Skip to content

Implementation Workflow

Build a feature end-to-end: plan the approach, set up the worktree and branch, implement incrementally with verification at every step, and know when to stop and re-plan. Use when the agent has been asked to build, implement, or ship a feature - the standard engineering loop from 'go' to 'ready for review'.

Software Engineering|v1|Updated 7/16/2026|License: Proprietary
MCP get_skill({ skillId: "implementation-workflow" })

Use this skill with your agent

Create a free account and connect via MCP

Get Started Free
---
title: "Implementation Workflow"
description: "Build a feature end-to-end: plan the approach, set up the worktree and branch, implement incrementally with verification at every step, and know when to stop and re-plan. Use when the agent has been asked to build, implement, or ship a feature - the standard engineering loop from 'go' to 'ready for review'."
author: AgentArmory
license: Proprietary
---

# Implementation Workflow

Build features systemically: plan, implement incrementally, verify continuously, and know when to stop and re-plan. This is the core engineering loop every agent follows - from "go" to "ready for review" - and it is the entry point for the agentic SWE workflow family.

Research shows AI coding agents produce ~1.7x more issues than human-authored code (CodeRabbit, 2025), with the #1 failure being premature jumping to implementation without a plan (Stack Overflow, 2026). This skill counters both patterns.

## Table of Contents

- [When to Use](#when-to-use)
- [Triggers](#triggers)
- [Prerequisites](#prerequisites)
- [Methodology](#methodology)
- [Dos](#dos)
- [Don'ts](#don'ts)
- [Pitfalls](#pitfalls)
- [Nonsense Check](#nonsense-check)
- [Validate Before Shipping](#validate-before-shipping)
- [Cross-Skill Hints](#cross-skill-hints)

## When to Use

Use this skill when you need to build, implement, or ship a feature - the standard engineering loop from receiving the request to having the change ready for PR review.

Do NOT use for: debugging a failing test (use Systematic Debugging), migrating code between languages (use Code Migration and Refactoring), performance optimization (use Performance Profiling), or looking up a config (use the project's docs).

## Triggers

"implement", "build this", "create", "add a feature", "ship", "make it work", "get this done", "develop", "code this", "implement the change"

## Prerequisites

Before starting, ensure you have access to:
- The source repository (local clone or checkout)
- Project README and CONTRIBUTING.md (most have worktree/branch conventions)
- A test runner and build command
- The project's CI configuration (what gates must pass?)
- Any existing ground skills loaded: Task Decomposition, PR Review

## Methodology

### Phase 1: Understand Before Acting

Spend at least 20% of total budget time (more for complex features) on understanding before writing any code. Jumping straight to implementation is the #1 agent failure mode.

Continue reading

Sign up for a free account to view the full skill content

Login / Register
#engineering-workflow#feature-development#tdd#git-worktree#agentic-engineering#software-engineering
License: Proprietary

Related Skills

More skills in Software Engineering

Accessibility Standards

Comprehensive web accessibility standards based on WCAG 2.2 AA, with 38+ anti-patterns, legal enforcement context (EAA, ADA Title II), WAI-ARIA patterns, and framework-specific fixes for modern web frameworks and libraries.

#github-copilot#accessibilityMIT

Accord

Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision → L1 Requirements → L2 Team Detail → L3 Acceptance Criteria). No code. Use when authoring cross-team specs, building L0-L3 packages, or aligning Biz/Dev/Design on a single source of truth.

#broad-capability#developmentMIT

Acquire Codebase Knowledge

Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.

#github-copilot#documentationMIT

Acreadiness Assess

Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.

#github-copilot#planningMIT

Acreadiness Generate Instructions

Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.

#github-copilot#skillMIT

Acreadiness Policy

Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.

#github-copilot#planningMIT