AI-Enablement Prompts
Bitovi's plugin marketplace: specs and feature delivery, Figma and React, Playwright QA, tRPC and Prisma
Install
/plugin marketplace add bitovi/ai-enablement-prompts
/plugin install code@bitovi-ai-enablementOther plugins: creating-prompts, figma-from-code, implement-workflow, react, react-mock, figma-react, playwright, trpc-prisma.
This is third-party code. Review the repository files before installing.
What it does
The consultancy Bitovi packaged its working prompt chains into nine plugins. The code plugin generates agent instructions for a codebase and writes and checks specs. implement-workflow takes a task from design through build and tests to self-review and PR prep. figma-react turns Figma designs into React components and keeps them in sync, figma-from-code rebuilds a design system in Figma from code, and playwright covers E2E tests, debugging and visual diffing. There are also plugins for React patterns, Zod-based mock data and types in tRPC plus Prisma monorepos.
Who it is for. For React frontend teams working with Figma who want repeatable agent workflows.
Good fit when
- You need to build a component from a Figma design
- You need to take a task to a ready PR through one process
- You need to write or debug a Playwright E2E test
Not a fit when
- The project is not React and you want the component plugins
- You lack Figma MCP or Playwright MCP for the plugins that need them
Example request
Implement the product card component from this Figma design and check the visual matchLimitations
Some plugins need Figma MCP or Playwright MCP, and Jira-based flows assume Atlassian access. The patterns reflect Bitovi's approach, such as the modlet component structure. Materials are in English.
How to disable. Uninstall the plugin via /plugin or remove the bitovi-ai-enablement marketplace.
Security check
- Changes project code and runs tests
- Works through Figma MCP and Playwright MCP
README in short
The README presents the repo as Bitovi's collection of prompt chains, organized around understanding and writing code. It details an agent instruction generator for a codebase and Jira ticket implementation that pulls Figma designs. Each chain has its own README with steps and inputs. The repo also contains plugin marketplaces for Claude Code and Copilot; MIT licensed.
FAQ
Does it work with GitHub Copilot?
Yes, the repo has a separate Copilot marketplace and Copilot skill variants, and the original prompt chains were written for Copilot Chat.
Related
Official shadcn/ui skill and MCP server: the agent searches registries, adds components via the CLI and follows the library's rules
A frontend design skill with 23 commands, live browser iteration and 61 detector rules for common AI-generated UI tells
Vercel Agent Skills
Agent Skills
Vercel's skills: React and Next.js performance, UI guideline audits, React Native, component composition and deploys
An MCP server that gives the agent simplified Figma layout data from a link so it can build the screen more accurately than from a screenshot