By micserr
Product design workflow for Toge (shadcn-vue) — screen specs, design QA, animations, and developer handoff.
Animation and micro-interaction principles from Emil Kowalski and Jakub Krehel. Use when adding animations, hover states, enter/exit transitions, icon state changes, button feedback, or any motion detail to a prototype. Triggers on "add animations", "make it feel better", "feels off", "hover state", "transition", "easing", "scale on press", "micro-interactions".
Use when reviewing a design for quality assurance, auditing visual consistency, checking accessibility, validating design token usage, or evaluating a screen before handoff. Trigger phrases: "design QA", "review this design", "audit the UI", "check the design", "design review", "QA this screen", "is this design ready", "before handoff", "design audit".
Use when applying design tokens, choosing colors, typography, spacing, or surface styles for a product UI. Trigger phrases: "what token should I use", "design token", "color token", "apply tokens", "which color for", "semantic color", "dark mode token", "typography token", "surface token", "what class for", "token for danger", "token for success".
Developer handoff pass — cleans and restructures prototype code for production readiness. Splits oversized components, extracts composables, types all props/emits, removes prototype artifacts (mock delays, console.logs, placeholder comments), and verifies file structure. Trigger phrases: "ready for handoff", "clean up the code", "handoff pass", "production ready", "prepare for dev", "clean for frontend".
Reads and writes the team-wide UX Learnings file — the agent's institutional memory. Accumulates patterns, anti-patterns, component preferences, conventions, and recurring QA findings across features so each new design benefits from everything the team has already learned. Called by design-qa and handoff after completing their passes. Human-callable for manual entries: "remember this", "add to learnings", "that worked well — save it", "what have we learned".
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of Claude Code skills and an agent for product designers. Covers the full product design workflow — market research, problem framing, user journeys, prototyping, design QA, and animations — so you can run structured, repeatable design thinking directly from your terminal.
See PROMPTS.md for ready-to-use prompts for every skill and workflow.
| Skill | What it does | Trigger phrases |
|---|---|---|
toge:prd-gap-analyzer | Mesh Mode screen spec generator — reads a product outcome (why) + product unit (what) and produces a ux-screen-spec: actors, screens, states, flow, and open design decisions. Standalone equivalent of the agent's inline Phase 0. | "generate screen spec", "translate this to screens", "what screens do I need", "run Phase 0" |
toge:prd-ux-validator | Optional research enrichment — validates a PRD against secondary research and produces a research brief. Not required in the core workflow; use for novel markets or high-stakes UX decisions. | "validate the PRD", "research against the PRD", "enrich with research" |
toge:secondary-research | Free-form competitive and market research — produces an 18-section research brief for use when no PRD exists | "research X", "competitive analysis", "landscape of X", "desk research on X" |
| Skill | What it does | Trigger phrases |
|---|---|---|
toge:user-journey | Journey maps and user flow diagrams | "user journey", "user flow", "map the flow", "journey map" |
toge:design-tokens | Token architecture, semantic color families, typography, dark mode | "what token should I use", "design token", "which color for", "semantic color" |
toge:design-qa | Pre-handoff QA across 4 pillars: visual consistency, token compliance, accessibility, interaction readiness | "design qa", "review this design", "audit the UI", "is this ready for handoff" |
toge:animations | Micro-interactions, hover states, enter/exit transitions, easing, and icon state changes (optional phase — designer decides) | "add animations", "make it feel better", "feels off", "hover state", "transition", "easing", "scale on press" |
toge:handoff | Developer handoff pass — splits oversized components, extracts composables, types props/emits, removes prototype artifacts, verifies file structure | "ready for handoff", "clean up the code", "handoff pass", "production ready", "prepare for dev" |
| Skill | What it does |
|---|---|
toge:workflow-state | Reads/writes the feature-scoped workflow ledger. Invoked by other skills; not called by humans directly. No-op on profiles without a ledger. |
toge:learnings | Reads/writes the team-wide UX Learnings file. Read at session start as passive design context. Invoked automatically after design-qa and handoff to capture patterns, anti-patterns, and recurring QA findings. Human-callable for manual entries: "remember this", "add to learnings", "what have we learned". |
Temporarily out of rotation — not auto-discovered by the plugin and not exposed under /toge:. See archive/.
| Skill | What it did | Status |
|---|---|---|
prototype | Built an interactive Vue 3 prototype from a user flow and layout reference | Archived 2026-06-17 — returning in a future release |
Sprout skills are SDLC-neutral — they read the active profile to know where to write, what front-matter shape to use, which other agents to coexist with, and where prototype code lives.
Two profiles ship:
bmad — full BMAD mesh (implem-aidlc style). Outputs land in _bmad-output/planning-artifacts/ux/, Sally's UX spec is preferred input when present, feature-scoped ledger at _bmad-output/state/, prototype code goes to sibling implem-prototype/ repo.vanilla — no framework. Outputs land in docs/design/, no coexistence agents, no ledger, prototype code in-repo under prototype/.At install, pick your profile (adapters/claude.sh asks; adapters/bmad.sh auto-selects bmad). Override per-repo with $REPO/.sprout/profile.yaml. Teams on other SDLCs (Linear, Notion, Shape Up, custom) can author their own profile — see profiles/README.md or docs/profiles-guide.md.
A dual-mode agent — acts as an advisor for focused design questions, or as an orchestrator that runs the full workflow from a PRD.
npx claudepluginhub micserr/sprout-design-agent --plugin togeComprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.