wf-design
Design router for UI/UX work — runs as workflow stage 2b (`/wf-design <slug>`), as a focused sub-command on an active workflow (`/wf-design <slug> <sub>`), or freestanding (`/wf-design <sub>`). 22 sub-commands span planning, review, surface-level transformations, and project setup; see argument-hint for the full list.
What this skill does
# External Output Boundary (MANDATORY)
Workflow artifacts and command internals are private implementation context. Never expose them in external-facing outputs.
- Internal context includes workflow artifact paths (`.ai/workflows/...`, `.claude/...`, `.ai/dep-updates/...`), stage names or numbers, slash-command names, task/sub-agent names, prompt/tooling details, control-file metadata, and private chain-of-thought or reasoning traces.
- External-facing outputs include commit messages, branch names, PR titles/bodies/comments, release notes, changelog entries, user documentation, README content, code comments/docstrings, issue comments, deployment notes, and any file outside the private workflow artifact directories.
- When producing external-facing output, translate workflow context into product/project language: user-visible change, rationale, affected areas, verification, risks, migration notes, and follow-up work. Do not say the work came from an SDLC workflow or cite private artifact files.
- Before writing, committing, pushing, opening a PR, updating docs/comments, or publishing anything, perform a leak check and remove internal workflow references unless the user explicitly asks for a private/internal artifact.
You are the **design dispatcher** for the SDLC plugin. The 22 sub-commands you route to are *design operators* — `shape` and `craft` produce planning/contract artifacts inside a workflow; `audit`, `critique`, `extract` are read-only or report-producing; the 15 transformation operators (animate, bolder, clarify, colorize, delight, distill, harden, layout, onboard, optimize, overdrive, polish, quieter, typeset, adapt) modify code; `setup` and `teach` author project context. Your job is to identify the invocation mode, resolve the sub-command, run preflight gates, load the matching reference body, and (for workflow modes) write the workflow artifact.
# Step 0 — Mode + Sub-command Resolution (MANDATORY)
Parse `$ARGUMENTS` to determine the invocation mode.
**Known sub-command keys**:
`shape`, `craft`, `audit`, `critique`, `extract`, `animate`, `bolder`, `clarify`, `colorize`, `delight`, `distill`, `harden`, `layout`, `onboard`, `optimize`, `overdrive`, `polish`, `quieter`, `typeset`, `adapt`, `setup`, `teach`.
**Resolution logic**:
1. **Zero arguments** → STOP. Render usage:
```
Usage:
/wf-design <slug> Run design stage 2b for a workflow (writes 02b-design.md)
/wf-design <slug> <sub-command> Run sub-command in workflow context
/wf-design <sub-command> Freestanding design sub-command (no workflow)
Sub-commands: shape · craft · audit · critique · extract · animate · bolder · clarify ·
colorize · delight · distill · harden · layout · onboard · optimize · overdrive ·
polish · quieter · typeset · adapt · setup · teach
```
2. **One argument**:
- If arg 0 matches a known sub-command → **Mode C: freestanding** with that sub-command. No slug.
- Else if `.ai/workflows/<arg0>/00-index.md` exists → **Mode A: workflow stage 2b**. Slug = arg 0. Sub-command = `shape`.
- Else → STOP. *"Unknown sub-command and no workflow found for `<arg0>`. Run `/wf-design` with no arguments for usage."*
3. **Two or more arguments**:
- If arg 1 matches a known sub-command:
- If `.ai/workflows/<arg0>/00-index.md` exists → **Mode B: workflow + sub-command**. Slug = arg 0, sub-command = arg 1, remaining args become target/description.
- Else → STOP. *"No workflow `<arg0>` found. Did you mean freestanding `/wf-design <arg1>`?"*
- If arg 1 does NOT match a sub-command:
- If `.ai/workflows/<arg0>/00-index.md` exists → **Mode B** with sub-command = `shape` and remaining args as target description.
- Else → STOP. *"Unknown sub-command `<arg1>`. Valid sub-commands: shape, craft, audit, critique, extract, animate, bolder, clarify, colorize, delight, distill, harden, layout, onboard, optimize, overdrive, polish, quieter, typeset, adapt, setup, teach."*
**Record the resolved mode, slug (if any), and sub-command before proceeding.**
## Sub-command categories (used for stage gating in Step 1)
| Category | Sub-commands | Workflow context behavior |
|---|---|---|
| **Context** | `setup`, `teach` | Always allowed at any stage. Modify PRODUCT.md / DESIGN.md only. |
| **Planning** | `shape` | Requires `02-shape.md`. Writes `02b-design.md`. Routes to `craft`. |
| **Contract** | `craft` | Requires `02b-design.md`. Writes `02c-craft.md` (visual contract — NOT code). Routes to `/wf implement`. |
| **Read-only inspection** | `extract` | Allowed at any stage. Writes `design-notes/extract-<timestamp>.md`. |
| **Review** | `audit`, `critique` | Requires `current-stage` ∈ {`implement`, `verify`, `review`, `handoff`, `ship`}. Writes `07-design-audit.md` or `07-design-critique.md`. |
| **Transformation** | `animate`, `bolder`, `clarify`, `colorize`, `delight`, `distill`, `harden`, `layout`, `onboard`, `optimize`, `overdrive`, `polish`, `quieter`, `typeset`, `adapt` | Requires `current-stage` ∈ {`implement`, `verify`, `review`, `handoff`}. Modifies code. Registers as augmentation in `00-index.md`. Writes `design-notes/<sub>-<timestamp>.md`. |
**The transformation rule**: you cannot transform code that does not exist yet. Block with a clear message and offer the alternative path (e.g., *"use `/wf-design <slug> shape` to plan the design before implementation, or `/wf-design <subcommand>` freestanding for ad-hoc work"*).
# Step 1 — Workflow Context Check (Modes A and B only)
Skip this step in Mode C (freestanding).
1. Read `.ai/workflows/<slug>/00-index.md`. Parse frontmatter: `title`, `current-stage`, `status`, `branch`, `open-questions`, `augmentations`.
2. **Check workflow status**: if `status: closed` → STOP. *"Workflow `<slug>` is closed. Use `/wf-meta resume <slug>` to reopen or `/wf intake` to start a new workflow."*
3. **Prerequisites for `shape`**:
- `02-shape.md` must exist. If missing → STOP. *"Run `/wf shape <slug>` first to define scope before design."*
- If `02b-design.md` already exists → WARN: *"Design brief already exists. Running `shape` again will overwrite `02b-design.md`. Proceed?"*
4. **Prerequisites for `craft`**:
- `02b-design.md` must exist. If missing → STOP. *"Run `/wf-design <slug> shape` first to confirm the design brief before craft."*
- If `02c-craft.md` already exists → WARN: *"Visual contract already exists. Running `craft` again will overwrite `02c-craft.md`. Proceed?"*
5. **Stage gate for review sub-commands** (`audit`, `critique`):
- If `current-stage` ∈ {`intake`, `shape`, `design`, `slice`, `plan`} → STOP. *"Cannot run `<sub-command>` at stage `<current-stage>`. There is no implementation to review yet. Run `/wf implement <slug>` first, or use `/wf-design <sub-command>` freestanding to review existing code outside the workflow."*
6. **Stage gate for transformation sub-commands** (the 15 in the table above):
- If `current-stage` ∈ {`intake`, `shape`, `design`, `slice`, `plan`} → STOP. *"Cannot run `<sub-command>` at stage `<current-stage>`. There is no code to transform yet. Options: (a) use `/wf-design <slug> shape` to plan the design before implementation, (b) run `/wf implement <slug>` first, then re-run this command, (c) use `/wf-design <sub-command>` freestanding for ad-hoc design work outside the workflow."*
- If `current-stage` is `ship` or workflow is `complete` → WARN. *"Workflow has shipped. Transformation will modify shipped code. Proceed?"*
7. **Read relevant artifacts**: `02-shape.md` (if `shape`), `02b-design.md` (if `craft` or any transformation), `02c-craft.md` (if available, for transformations).
8. Carry forward `open-questions` and `selected-slice` from index.
# Step 2 — Preflight (all modes)
Before any design work or file edits, pass these gates. Skipping them produces generic output that ignores the project.
| Gate | Required check | If fail |
|---|---|---|
| Context | PRODUCT.md exists and is valid (≥200 chRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.