Write plan

Skill S3YED/appie-kit/skills/meta/write-plan

MUST use after brainstorming and before executing. Creates detailed implementation plans with checkpoints, verification criteria, and execution options.From its SKILL.md

Install

npx -y skills add S3YED/appie-kit --skill write-plan

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 426 tokens by cl100k_base, as published. Nobody here has run it

Write Plan

Overview

Transform validated designs into detailed, actionable implementation plans with checkpoints.

Every plan includes:

Bite-sized tasks (2-5 minutes each)
Checkpoints with verification criteria
Estimated time for each section
Execution options at the end

Plan Structure

# [Project Name] - Implementation Plan

**Goal:** One sentence describing success
**Approach:** Brief summary of the chosen approach
**Estimated Total Time:** X minutes

## Checkpoint 1: [Milestone Name]
- [ ] Task 1: [Description] (~X min)
  - **Action:** [Specific action]
  - **Verify:** [How to confirm done]
- [ ] Task 2: [Description] (~X min)
  ...

## Checkpoint 2: [Milestone Name]
...

## Verification Criteria
- [ ] All checkpoints complete
- [ ] Quality standards met
- [ ] User approval obtained

Task Granularity

Small: 2-5 minutes of work
Specific: Clear what "done" means
Verifiable: Can confirm completion
Independent: Doesn't block on other tasks in same checkpoint

Execution Handoff

After saving the plan, offer execution choice:

"Plan complete and saved to memory/plans/<filename>.md. Two execution options:

1. Single-Agent (this session) - I execute tasks sequentially, review at each checkpoint

2. Dispatch Multiple Agents (parallel) - Spawn subagents for independent tasks

Which approach?"

If Single-Agent chosen:

Stay in this session
Execute tasks sequentially
Report progress at each checkpoint

If Dispatch Multiple Agents chosen:

Use dispatch-multiple-agents skill
Spawn subagents for parallel work
Integrate results

Integration with Other Skills

After brainstorming → Use write-plan
Before doing-tasks → Plan must exist
With dispatch-multiple-agents → For parallel execution

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.