Vercel Composition Patterns
Applies Vercel composition patterns for React component architecture and reuse.
ai agent skills.
371 skills · 341–360
Applies Vercel composition patterns for React component architecture and reuse.
Optimizes Vercel cost and performance for deployed Next.js and related framework projects.
Applies Vercel Engineering React Native/Expo performance rules—lists, animations, navigation, UI, and monorepos.
Forces verification (tests, checks, evidence) before declaring work done.
Rephrases the previous response when its meaning or explanation was not clear.
Plans multi-session work as a shared map of decision tickets so large efforts stay navigable.
Builds interactive web artifacts (HTML/JS widgets) suitable for Claude artifacts-style delivery.
Reviews UI code against Web Interface Guidelines for accessibility, UX, and interface quality.
Improves web performance with Cloudflare-aware guidance—caching, edge, and measurement.
Runs an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing.
Tests local web apps with Playwright—navigate UI, verify behavior, and catch regressions.
Reviews and authors Cloudflare Workers code against production best practices and wrangler conventions.
Uses Wrangler CLI correctly for Cloudflare Workers projects—config, deploy, and local dev.
This skill uses Firecrawl to search and read the web on a complex topic, then writes a formal report with sources. The report has an executive summary, key findings, detailed analysis, contrarian views and risks, and open questions. It is meant for hard scientific, technical, policy, or market questions, not quick lookups or product picks.
This skill turns a solved ticket or a question that keeps coming up into a knowledge base article. It picks a template such as a how-to or a known-issue notice, writes the title and opening for search, and adds publishing notes. Workarounds and known problems customers should hear about also qualify.
This skill uses Firecrawl to look into a company and the people who run it before a meeting. The brief covers an overview, recent activity, things to bring up, problems they likely face, an angle for outreach, and sources. It suits sales calls, partner meetings, investor chats, and customer interviews. A Firecrawl API key is required.
This skill searches Firecrawl's paper index and writes a literature review on a topic. The index leans toward biomedical and life-science work, with PubMed, bioRxiv, and medRxiv as sources, and it also holds arXiv papers in computing, physics, and mathematics. It expands to related papers and checks claims in the paper text. The review covers key papers, themes, debates, trends, and sources.
This skill turns what a team wants from marketing into a campaign brief. The brief covers objectives, the audience, key messages, which channels to use, a weekly content schedule that shows what depends on what, and how success is measured. It adds budget split, risks, and next steps when you supply a budget. Product launches and lead-gen pushes are typical uses.
This skill writes the forecast story you bring to a forecast meeting or a manager check-in, split into commit, upside, and pipeline. It sorts deals into buckets, notes changes since the last call, and comments on each deal. With your approval it can also update forecast categories.
This skill writes ad headlines, supporting lines, and main body copy for paid placements and keeps each line inside the target platform's character limits. It can start from a blank brief, rework copy using past performance numbers, or produce large static batches. Platform specs cover Google responsive search, Meta, LinkedIn, TikTok, and X.
An agent skill is a portable pack of instructions that gives an agent specialized know-how for a task. In the open Agent Skills format (from Anthropic, now widely adopted), that pack is a folder with a SKILL.md file and optional scripts or references the agent can load when needed.
SKILL.md is the required main file in a skill folder. It starts with simple metadata (name and description) plus the instructions. Agents use the metadata to decide when a skill applies, then read the full file — and any linked files — only when the task needs them.
Open the listing and follow the source link — usually a GitHub SKILL.md. Install with your agent’s skill flow, or add the repo the way that product documents. When this site shows the skill text, Copy is on the page.
A prompt is paste-in text for one chat turn (or a short thread). A skill is a reusable file pack an agent can discover and load across a task, sometimes with code attached. Prompts live in the prompt directory; skills usually live on GitHub and we link out.
Each skill uses one sitewide category — the same set as the rest of the directory (Coding agent, Marketing, Document intelligence, and so on). Hops filter to categories that already have skills.
Yes. Submit with a public GitHub SKILL.md URL, or attach a skill as part of a method on a use case. An editor reviews it before it appears here.