agentleFS
Sign inStart free
phoenixvnphoenixvn/claude-code-agency/.claude/skills/team-website/SKILL.md

team-website

Skill0 starsChanged 7 months agoMITView on GitHub

The most complex orchestration. 8+ agents across 8 phases. Full website from architecture to launch-ready. USER APPROVAL GATE — Approve tech stack and architecture. USER APPROVAL GATE — Approve wireframes. USER APPROVAL GATE — Approve visual design. frontend-developer → src/frontend/: - Build pages from wireframes and design specs - Create reusable components from design system - Implement responsive layouts - Add loading, error, and empty states backend-developer → src/backend/: - Build API endpoints from architecture spec - Implement authentication and…

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 9 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write ADR to deliverables/docs/architecture.md

    line 14
  2. Distinctive:

    Create user flows for key journeys (signup, purchase, contact, browse)

    line 20
  3. Distinctive:

    Create text-based wireframes for all key pages

    line 22
  4. Distinctive:

    Create responsive breakpoint specs

    line 31
  5. Distinctive:

    Document interactive behaviors (hover, click, transitions)

    line 32
  6. Very specific:

    Create project structure in src/

    line 42
  7. Distinctive:

    Create reusable components from design system

    line 50
  8. Distinctive:

    Add loading, error, and empty states

    line 52
  9. Distinctive:

    Create service layer with business logic

    line 57
  10. Distinctive:

    Add input validation and error handling

    line 58
  11. Distinctive:

    Write seed data for development

    line 63
  12. Very specific:

    Update active.md. Suggest /team-launch for go-live or /deploy for deployment.

    line 94

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/team-website — Website Build Pipeline

The most complex orchestration. 8+ agents across 8 phases. Full website from architecture to launch-ready.

Instructions

Phase 1: Architecture (technical-director)

Spawn technical-director to:

  • Review brief, design specs, and any existing technical constraints
  • Define tech stack (present options via AskUserQuestion)
  • Design system architecture (text-based C4 diagram)
  • Define data model and API endpoints
  • Write ADR to deliverables/docs/architecture.md

USER APPROVAL GATE — Approve tech stack and architecture.

Phase 2: UX Design (ux-lead)

Spawn ux-lead to:

  • Create user flows for key journeys (signup, purchase, contact, browse)
  • Define information architecture and navigation
  • Create text-based wireframes for all key pages
  • Save to deliverables/design/wireframes/

USER APPROVAL GATE — Approve wireframes.

Phase 3: Visual Design (ui-designer)

Spawn ui-designer to:

  • Apply brand guidelines to wireframes
  • Define component specifications with all states
  • Create responsive breakpoint specs
  • Document interactive behaviors (hover, click, transitions)
  • Save to deliverables/design/design-system.md

USER APPROVAL GATE — Approve visual design.

Phase 4: Project Setup (devops-engineer)

Spawn devops-engineer to:

  • Initialize project (Next.js, Tailwind, TypeScript, etc.)
  • Configure ESLint, Prettier, TypeScript
  • Set up testing framework (Jest, Playwright)
  • Create project structure in src/
  • Initialize git repository

Phase 5: Implementation (PARALLEL: frontend-developer + backend-developer + database-engineer)

Spawn in parallel:

frontend-developer → src/frontend/:

  • Build pages from wireframes and design specs
  • Create reusable components from design system
  • Implement responsive layouts
  • Add loading, error, and empty states

backend-developer → src/backend/:

  • Build API endpoints from architecture spec
  • Implement authentication and authorization
  • Create service layer with business logic
  • Add input validation and error handling

database-engineer (if needed):

  • Set up database schema from data model
  • Create migrations
  • Write seed data for development

USER APPROVAL GATE — Review code before integration.

Phase 6: Content Integration (content-writer + copywriter)

Spawn:

  • content-writer: Write page copy — headlines, body text, feature descriptions
  • copywriter: CTAs, microcopy, form labels, error messages, meta descriptions

Integrate all content into the built pages. SEO metadata for all pages.

Phase 7: Quality Assurance (PARALLEL: qa-tester + performance-analyst + accessibility-specialist)

Spawn in parallel:

qa-tester: Functional testing, cross-browser, responsive performance-analyst: Lighthouse audit, Core Web Vitals accessibility-specialist: WCAG 2.1 AA compliance

Compile bug report with severity ratings.

USER APPROVAL GATE — Review bugs. Fix Critical and Major before proceeding.

Phase 8: Launch Preparation (project-lead)

Spawn project-lead to create:

  • Pre-launch checklist
  • DNS and SSL verification plan
  • Analytics and tracking setup checklist
  • Launch timeline and rollback strategy
  • Final sign-off document

Update active.md. Suggest /team-launch for go-live or /deploy for deployment.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free