Skip to content

OffchainLabs/arbitrum-docs / .agents/skills/implement

implement

Verified

Orchestrate the implementation workflow. Use after requirements are defined to design, build, validate, polish, and document. Triggers on "implement this", "build this", "start implementation", "execute the plan".

Implementation Workflow

Orchestrate the implementation pipeline.

When working on Arbitrum projects, use @arbitrum-best-practices for domain-specific patterns.

Workflow

/context-prep                → Project Orientation (if needed)
design                       → Implementation Planning (architect)
execute                      → Implementation (engineer)
qa                           → Validation (qa)
polish                       → Naming Review & Cleanup (code-quality-engineer)
docs                         → Documentation (docs)

Note: Run /context-prep first if starting a new session or after context loss.

Prerequisites

Before running this workflow, ensure:

  • Requirements are defined
  • Specifications exist OR provide them inline

Instructions

Execute phases sequentially using the Task tool:

Design

subagent_type: architect

  • Design system architecture
  • Define component boundaries
  • Specify file paths and integration points
  • Create implementation plan with dependencies

Execute

subagent_type: engineer

  • Implement according to design
  • Write production-ready code
  • Include error handling and edge cases
  • Run initial tests

QA

subagent_type: qa

  • Hostile falsification testing
  • Edge case verification
  • Security and performance validation
  • Ensure implementation matches specifications

Polish

subagent_type: code-quality-engineer

  • Audit naming conventions
  • Remove debug artifacts
  • Ensure code clarity and consistency

Docs

subagent_type: docs

  • Document new features
  • Update API references
  • Create usage examples

Quick Start

For simple implementations, run design-execute-qa only:

1. Design → 2. Build → 3. Validate

Add polish and docs for public APIs or significant features.

Output

Implementation report includes:

  • Changes made (file paths, key functions)
  • Validation results
  • Unresolved Questions (even if "None")
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 318kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 196kUpdated Claude CodeCodexVerifiedInstall