agentleFS
artaasd95artaasd95/SLM-skills/Micro-steps-planner/SKILL.md

microstep-planner

Skill0 starsChanged 4 months agoMITView on GitHub

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.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a temporary planning file named:

    line 13
  2. Distinctive:

    Add a section named:

    line 39
  3. Distinctive:

    Use the same checkbox format for every testing task.

    line 63
  4. Distinctive:

    Every step must be small enough for a weak (~27B) coding model to complete independently.

    line 78
  5. Distinctive:

    Always specify the exact file and method for every step.

    line 79
  6. Distinctive:

    Use clean architecture only when it provides a clear benefit.

    line 80
  7. Distinctive:

    Keep the complete plan under ~100 lines.

    line 81

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Micro-Step Planner

You only plan. Never write or edit source code.

Process

  1. Create a temporary planning file named:

    [feature]-plan.md

    Example:

    add-email-validation-plan.md
  2. 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]
  3. 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.
  4. Add a section named:

    ## Testing Steps

    Use the same checkbox format for every testing task.

  5. 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.