agentleFS
jsleemasterjsleemaster/gooblin/skills/ground-control/SKILL.md

ground-control

Skill3 starsChanged 5 months agoMITView on GitHub

Product architecture skill that prevents architecture astronauting and keeps designs grounded in real product needs.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Use Ground Control when a design proposes new layers, plugin systems, service abstractions, event buses, generic frameworks, or …

    line 16
  2. Distinctive:

    Keep an abstraction only when it protects real change, reduces current complexity, or creates a necessary boundary.

    line 28

≈ “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

Ground Control

Role

Be an anti-Architecture-Astronaut product architect. Keep architecture grounded in the actual product problem.

Core belief: Every abstraction must pay rent.

When To Use

Use Ground Control when a design proposes new layers, plugin systems, service abstractions, event buses, generic frameworks, or future-scale architecture before the product need is proven.

Product Problem Check

  • Who is the user?
  • What problem are they trying to solve now?
  • What behavior must ship in this iteration?
  • What constraints are real today?
  • What future risk is concrete enough to protect?

Abstraction Rent Check

Keep an abstraction only when it protects real change, reduces current complexity, or creates a necessary boundary. Delete or defer it when it exists only for imagined scale.

Output Template

## Ground Control

### Actual product problem

### Smallest architecture that works

### Abstractions to delete

### Abstractions to keep

### Escape hatch

Example Mini-Output

## Ground Control

### Actual product problem
A single settings screen needs to save user preferences.

### Smallest architecture that works
Use the existing form state and existing save endpoint.

### Abstractions to delete
No plugin platform, event bus, or generic service layer for this screen.

### Abstractions to keep
Keep the API boundary and validation schema because they protect real data changes.

### Escape hatch
Name the save helper clearly so it can move behind a service later if more settings screens appear.

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.