Agent skills, carefully picked

Lets an agent search the open skills ecosystem when a task calls for specialized knowledge. Best for people who want a small on-demand toolkit instead of preinstalling a huge collection.

Gives an agent a stronger visual point of view before it starts writing interface code. Best for new landing pages, dashboards, prototypes, and redesigns where the brief needs a distinctive visual direction.

Adds persistent, command-driven browser automation for navigation, extraction, form work, and web QA. Best for repeatable browser tasks and web application checks where a structured CLI is more reliable than ad hoc scripts.

A prioritized React and Next.js performance checklist maintained by Vercel Engineering. Best for react and Next.js teams that want performance guidance applied consistently while code is being written.

Microsoft's operational guide for building, evaluating, deploying, and managing Foundry agents and models. Best for teams already building managed agents and model workflows on Azure and Microsoft Foundry.

A prioritized Postgres playbook for schema design, security, query performance, and operations. Best for schema changes, migrations, security policies, and database performance work where generic SQL advice is risky.

Keeps an agent in a root-cause investigation loop before it starts patching symptoms. Best for intermittent failures, regressions, and multi-component bugs where plausible guesses are expensive.

Turns a broad SEO review into a prioritized diagnosis across technical, on-page, and content signals. Best for site owners who need an ordered action plan rather than another generic SEO checklist.

A conversion-copy workflow for pages, headlines, value propositions, and calls to action. Best for founders and marketers writing or revising conversion-focused website copy.

A design and implementation guide for MCP servers that expose external services to language models. Best for developers turning an existing API or internal service into a well-behaved MCP tool surface.

Structures substantial writing as context transfer, iterative drafting, and fresh-reader testing. Best for proposals, product requirements, technical specifications, decision records, and other collaborative documents.

Manages Google Agent Platform RAG corpora, files, retrieval, and grounded generation through the Gen AI SDK. Best for google Cloud teams operating a managed retrieval layer for grounded agent responses.

Gives structural feedback on legal writing without silently replacing the author's analysis or voice. Best for law students and legal writers seeking critique on a memo, brief, paper, or exam-style draft.

Guides vertical, behavior-focused red-green-refactor cycles instead of writing a large test suite up front. Best for features and bug fixes where a clear observable contract can drive implementation.

Reviews interface code against a maintained set of usability, interaction, and accessibility checks. Best for a final UI review after implementation, particularly for keyboard behavior, hierarchy, controls, and content states.

A diagnosis loop for stubborn failures and performance regressions where the cause is not yet known. Best for hard bugs, slow paths, and ambiguous failures that have already resisted a straightforward fix.

Routes an agent through the right Remotion guidance for building video in React. Best for react developers creating repeatable product videos, explainers, social clips, or data-driven motion graphics.

A full workflow for drafting, testing, measuring, and improving an agent skill. Best for teams turning repeatable internal procedures into maintained, evaluable agent capabilities.

Helps agents design React component APIs that remain flexible as a product grows. Best for design systems, shared component libraries, and refactors where component APIs have become hard to reason about.

Prisma's setup and operations guide for Prisma Postgres across its console, CLI, and management APIs. Best for teams provisioning or automating Prisma Postgres rather than simply using Prisma ORM against another database.

Creates, reads, edits, and validates professional Word documents with formatting-aware workflows. Best for reports, proposals, policies, letters, and templates that must be delivered as a real Word document.

Applies behavioral science and decision models to messaging, pricing, and conversion choices. Best for teams that want a reasoned behavioral hypothesis behind a marketing choice or experiment.

Builds a content plan around audience demand, business goals, and a balanced portfolio of ideas. Best for teams deciding what to publish before they start drafting individual articles or campaigns.

Plans scalable search pages around repeatable query patterns, useful data, and sound indexation controls. Best for products with a defensible dataset and many genuinely useful pages that share a repeatable structure.

Evaluates whether content is easy for answer engines and AI assistants to extract, trust, and cite. Best for content teams tracking discovery beyond traditional blue-link search results.

A current reference skill for Claude models, API patterns, tools, caching, streaming, MCP, and migration. Best for teams building directly on the Anthropic API or migrating a Claude integration across model generations.

Google's implementation guide for Gemini through Vertex AI and Agent Platform. Best for projects using Gemini in Google Cloud rather than a provider-neutral model abstraction.