dx-swe-writing-plans

Generates detailed task-by-task implementation plans with TDD steps from feature specifications.

3|5|Updated Jan 21, 2025
One-click install
npx skills add https://github.com/DEEPX-AI/dx_stream --skill dx-swe-writing-plans-deepx-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dx-swe-writing-plans
Source: https://github.com/DEEPX-AI/dx_stream/tree/main/.deepx/skills/dx-swe-writing-plans
Command: npx skills add https://github.com/DEEPX-AI/dx_stream --skill dx-swe-writing-plans-deepx-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a feature spec into working code often fails because engineers lack context on the codebase, file structure, and testing approach. This Skill converts a spec or requirements document into a complete, bite-sized implementation plan that an engineer with zero project context can execute task by task. ## Core Features & Use Cases - Bite-Sized Task Decomposition: Breaks work into 2-5 minute steps following TDD: write failing test, verify failure, implement, verify pass, commit. - No-Placeholder Enforcement: Requires exact file paths, complete code blocks, exact commands with expected output, and forbids vague steps like "add error handling". - Self-Review & Handoff: Runs a spec-coverage, placeholder, and type-consistency review, then offers subagent-driven or inline execution of the plan. - Use Case: Given a spec for a new GStreamer pipeline element, produce a plan saved to docs/superpowers/plans/ with every file to create or modify, full test code, and commit commands. ## Quick Start Use the writing-plans skill to turn this feature spec into a step-by-step TDD implementation plan.

Frequently Asked Questions about dx-swe-writing-plans

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write an implementation plan from a feature spec?▼

Start from the spec, map out which files will be created or modified, then decompose the work into tasks of 2-5 minute steps. Each task follows TDD: write a failing test, verify it fails, implement minimal code, verify it passes, and commit.

What makes a good task breakdown for AI-driven coding?▼

Good tasks have exact file paths, complete code in every step, exact commands with expected output, and no placeholders like TODO or "add error handling". Each task should produce self-contained, independently testable changes.

When should a spec be split into multiple implementation plans?▼

Split when the spec covers multiple independent subsystems. Each plan should produce working, testable software on its own, so one plan per subsystem keeps scope manageable and reviewable.

How are completed plans executed after writing?▼

After saving the plan, you choose subagent-driven execution, which dispatches a fresh subagent per task with review between tasks, or inline execution, which runs tasks in batches with checkpoints in the current session.

What are common mistakes in implementation plans?▼

Common failures include placeholder steps without code, inconsistent type or method names across tasks, missing spec requirements, and steps that describe what to do without showing how. A self-review pass catches these before execution.