agentleFS
ww-w-aiww-w-ai/bkit-gemini/skills/development-pipeline/SKILL.md

development-pipeline

Skill66 starsChanged 7 months agoApache-2.0View on GitHub

9-phase Development Pipeline complete knowledge. Use when user doesn't know development order or starts a new project.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Development Pipeline

9-Phase Development Pipeline for systematic project development

The 9 Phases

PhaseNamePurposePDCA
1SchemaDefine terminology & data structuresPlan
2ConventionSet coding rules & standardsPlan
3MockupCreate UI/UX prototypesDesign
4APIDesign & implement backend APIDo
5Design SystemBuild component libraryDo
6UI IntegrationConnect frontend to backendDo
7SEO/SecurityOptimize & secureDo
8ReviewCode & architecture reviewCheck
9DeploymentDeploy to productionAct

Phase by Level

Starter (Static Web)

Phase 1 → 2 → 3 → 6 → 9
(Skip: 4, 5, 7, 8)

Dynamic (Fullstack)

Phase 1 → 2 → 3 → 4 → 6 → 9
(Optional: 5, 7, 8)

Enterprise (Microservices)

Phase 1 → 2 → 3 → 4 → 5 → 6 → 7 → 8 → 9
(All required)

Commands

# Start pipeline
/development-pipeline start

# Check current status
/development-pipeline status

# Move to next phase
/development-pipeline next

Phase Details

Phase 1: Schema

  • Define domain terminology
  • Create data models
  • Document relationships

Phase 2: Convention

  • Naming conventions
  • Code style rules
  • Git workflow

Phase 3: Mockup

  • Wireframes
  • UI components
  • User flows

Phase 4: API

  • Endpoint design
  • Request/response schemas
  • Authentication

Phase 5: Design System

  • Component library
  • Design tokens
  • Storybook

Phase 6: UI Integration

  • Frontend implementation
  • State management
  • API integration

Phase 7: SEO/Security

  • Meta tags
  • Security headers
  • Vulnerability scan

Phase 8: Review

  • Code review
  • Architecture audit
  • Performance check

Phase 9: Deployment

  • CI/CD setup
  • Environment config
  • Go live

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.