review-plan
Reviews and edits all existing plan files based on user feedback. Accepts feedback from arguments (/review-plan change X to Y) or via AskUserQuestion. Same sequential flow as /plan (ui-ux -> tech-lead -> frontend+backend parallel) but EDITS existing plans instead of creating from scratch. Also updates progress.json if it exists. Triggers on: review plan, edit plan, update plan, change plan, revise plan, adjust plan.
What this skill does
# Review Plan Skill
Edit and update all existing plan files based on user feedback, following the same orchestration flow as `/plan`.
---
## How It Differs from /plan
| Aspect | /plan | /review-plan |
|--------|-------|-------------|
| Purpose | Create plans from scratch | Edit existing plans |
| Input | PRD file | User feedback + existing plans |
| Agent action | Write new files | Read existing files, apply changes, rewrite |
| progress.json | Not created (use /complete-plan) | Updated/regenerated if it exists |
| Prerequisite | PRD must exist | Plan files must exist |
---
## Flow
```
/review-plan [user feedback OR empty]
|
v
+----------------------------------------------------------+
| STEP 1: Get review feedback |
| - From arguments: /review-plan change auth to OAuth |
| - OR from AskUserQuestion if no arguments provided |
+----------------------------------------------------------+
|
v
+----------------------------------------------------------+
| STEP 2: Verify existing plan files |
| - docs/ui-ux-plan.md (REQUIRED) |
| - docs/dev-plan.md (REQUIRED) |
| - docs/frontend-plan.md (REQUIRED) |
| - docs/backend-plan.md (REQUIRED) |
| - docs/progress.json (optional — update if exists) |
+----------------------------------------------------------+
|
v
+----------------------------------------------------------+
| STEP 3: ui-ux-specialist (SEQUENTIAL) |
| - Reads: docs/ui-ux-plan.md + user feedback |
| - EDITS and rewrites: docs/ui-ux-plan.md |
+----------------------------------------------------------+
|
v
+----------------------------------------------------------+
| STEP 4: tech-lead-specialist (SEQUENTIAL) |
| - Reads: updated docs/ui-ux-plan.md + user feedback |
| - EDITS and rewrites: docs/dev-plan.md |
+----------------------------------------------------------+
|
v
+----------------------------------------------------------+
| STEP 5: PARALLEL — frontend + backend specialists |
| |
| frontend-specialist |
| - Reads: updated docs/dev-plan.md + user feedback |
| - EDITS and rewrites: docs/frontend-plan.md |
| |
| backend-specialist |
| - Reads: updated docs/dev-plan.md + user feedback |
| - EDITS and rewrites: docs/backend-plan.md |
+----------------------------------------------------------+
|
v
+----------------------------------------------------------+
| STEP 6: progress-creator (SEQUENTIAL, only if exists) |
| - Reads: updated dev-plan.md, frontend-plan.md, |
| backend-plan.md |
| - Rewrites: docs/progress.json |
+----------------------------------------------------------+
|
v
+----------------------------------------------------------+
| STEP 7: Report changes |
+----------------------------------------------------------+
```
---
## Step 1: Get Review Feedback
### Option A: Feedback from arguments
If the user invokes with arguments:
```
/review-plan change the auth flow to use OAuth instead of magic links
/review-plan add a dark mode toggle to the settings page
/review-plan remove the billing feature entirely
```
Extract the feedback directly from the arguments. **Do NOT ask questions — the user already told you what to change.** Proceed directly to Step 2.
### Option B: No arguments provided
If the user invokes with no arguments (`/review-plan`), you MUST use AskUserQuestion to gather feedback.
```
AskUserQuestion:
question: "What changes would you like to make to the plan?"
header: "Change Type"
options:
- label: "Add a feature"
description: "Add a new feature or capability to the plan"
- label: "Remove a feature"
description: "Remove an existing feature from the plan"
- label: "Change approach"
description: "Modify how a feature is implemented"
- label: "I'll describe it"
description: "Provide detailed feedback in my own words"
```
Then follow up with a specific question based on their choice:
**If "Add a feature":**
```
AskUserQuestion:
question: "What feature would you like to add? Describe it briefly."
header: "New Feature"
options:
- label: "New page/screen"
description: "Add a new page with its own route"
- label: "New component/widget"
description: "Add a new UI element to an existing page"
- label: "New backend capability"
description: "Add new tables, APIs, or data processing"
- label: "I'll describe it"
description: "Let me explain what I need"
```
**If "Remove a feature":**
```
AskUserQuestion:
question: "Which feature should be removed?"
header: "Remove"
options:
- label: "I'll specify it"
description: "Let me name the feature to remove"
```
**If "Change approach":**
```
AskUserQuestion:
question: "What would you like to change?"
header: "Change"
options:
- label: "UI/UX design"
description: "Change layout, colors, components, user flows"
- label: "Backend/database"
description: "Change schema, APIs, data model"
- label: "Tech stack"
description: "Change frameworks, libraries, tools"
- label: "I'll describe it"
description: "Let me explain the change"
```
### Question Rules
- Maximum **3 questions** to gather feedback
- If the user provided arguments, ask **ZERO questions** — use their input directly
- Capture the full feedback as `{user_feedback}` for all agent prompts
---
## Step 2: Verify Existing Plan Files
Check that required plan files exist:
```
Glob: **/ui-ux-plan.md
Glob: **/dev-plan.md
Glob: **/frontend-plan.md
Glob: **/backend-plan.md
Glob: **/progress.json
```
### If any REQUIRED file is missing:
Tell the user which files are missing and suggest running `/plan` first:
> Missing: `[file]`. Run `/plan` first to create all plan files, then use `/review-plan` to edit them.
**STOP. Do NOT proceed with partial plans.**
### Track progress.json existence:
```
has_progress_json = true/false
```
If `progress.json` exists, it will be regenerated in Step 6.
---
## Step 3: Spawn ui-ux-specialist — EDIT Mode (SEQUENTIAL)
```
Task:
subagent_type: ui-ux-specialist
description: "Edit UI/UX plan"
prompt: |
You are in REVIEW/EDIT mode — NOT creating from scratch.
Read the EXISTING plan:
- docs/ui-ux-plan.md
User feedback to apply:
---
{user_feedback}
---
Instructions:
1. Read docs/ui-ux-plan.md completely
2. Identify which sections are affected by the user's feedback
3. Apply the requested changes to those sections
4. Keep all UNAFFECTED sections exactly as they are — do not rewrite unchanged content
5. Add a "## Revision Log" section at the bottom with:
- Date of revision
- Summary of what changed
6. Write the updated file back to: docs/ui-ux-plan.md
IMPORTANT:
- This is an EDIT, not a rewrite. Preserve existing work.
- Only change what the user asked to change.
- If the feedback doesn't affect UI/UX (e.g., only backend changes), make no changes and return "No UI/UX changes needed."
Write the file using the Write tool. Return "Done: docs/ui-ux-plan.md [summary of changes]" when complete.
```
**Wait for completion before proceeding.**
Verify:
```
Glob: docs/ui-ux-plan.md
```
---
## Step 4: Spawn tech-lead-specialist — EDIT Mode (SEQUENTIAL)
```
Task:
subagent_type: tech-lead-specialist
description: "Edit dev plan"
prompt: |
You are in REVIEW/Related 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.