xiaohongshu
xiaohongshu
feature-build
Orchestrator skill for the complete feature development lifecycle. Coordinates 5 phases - task selection, component design, build loop, analytics setup, and commit/documentation. Use when building any new feature or enhancement that requires multiple steps.
Full skill instructions
Orchestrates the complete feature development lifecycle with clear phases, entry/exit criteria, and conversation loop patterns. This skill transforms feature requests into shipped, tested, and documented code.
Inputs:
Outputs:
Success Criteria:
Acceptance Criteria First — Define what "done" looks like before writing code. Testable criteria prevent scope creep and enable verification.
Components Live in Style Guide — Every UI component starts in the style-guide page. This ensures reusability, documents all states, and provides a living reference.
Test What You Build — Use browser tools to verify each step. Don't wait until the end to discover issues.
KISS (Keep It Simple, Stupid) — Implement the simplest solution that meets the criteria. Avoid over-engineering.
Loop Back, Don't Push Forward — When something doesn't work, return to the appropriate phase rather than patching around issues.
Features are built through phases that can loop back when issues arise:
┌───────────────────────────────────────────────────────────────────────────────┐
│ │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌─────────────┐ │
│ │ Task │──▶│Component │──▶│ Build │──▶│Analytics │──▶│ Build │ │
│ │Selection │ │ Design │ │ Loop │ │ Setup │ │Verification │ │
│ └──────────┘ └──────────┘ └──────────┘ └──────────┘ └─────────────┘ │
│ ▲ │ │ │ │ │
│ │ ▼ ▼ ▼ ▼ │
│ │ ◀────────────◀─────────────◀──────────────────────────────────│
│ │ (loop back if criteria fail or build errors) │
│ │ │
│ │ ┌──────────────┐ │
│ └────────────────────────────────────────────────────│ Commit & │◀──│
│ (next feature) │ Document │ │
│ └──────────────┘ │
└───────────────────────────────────────────────────────────────────────────────┘
Read TASKS.md — Identify the next item from Current Sprint
Read TASKS.md and identify the next unchecked item in Current Sprint
Confirm Scope — Clarify with user what's included and excluded
Break Down if Complex — Split large features into sub-tasks
Define Acceptance Criteria — Write testable criteria
### Feature: [Name]
**Acceptance Criteria:**
- [ ] User can [specific action]
- [ ] System [specific behavior] when [condition]
- [ ] Error case: [scenario] displays [message]
- [ ] Mobile: [behavior] works on viewport < 768px
Check Style Guide First — Look for existing components that can be reused or extended
Navigate to /style-guide and snapshot to see existing components
Design in Style Guide — Build new components in the style-guide page
components/ui/ barrel fileShow All States — Document every component state:
Mobile Considerations — Test responsive behavior
<section id="my-component">
<SectionHeader title="My Component" />
<div className="space-y-6">
<h4 className="text-xs font-medium text-muted-foreground uppercase tracking-wide">
Variants
</h4>
<div className="flex flex-wrap gap-3">
<MyComponent variant="default" />
<MyComponent variant="secondary" />
</div>
<h4 className="text-xs font-medium text-muted-foreground uppercase tracking-wide">
States
</h4>
<div className="flex flex-wrap gap-3">
<MyComponent loading />
<MyComponent disabled />
<MyComponent error="Error message" />
</div>
</div>
</section>
/style-guidecomponents/ui/index.tsBuild data layer and API before wiring to UI:
Wire components to backend:
Test at each step using Cursor browser tools:
1. Navigate to the page being tested
2. Snapshot to get element references
3. Interact with elements (click, type, etc.)
4. Re-snapshot after state changes
5. Verify expected behavior
6. Screenshot if visual verification needed
See references/testing-patterns.md for detailed testing scenarios.
Forms:
Lists/Tables:
Modals/Dialogs:
Navigation:
Return to Phase 2 if:
Return to Phase 1 if:
Identify Tracking Needs — What user actions matter?
| Feature Type | Typical Events |
|---|---|
| Form | {form}_submitted, {form}_error |
| Feature | {feature}_used, {feature}_completed |
| Navigation | {page}_viewed |
| Pro Feature | {feature}_attempted, {feature}_upgrade_shown |
Implement Events — Add PostHog capture calls
posthog.capture('{feature}_{action}', {
feature: 'feature-name',
// action-specific properties
})
Create Dashboard (if appropriate) — Use PostHog MCP tools
Use mcp_posthog-study-bible_dashboard-create for new dashboards
Use mcp_posthog-study-bible_insight-create-from-query for insights
Pro Features — If feature is gated, follow feature-gating skill:
useProFeature() hook_attempted, _upgrade_shown, _upgrade_clicked events{feature}_{action}
Examples:
- notes_created
- notes_synced
- chat_message_sent
- upgrade_modal_shown
- model_changed
Run Production Build
npm run build
Check Linter
npm run lint
Verify No Regressions
Return to Phase 3 if:
npm run build succeeds with exit code 0npm run lint passes (no errors)Update TASKS.md
Update CHANGELOG.md
Stage and Commit
<type>(<scope>): <subject>
Types: feat, fix, docs, style, refactor, perf, test, chore, ci, build, revert
Provide at end of feature for easy copy-paste:
### Done
**Summary**: [Brief description of what was built]
**Commits** (ohmyzsh):
gaa && gcmsg "feat(scope): add feature description"
gcmsg "fix(scope): fix related issue"
gp
## Completed
- [x] Feature name (YYYY-MM-DD)
- [x] Sub-task 1 ✓
- [x] Sub-task 2 ✓
- [x] Sub-task 3 ✓
| Phase | Entry | Exit |
|---|---|---|
| 1. Task Selection | Feature request | Criteria defined |
| 2. Component Design | Criteria clear | Components in style-guide |
| 3. Build Loop | Components ready | All criteria pass in browser |
| 4. Analytics | Feature working | Events instrumented |
| 5. Build Verification | Analytics done | npm run build succeeds |
| 6. Commit | Build passes | Docs updated, committed |
# Start dev server
npm run dev
# Clear Next.js cache if issues
rm -rf .next
# Rebuild native modules
npm rebuild better-sqlite3
# Git workflow (ohmyzsh)
gaa && gcmsg "feat(scope): description"
gp
1. mcp_cursor-ide-browser_browser_navigate → load page
2. mcp_cursor-ide-browser_browser_snapshot → get elements
3. mcp_cursor-ide-browser_browser_click/type → interact
4. mcp_cursor-ide-browser_browser_snapshot → verify changes
5. mcp_cursor-ide-browser_browser_take_screenshot → visual check
xiaohongshu
technical spec
product ux expert
database patterns
Conduct multi-agent task orchestration and workflow coordination.
Initialize project with Conductor artifacts (product definition,
Expert in web animations, transitions, and motion design using Framer Motion and CSS
Creates Mermaid and ASCII diagrams for flowcharts, architecture, ERDs, state machines, mindmaps, and more. Use when user mentions diagram, flowchart, mermaid, ASCII diagram, text diagram, terminal diagram, visualize, C4, mindmap, architecture diagram, sequence diagram, ERD, or needs visual docume...
PostgreSQL bindings for H3 hexagonal grid system. Use when working with H3 cells in Postgres, including spatial indexing, geometry/geography integration, and raster analysis.
Context-Driven Development skill for projects using Conductor. Use this skill when you detect a `conductor/` directory in the project, when working on tasks defined in a `plan.md` file, or when the user asks about tracks, specs, or plans. Automatically applies TDD workflow, tracks task completion...
Display project status, active tracks, and next actions
Official Stakpak application containerization standard operating procedure, a step-by-step guidline to properly dockerize applications. This is a rule book curated by the Stakpak Team.
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience