PR review canvas
Renders a PR diff review as a Cursor Canvas grouped by reviewer importance, separating boilerplate from core logic.
ai agent skills.
371 skills · 221–240
Renders a PR diff review as a Cursor Canvas grouped by reviewer importance, separating boilerplate from core logic.
Writes clear PR descriptions covering intent, risk, and test evidence.
Develops product requirements documents with problem framing, scope, and measurable outcomes.
This skill builds a brief before a sales meeting. It finds the meeting, pulls account history and notes from earlier call transcripts, profiles each attendee, and shows where the open deal stands. The brief ends with a call plan and discovery questions to ask.
This skill finds your next meeting through the Google Workspace CLI and shows its agenda, who is attending, and any docs linked to it. It gives a quick read before the meeting starts.
This skill builds a P&L, a statement of financial position, and a cash-flow report for a month or quarter. It compares each period with the prior one or with budget, flags large variances, and adds a short key-metrics summary. It also includes GAAP layout notes and typical closing entries.
Writes working-backwards press releases to clarify customer value before building.
Designs and critiques SaaS pricing pages, packaging, and pricing narrative.
Applies PM prioritization frameworks (RICE, MoSCoW, etc.) to rank opportunities and roadmap items.
Uses Prisma CLI correctly for init, generate, migrate, db, studio, and related commands.
Uses the Prisma Client API correctly—queries, relations, transactions, and type-safe patterns.
Configures Prisma with Postgres, MySQL, SQLite, MongoDB, and other supported providers.
Operates Prisma Postgres across Console, create-db CLI, and Management API workflows.
Migrates Prisma ORM projects from version 6 to version 7 across breaking changes.
Frames problems on a canvas so teams share the same problem, users, and constraints before solutions.
Crafts product marketing narratives—positioning, audience, and message hierarchy.
This skill takes the web addresses of rival companies and writes one structured markdown profile for each. It scrapes their sites, pulls SEO and market data when those tools are connected, and then sums up positioning, product, and differences. Every profile uses the same layout and sticks to sourced facts.
Builds SEO pages at scale from templates and data without thin-content traps.
Optimizes prompts and agent instructions for clarity, constraints, and better outcomes.
Applies property-based testing to find edge-case bugs with generative properties.
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.