Speech
Generates text-to-speech narration and voiceover audio from prompts or scripts.
ai agent skills.
371 skills · 301–320
Generates text-to-speech narration and voiceover audio from prompts or scripts.
This skill turns a one-sentence app idea into a small Convex backend plus web template and starts it locally. It shares a short plan before adding features and keeps the starter lean. Its rules cover where Convex code lives, indexes, imports, and checking the build before calling it done.
Builds and extends Stripe Apps that embed into the Stripe Dashboard and workflows.
Guides Stripe integration choices across sandboxes, API design, webhooks, and test vs live environments.
Finds and applies Stripe documentation accurately when implementing payments integrations.
Pays another Stripe business using its Stripe Profile handle.
Executes implementation plans via subagents for independent tasks in the current session.
This skill takes a call transcript or rough notes and produces three things: a follow-up email draft for the customer, a short internal summary, and suggested CRM updates. Proposed CRM changes come with the transcript line behind each, and you choose which ones to apply.
This skill uses the Google Workspace CLI to list unread Gmail messages, showing who sent each one, its subject, and when it arrived. It reads only and does not change the mailbox. Flags set how many messages to show, a custom search query, and whether to include labels.
Works across the Supabase platform—Auth, Storage, Edge Functions, and project setup—beyond Postgres alone.
Applies Supabase-maintained Postgres best practices before writing or changing schema, queries, or RLS.
Audits dependencies for advisories, abandoned upstreams, publisher concentration, and install scripts.
Fixes bugs at the narrowest responsible layer while preserving surrounding behavior.
Applies a disciplined debugging process for bugs, test failures, and unexpected behavior before proposing fixes.
Drives feature work with Matt Pocock's TDD skill patterns—failing tests first, then implementation.
Teaches a skill or concept in the current workspace with explanations grounded in your code and goals.
Authors and applies Terraform policy-as-code checks for safe infrastructure changes.
Designs and works with Terraform Stacks for composing and deploying infrastructure units.
Generates and reviews Terraform HCL using HashiCorp’s official style conventions.
Writes and runs Terraform tests using HashiCorp's recommended testing patterns.
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.