website-devtools
Use Chrome DevTools MCP tools to inspect rendering and troubleshoot website issues with the Maintainer.
Discover Research skills, compare source repositories and read the instructions for each workflow.
Use Chrome DevTools MCP tools to inspect rendering and troubleshoot website issues with the Maintainer.
Calculate training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the corr...
Fine-tune LLMs using the Tinker API. Covers supervised fine-tuning, reinforcement learning, LoRA training, vision-language models, and both high-level Cookbook patterns and low-level API usage.
Guidelines for creating high-quality datasets for LLM post-training (SFT/DPO/RLHF). Use when preparing data for fine-tuning, evaluating data quality, or designing data collection strategies.
Run OpenAI's Codex CLI agent in non-interactive mode using `codex exec`. Use when delegating coding tasks to Codex, running Codex in scripts/automation, or when needing a second agent to work on a task in paral...
Patterns for data loading, exploration, and statistical analysis
Patterns for data loading, exploration, and statistical analysis
Best practices for designing reproducible experiments
Best practices for designing reproducible experiments
Enforces baseline comparisons, cross-validation, interpretation, and leakage prevention for ML pipelines
Enforces baseline comparisons, cross-validation, interpretation, and leakage prevention for ML pipelines
Build features with AI coding tools (Claude Code, Lovable, Replit, Cursor). Use when implementing specs, iterating on AI code, or choosing tools. Focuses on tool selection, effective prompting, and iteration wo...
Track production app health and catch issues before users complain. Use after deploying, to check app status, or when investigating user reports. Covers error tracking, uptime monitoring, and metrics for non-te...
Test features before users find bugs. Use when feature is built, before deploying, or when bugs reported. Covers manual testing, edge cases, cross-browser testing, and testing checklists for non-technical found...
Protect your SaaS app from common vulnerabilities. Use when building auth, handling user data, or deploying features. Covers authentication, data protection, API security, and OWASP Top 10 for non-technical fou...
Optimize your SaaS app across four dimensions - Speed (page load, API response), Code (unused files, dead code), Database (orphaned data, schema hygiene), and Dependencies (package bloat, bundle size). Use when...
Turn ideas into clear, buildable specs for AI tools or stakeholder review. Use when starting features, planning projects, or when AI keeps building the wrong thing. Creates Quick Feature Specs (10-15 min) for i...
Fix bugs systematically instead of guessing. Use when features break, users report errors, or tests fail. Covers reproducing bugs, gathering diagnostic info, and working with AI tools to fix issues efficiently...
Create and manage project-specific design systems for SaaS applications. Use when starting a new app (CREATE mode), updating an existing design system (MODIFY mode), or building features that need to follow est...
Auto-invoke when reviewing API routes, server logic, Express/Node.js code, or backend architecture. Enforces REST conventions, middleware patterns, and separation of concerns.
Auto-invoke when reviewing loops, data fetching, rendering, database queries, or resource-intensive operations. Identifies N+1 queries, unnecessary re-renders, memory leaks, and scalability issues.
Auto-invoke when reviewing JSX with interactive elements, forms, buttons, or navigation. Enforces WCAG compliance and inclusive design.
Auto-invoke when reviewing README files, JSDoc comments, or inline documentation. Enforces "WHY not WHAT" principle.
Verify security considerations were addressed before shipping. Issues result in WARNINGS that strongly recommend fixing.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.