agentleFS
Sign inStart free
t1mericksont1merickson/skills/explaining-problems/SKILL.md

explaining-problems

Skill1 starsChanged 2 months agoMITView on GitHub

Structure a causal explanation when the user asks to understand a mechanism, root cause, postmortem, surprising deployment result, or consequential design rationale beyond a short answer. Do not use merely because a task contains an error, diagnosis, design choice, or deployment step; ordinary implementation and status answers should stay direct.

The file

Create a free account to mount
Files
SKILL.md

explaining-problems

Write for a smart reader who knows nothing about this system. Give the verdict in one plain sentence first. Then start at the beginning, define each term before using it, and explain only the commands, files, services, or workflows needed to understand the verdict. Short sentences. Active voice.

Problem reports walk this order. The normal world first:

  1. What the named thing is.
  2. Where it exists.
  3. Who uses it, and why.
  4. Whether it runs automatically or manually.
  5. What should normally happen.

Then the break:

  1. What is wrong.
  2. The exact conditions that cause it.
  3. A numbered example using real objects from this system.
  4. The result the user would actually see.
  5. How likely this path is in practice.
  6. The smallest permanent fix.
  7. One focused check to run after the fix.

This is an order to walk, NOT a form to fill. Skip a step that doesn't apply. Say nothing rather than pad. And it's only for explanations that earn the depth: a bug worth understanding, a design decision, a deployment surprise. A one line answer to a one line question stays one line.

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.

Check your setup, free