paint," "Cumulative Layout Shift," or "Page Experience." For GSC CWV, use google-search-console.
code-reviewer
Elite code review expert specializing in modern AI-powered code
edit-article
通过重组 sections、提升 clarity、收紧 prose 来编辑并改进 articles。Use when user wants to edit, revise, or improve an article draft.
finviz-screener
Build and open FinViz screener URLs from natural language requests. Use when user wants to screen stocks, find stocks matching criteria, filter by fundamentals or technicals, or asks to open FinViz with specific conditions. Supports both Japanese and English input (e.g., "高配当で成長している小型株を探したい", "Find oversold large caps with high ROE").
diary-study-plan
Design a diary study plan with prompts, duration, participant criteria, and analysis framework. Use when you need to understand user behavior over time in natural contexts.
workload-manager-basics
>-
openai-docs
Use official OpenAI docs.
native-ads
When the user wants to run native ads on Taboola, Outbrain, or similar platforms. Also use when the user mentions "native ads," "Taboola," "Outbrain," "content recommendation," "sponsored content," or "in-feed ads." For strategy, use paid-ads-strategy.
commit
Create well-formatted commits with conventional commit messages and emoji
accessibility-test-plan
Create accessibility testing plans covering assistive technologies and WCAG criteria.
api-security-hardening
>
3d-modeling
Agent skill from omer-metin/skills-for-antigravity.
status-page-generator
When the user wants to create, optimize, or structure a status page. Also use when the user mentions "status page," "status.yourdomain.com," "uptime," "service health," "incident page," or "system status." For incident comms, use public-relations.
metrics-definition
Define UX metrics and KPIs that connect design decisions to measurable business and user outcomes.
multi-domain-brand-seo
When the user wants to optimize brand search for a company with multiple domains (e.g. parent company.com vs product.ai). Ensure the parent/company domain ranks first for brand queries. Also use when the user mentions "brand search," "multi-domain SEO," "company domain first," "parent vs product domain," "hub-spoke domain," "brand SERP control," or "differentiate company and product domains." For domain structure, use domain-architecture.
trading-wisdom
Core trading insights learned from Agent Arena competition. Use when making any trading decision to apply institutional knowledge.