Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".
5368mo agoReviewMountCreate a free account to mount
Create a design brief through an interactive interview, codebase exploration, and experience design decisions. Saved as a markdown file in the project. Use when user wants to write a design brief, plan a new feature or page, define a UI direction, or mentions "brief".
5368mo agoReviewMountCreate a free account to mount
Run the full design-to-build workflow as a guided sequence. Orchestrates all designer skills in order, from grilling through review. Use when user wants to go through the complete design process, start a project from scratch, run the full flow, or mentions "design flow" or "full workflow".
5368mo agoReviewMountCreate a free account to mount
Run a structured design critique against the brief and codebase. Checks visual hierarchy, consistency, responsiveness, accessibility, and aesthetic fidelity. Use when user wants a design review, critique, QA pass, polish pass, or mentions "review" after building.
Generate a design tokens file (CSS variables or Tailwind config) based on a chosen aesthetic philosophy, with light and dark mode palettes, spacing scale, type ramp, and component-level tokens. Use when starting a new project, establishing a visual system, setting up tokens, or mentions "tokens" or "design system".
Build distinctive, production-grade frontend interfaces with high design quality, guided by named aesthetic philosophies. Use when building components, pages, or applications. Generates working code with exceptional attention to aesthetic details and creative choices that avoid generic AI output.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, challenge an approach, or mentions "grill me".
Define the structural layer of a product or site before visual design begins. Covers navigation, content hierarchy, page structure, URL patterns, and user flows. Use when user wants to plan site structure, define navigation, map user flows, organize content, or mentions "IA" or "information architecture".
5368mo agoReviewMountCreate a free account to mount
Guidance for working on this repo. This is the Product Manager Copilot plugin — a Codex / Codex Desktop plugin that packages product-management Agent Skills built on the Pragmatic Institute Framework. - .Codex-plugin/plugin.json — plugin manifest. No version field on purpose (see Releasing below). displayName is Product Manager Copilot; plugin name is product-manager. - .Codex-plugin/marketplace.json — marketplace manifest (product-manager-marketplace). - skills/<name>/SKILL.md — one folder per skill. Skills are auto-discovered from this folder; the manifests do not enumerate them. - skills/pm-copilot/references/…
314mo agoReviewMountCreate a free account to mount
Guidance for working on this repo. This is the Product Manager Copilot plugin — a Claude Code / Claude Desktop plugin that packages product-management Agent Skills built on the Pragmatic Institute Framework. - .claude-plugin/plugin.json — plugin manifest. No version field on purpose (see Releasing below). displayName is Product Manager Copilot; plugin name is product-manager. - .claude-plugin/marketplace.json — marketplace manifest (product-manager-marketplace). - skills/<name>/SKILL.md — one folder per skill. Skills are auto-discovered from this folder; the manifests do not enumerate them. -…
314mo agoReviewMountCreate a free account to mount
An MCP (Model Context Protocol) server that lets AI assistants query Google NotebookLM notebooks. Authenticates via Chrome CDP cookie extraction, communicates with Google's internal batchexecute RPC API, and exposes 9 tools over stdio JSON-RPC. Built with FastMCP, httpx, and Rich. All CLI subcommands support --debug for verbose logging. The setup command also supports --dry-run. 5-layer stack, each layer only calls the one below it: Data flow: MCP JSON-RPC → server.py dispatches → tool function → get_client() returns singleton → NotebookLMClient…
169mo agoReviewMountCreate a free account to mount
Produce a single self-contained .html file instead of a markdown wall when the answer has shape — side-by-side comparisons, a timeline, a diagram, a sortable list, or a deck. This skill should be used when the user invokes /html or any of its patterns (options, plan, pr, codemap, tokens, motion, diagram, deck, explainer, status, editor), and when a request implies a structured artifact — phrases like "show me my options for X", "write the plan", "do a post-mortem", "make a deck from these notes", "let me triage these", "render the design system", "explain how X works", "diagram the flow". Prefer this skill even when the user says "write me a doc" or "summarize" — HTML is often the better surface, and the user can always ask for markdown if they prefer.
MCP Modus is a Model Context Protocol (MCP) server that provides AI assistants with access to Modus Web Components documentation. It runs as a standalone Node.js process that communicates via stdio using JSON-RPC, serving documentation from pre-bundled files. The codebase implements a single-file MCP server with three main responsibilities: The server never writes files or makes network calls at runtime. All documentation is pre-bundled during the build/publish process. The server tries multiple paths to find documentation directories: 1. dist/../docs -…
414mo agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.