
Create or improve agent skills. Load when creating SKILL.md files, writing skill descriptions, or structuring skill content.
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
A specialist skill for security reviews, threat modeling, and remediation guidance. Use for auth/permissions changes, secrets or PII handling, public endpoints, or dependency upgrades.
Drives changes through a strict red-green-refactor loop using behaviour tests at the public interface. Use when the user asks for TDD, test-first development, integration tests, regression coverage, or a feature built one vertical slice at a time.
Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices.
Design robust backend systems and APIs. Use when users ask to plan or implement services, data models, or integrations.
Builds a fast feedback loop, reproduces the symptom, tests ranked hypotheses, instruments narrowly, fixes, and adds regression coverage. Use when the user says diagnose/debug, reports broken behaviour, failing checks, thrown errors, flaky bugs, or performance regressions.
A skill that outlines best practices for using Git in a collaborative development environment, including branching strategies, commit conventions, and pull request workflows.
Create distinctive, production-grade frontend interfaces with high design quality. Use when users ask to build web components, pages, or applications.
Audits web performance using Chrome DevTools MCP. Measures Core Web Vitals, finds render-blocking resources, dependency chains, layout shifts, caching issues, and accessibility gaps. Use for audits, profiling, debugging, or optimising page load performance and Lighthouse scores.
Reviews a codebase for architectural friction and proposes deepening opportunities grounded in its domain language, tests, dependencies, and ADRs. Use when the user wants architecture review, refactoring candidates, better module shape, clearer seams, or a codebase that is easier to test and navigate.
Stress-tests a plan against the existing domain language, code, and documented decisions, then updates CONTEXT.md or ADRs as decisions crystallise. Use when the user wants to be grilled on a design, validate a plan, sharpen terminology, or record the reasoning behind a decision.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.