Loading...
Loading...
Found 1,927 Skills
Use when receiving code review feedback, processing PR comments, or needing to evaluate suggestions before implementing - requires technical verification not blind agreement
Provides brand typography selection and hierarchy development frameworks including the Brand-First Typography Selection Process, Modular Scale System, Font Classification Matrix, Serif vs. Sans-Serif Decision Framework, Typeface Evaluation Criteria, Font Pairing Principles, WCAG accessibility requirements, and typography design tokens. Auto-activates during brand typography development, font selection, type hierarchy creation, and typography system work. Use when discussing brand typography, font selection, font pairing, type hierarchy, modular scale, typography accessibility, WCAG typography, or typography guidelines.
Supervised & unsupervised learning, scikit-learn, XGBoost, model evaluation, feature engineering for production ML
Unified code review system — dispatches the right review agents for the situation. Use when reviewing code for quality, bugs, compliance, or before merging.
Write newsletter subject lines for OpenEd Daily using 15 proven formulas + 10 Commandments evaluation. Generate 10+ options, select best through systematic criteria.
Comprehensive technical research by combining multiple intelligence sources — Grok (X/Twitter developer discussions via Playwright), DeepWiki (AI-powered GitHub repository analysis), and WebSearch. Dispatches parallel subagents for each source and synthesizes findings into a unified report. This skill should be used when evaluating technologies, comparing libraries/frameworks, researching GitHub repos, gauging developer sentiment, or investigating technical architecture decisions. Trigger phrases include "tech research", "research this technology", "技术调研", "调研一下", "compare libraries", "evaluate framework", "investigate repo".
Walk through decisions using a 3-part framework (first-principles, cost/benefit, second-order effects). Use when choosing between options, evaluating trade-offs, or making high-stakes decisions.
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.
Use when evaluating AI tools and agentic workflows against workflow gaps, when conducting quarterly landscape scans, or when assessing integration feasibility of new tools for startup workflows.
Comprehensively reviews Python libraries for quality across project structure, packaging, code quality, testing, security, documentation, API design, and CI/CD. Provides actionable feedback and improvement recommendations. Use when evaluating library health, preparing for major releases, or auditing dependencies.
Use when seeking analogous solutions from other domains, when stuck on a problem and need fresh perspectives, or when evaluating whether approaches from field X might apply to field Y. Requires structured problem statement.
Fetches aggregated trace metrics (token usage, latency, trace counts, quality evaluations) from MLflow tracking servers. Triggers on requests to show metrics, analyze token usage, view LLM costs, check usage trends, or query trace statistics.