Build a personal library of prompts and skills. SkillStorr's MCP server and browser extension make them available everywhere — Claude, ChatGPT, Cursor, Gemini, Perplexity, and more.
Works with every AI tool
Generate an API key, paste a config snippet. Your prompts and skills become callable tools inside any MCP-compatible client.
Press ⌘K in any input field on any web AI tool. Pick a prompt. Insert. Works on tools without MCP support.
Write and publish prompts. Browse, install, and use prompts written by others. All on one library.
Slash menu, AI commands, @-mentions to reference other prompts. Feels like writing a doc.
Compose prompts from sub-prompts. Resolved on demand by the agent — saving tokens, keeping context lean.
Group related prompts into a single callable skill. Ship as a unit. Update once, propagates everywhere.
Comments anchored to text. Suggested changes, GitHub-style. Versioned.
Slash menu for blocks. Inline AI suggestions when you get stuck. @-mention any other prompt to compose them — no more copy-paste prompt soup.
You are a staff engineer doing a careful PR review.
Focus on:
When reviewing TypeScript, also apply @typescript-style-guide.
For backend code, defer to @security-checklist on auth flows.
When a prompt @-mentions another, we don't dump the whole graph into your context. The agent fetches references on demand — keeping prompts modular and your token bill sane.
Publish any prompt or skill to the public catalog.
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma). origin: ECC
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo. origin: ECC
Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices"