writing-plans

Writing Implementation Plans

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "writing-plans" with this command: npx skills add starwards/starwards/starwards-starwards-writing-plans

Writing Implementation Plans

Overview

Use when design is complete and you need detailed implementation tasks for engineers with minimal codebase familiarity. Creates comprehensive guides with exact file paths, code examples, and verification steps.

Key Characteristics

Task Granularity: Each step represents 2-5 minutes of work, breaking down features into atomic actions like writing failing tests, implementing solutions, and committing changes.

Documentation Standard: Plans follow a mandatory header format including goal, architecture, and tech stack, followed by numbered tasks with file locations, code snippets, and exact command sequences.

Plan Structure

Feature Name

Goal

[One sentence: what this accomplishes]

Architecture

[How this fits in the system]

Tech Stack

  • [Libraries/frameworks used]

Tasks

1. [Task name]

File: path/to/file.ts

[What to do]

Code:

[Exact code or snippet]

Verify:

[Commands to run]

Commit: [commit message]

2. [Next task...]

## Core Principles

- **DRY** - Don't Repeat Yourself
- **YAGNI** - You Aren't Gonna Need It
- **TDD** - Test-Driven Development
- **Frequent commits** - One task, one commit

## Execution Workflow

After completion, offer two implementation paths:

1. **Subagent-Driven** — Dispatch fresh agents per task with reviews within the current session
2. **Parallel Session** — Guide toward separate sessions using the executing-plans skill

## When to Use

- Design phase is complete
- Need step-by-step implementation guide
- Working with engineers unfamiliar with codebase
- Breaking down complex features
- Ensuring consistent implementation approach

## What to Include

- Exact file paths (no vague locations)
- Complete code snippets (not pseudocode)
- Verification commands
- Expected outputs
- Commit messages for each step
- Dependencies between tasks
- Edge cases to handle

## Output Location

Save to: `docs/plans/YYYY-MM-DD-<feature-name>.md`

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

writing-plans

No summary provided by upstream source.

Repository SourceNeeds Review
General

writing plans

No summary provided by upstream source.

Repository SourceNeeds Review
General

starwards-pixijs

No summary provided by upstream source.

Repository SourceNeeds Review
General

writing-plans

No summary provided by upstream source.

Repository SourceNeeds Review