pm-kit
01Plugin Claude Code
Bundles 39 skills, 4 agents, 2 hooks · 2,541 tokens together
AI-augmented knowledge vault for Technical PMs and Engineering Leads — PRDs, sprints, decisions, blockers, daily standups, HTML previews, executive briefs.
Plugin Claude Code
Bundles 39 skills, 4 agents, 2 hooks · 2,541 tokens together
AI-augmented knowledge vault for Technical PMs and Engineering Leads — PRDs, sprints, decisions, blockers, daily standups, HTML previews, executive briefs.
Skill Claude CodeCodex
Build animated technical diagrams (flowcharts, decision trees, pipelines) as Remotion + React videos. You describe the diagram in plain English, Claude writes Mermaid, and a set of React components bake in the design system, auto-layout, and animation patterns — node/edge reveals, trace dots that follow a path and…
Skill Codex
Run two independent subagents through a structured debate on the same prompt: independent answers, cross-critique, revision, and a synthesized unified response. Use when explicitly invoked as $debate-brainstorm or /debate-brainstorm with a prompt, or when the user asks for a two-agent debate or adversarial comparison…
Skill Claude CodeCodex
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.
Skill Claude CodeCodex
Create Excalidraw diagrams as JSON files for flowcharts, user journeys, system architectures, wireframes, and visual documentation. Use when the user asks to create diagrams, flowcharts, visual representations, architecture diagrams, mind maps, or any Excalidraw-compatible visualizations. Outputs .excalidraw.json…
Skill Claude CodeCodex
Rewrites ambiguous English into ASD-STE100 style — one meaning per word, active voice, simple tense, short sentences. Use when agent output is hard to parse; triggers: simplify this, STE100 rewrite.
Skill Claude CodeCodex
Explains difficult concepts and unfamiliar code with adaptive, multilingual clarity. Use for “explain to me,” “help me understand,” “how does this work,” simple, visual, beginner-friendly, or step-by-step requests; architecture, data flow, state, ownership, trade-offs, difficult concepts, or confusion; and equivalent…
Skill Claude CodeCodex
Explains technical systems, abstract concepts, workflows, architecture, comparisons, loops, and tradeoffs using plain language and readable ASCII diagrams. Use when the user asks how something works, requests a visualization, seems confused by a difficult concept, or would benefit from a clear mental model before…
Skill Claude CodeCodex
This skill should be used when the user asks to "set up gws", "install Google Workspace CLI", "connect Gmail to Claude", "manage Google Drive from terminal", "send email from CLI", "check my calendar", "create a Google Doc", "use gws", "Google Workspace agent", or mentions gws CLI, Google Workspace automation, or…
Skill Claude CodeCodex
Set up and run Ralph Wiggum loop - autonomous AI coding with clean slate iterations, PRD-driven features, and CI quality gates. Use for long-running autonomous coding tasks.
Skill Claude CodeCodex
Implements a specific UI animation or transition. Use when asked to build motion; not for discovering opportunities, auditing an interface, reviewing a diff, or naming an effect.
Skill Claude CodeCodex
Names a motion effect from a plain-language description and distinguishes close terms. Use for “what is this animation called?” questions, not design or implementation.
Skill Claude CodeCodex
Applies an explicitly Apple-style design language to web interfaces: fluid gestures, interruptible springs, translucent materials, depth, and platform-like typography. Use when the user asks for Apple/iOS/macOS-inspired behavior or styling.
Skill Claude CodeCodex
Implements and troubleshoots Sonner React toasts, including setup, promise flows, styling, themes, positioning, and duplicate or missing toasts. Use only for Sonner-specific work.
Skill Claude CodeCodex
Creates polished Vietnamese HTML proposals for business owners and investment partners, focused on product scope, customer experience, roadmap, and operating model. Use when preparing a client-facing proposal, pitch document, or HTML-to-PDF presentation.
Skill Claude CodeCodex
Turns writing, products, workflows, or abstract ideas into a tailored UI-driven motion-graphics video. Use when the requested deliverable is a scripted, storyboarded, rendered video rather than an interface animation.
Skill Claude CodeCodex
Explains a technical spec or proposed change in short, plain language. Use when the user explicitly asks for an ELI5 explanation.
Skill Claude Code
Applies Emil Kowalski-inspired design-engineering philosophy when explicitly requested. Use for opt-in guidance on UI taste, polish, interaction craft, and invisible details; use the dedicated animation skills for motion tasks.
Skill Claude CodeCodex
Explains code, system behavior, and code changes with plain technical prose, before and after diagrams, pseudocode, call trees, and diffs. Use for architecture walkthroughs, when asked how something works, or when explaining what a change does: a diff, a commit, a pull request, or the work just done in this thread.
Skill Claude CodeCodex
Finds high-value places where missing motion harms feedback, continuity, or comprehension. Use for a read-only search for animation opportunities; it does not audit existing motion or implement changes.
Skill Claude CodeCodex
A design workflow for creating HTML prototypes, slide decks, interactive slides, PDFs, animations, visualizations, and design critiques. It supports requests made in English, Vietnamese, or Chinese and can export video or GIF files when requested.
Skill Claude CodeCodex
Audits codebase motion and produces prioritized improvement plans. Use for animation roadmaps; implementation requires an explicit execute request.
Skill Claude CodeCodex
Edit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI. Also the default writing standard for all agent…
Skill Claude Code
Pick the right library for a given frontend task from a curated, opinionated list — numbers, OTP inputs, charts, command menus, virtualization, drag and drop, toasts, state, styling, and more. Only runs when explicitly invoked; it does not trigger on its own.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: