writing-plans

Convert approved specs into detailed execution plans with atomic tasks.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/ArcadeAI/dexa --skill writing-plans-arcadeai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/ArcadeAI/dexa/tree/main/.claude/skills/safeword-writing-plans
Command: npx skills add https://github.com/ArcadeAI/dexa --skill writing-plans-arcadeai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts specs into detailed, execution-ready plans for LLM agents, with exact file paths, complete code, and verification steps.

Core Features & Use Cases

  • Atomic Tasks: Break specs into small, verifiable tasks.
  • Exact Paths & Code: Provide precise file paths and complete code.
  • Verification Gates: Clear commands and expected outcomes for each task.

Quick Start

Read the approved spec, decompose into tasks, and produce a plan file with tasks listed in order. Prepare exact commands to verify each task.

Frequently Asked Questions about writing-plans

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

FAQPage Schema
How do I convert a software spec into an executable plan for development?

Convert specs into detailed execution plans by decomposing them into atomic tasks with exact file paths, complete code snippets, and verification commands. Each task specifies a single verifiable action, its input files, output, and the command to confirm it succeeded.

What's the best way to break down a spec into tasks for an LLM agent?

Decompose specs into atomic, granular tasks ordered sequentially. Each task maps to exact file paths and includes complete code, test steps, and verification gates. This structure ensures agents execute precisely without ambiguity.

How do I ensure every task in my execution plan is verifiable?

Attach clear verification commands and expected outcomes to each task. Verification gates confirm the task completed correctly before the agent proceeds to the next step, enforcing test-driven delivery across implementation and testing.

Can I use execution plans for both implementation and testing tasks?

Yes. Execution plans cover the full workflow: test definition, implementation, and verification. Each phase decomposes into atomic tasks with exact paths and commands, maintaining consistency across the entire delivery cycle.

What should I include in an execution plan to avoid ambiguity?

Include exact file paths, complete code for each task, atomic task granularity, step-by-step instructions, and verification commands with expected outcomes. This prevents agents from guessing and ensures reproducible execution.