AI skill directory

ai agent skills.

371 skills · 1–20

A/B Testing

Plans and designs A/B and growth experiments with hypotheses, variants, and success metrics.

Abstract clinical notes into cited data fields

This skill extracts the fields you define from clinical notes and ties each value to the exact text it came from. Missing values stay empty instead of being guessed. Output can feed chart abstraction, a patient registry, or a research cohort, and it can be exported as FHIR.

Academy Guide

Recommends Claude Academy courses and tutorials for how-to questions about Claude products.

Add embedded captions to a talking-head video

This skill adds captions to an existing single-speaker video with HyperFrames, leaving the footage itself uncut. Styles range from plain word-for-word subtitles to text placed behind the speaker, picked from a style catalog. Transcription and cutting out the subject both run locally, and you preview the result before rendering. Multi-shot footage has to be split first.

Add Firebase Authentication to an app

This skill guides adding Firebase Authentication to an app for user sign-in and account management. It covers users, identity providers, and tokens, then steps through provisioning, client setup, and security rules that limit data access by signed-in user.

Add graphic overlays to an interview or podcast video

This skill packages a recorded interview, podcast, or single-speaker clip with timed graphics such as titles, lower thirds, quotes, data callouts, and side panels. It transcribes the audio locally, lines the cards up with the transcript, and renders an MP4 in 16:9, 9:16, or 4:5. The original clip plays unchanged underneath. Plain subtitles belong to the captions skill.

Agent browser

Gives agents a browser automation CLI for navigating sites, filling forms, clicking, and capturing screenshots.

AI SEO

Optimizes content to be cited by AI search and answer engines, not only classic SERPs.

Animate web pages with GSAP

This skill is GreenSock's guide to the core GSAP API: tweens with to, from, and fromTo, easing, duration, stagger, and defaults. It also covers matchMedia for responsive and reduced-motion animation and when to pick GSAP over CSS or other libraries.

Annotate and sign PDFs in a viewer

This skill opens a PDF in a viewer on your machine so you and the agent can work on it visually. You can highlight, comment, stamp, fill in form fields, and place a signature or initials. Signatures are visual only, not certified. Use plain file reading for summaries or text extraction.

Answer a sales objection

This skill helps answer an objection or a competitor showing up in a deal. It works out what the buyer really means, finds responses that won before, and backs them with proof points from your own win/loss records and customer quotes.

Answer small-business support emails with order context

This skill takes a customer message passed along by the owner and writes an answer that sounds like them. Before writing, it checks order and refund status in PayPal, Square, Stripe, or Shopify, the customer's past dealings in the CRM, and existing Zoho Desk tickets. It can issue a refund, but only after the owner approves. With Shopify connected, it can also list orders that need attention before customers write in.

Apple Design

Applies Apple-like interface and physical-motion design patterns to web experiences.

Ask Matt

Routes you to the right Matt Pocock skill or flow for the situation at hand.

FAQ

What is an ai agent skill?

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.

What is a SKILL.md file?

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.

How do I use a skill from this directory?

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.

What’s the difference between a skill and a prompt?

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.

How are skills categorized?

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.

Can I submit a skill?

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.