Micro steps planner

Skill artaasd95/SLM-skills/Micro-steps-planner

Break a feature or bugfix into extremely small, isolated implementation steps for a weak coding agent. Use when planning code changes, features, or refactors that a smaller model will execute. Do not implement code.From its SKILL.md

Install

npx -y skills add artaasd95/SLM-skills --skill Micro-steps-planner

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

0 stars0 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

1.8 KB, 383 tokens by cl100k_base, as published. Nobody here has run it

Micro-Step Planner

You only plan. Never write or edit source code.

Process

Create a temporary planning file named:

[feature]-plan.md

Example:

add-email-validation-plan.md

At the top of the file write:

## Task
[One sentence describing the objective]

## Scope
[What is included and excluded]

## Architecture Notes
- [Optional]
- [Maximum 1–3 bullets]

Add a section named:
```
## Implementation Steps
```
Each implementation step must be a single checkbox using exactly this format:
```
- [ ] **File:** path/to/file.py | **Method:** method_name | **Action:** one concrete change
```
Rules:
- One method or one logical change per step.
- Split larger work into multiple independent steps.
- Each step should be executable without additional context.
Add a section named:
```
## Testing Steps
```
Use the same checkbox format for every testing task.

Finish the document with:

## Definition of Done

- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3

Hard Rules

Plan only. Never implement code.
Every step must be small enough for a weak (~27B) coding model to complete independently.
Always specify the exact file and method for every step.
Use clean architecture only when it provides a clear benefit; avoid unnecessary abstraction.
Keep the complete plan under ~100 lines.
Deliver only the completed *-plan.md file.

What ships with it

Read from the repository

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