agentleFS
youmissedaspotyoumissedaspot/ymas-agent-workflows/skills/like-im-5/SKILL.md

like-im-5

Skill1 starsChanged 46 days agoMITView on GitHub

Explain technical, architectural, domain or project concepts in clear adult language for a competent reader unfamiliar with the subject. Use for explanation requests, including like-im-5; inspect relevant repository evidence when available. Explanation alone does not authorize implementation, adoption or documentation migration.

1 other project uses a version of this.

Adopted by

Most recently taken up by

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:

    Start with the underlying idea and why it exists.

    line 12
  2. Distinctive:

    When the question concerns a repository, read its instructions and index, then the smallest relevant specifications, accepted decisions, …

    line 25

≈ “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

Like I'm 5

Explain as one competent adult speaking to another who does not know this subject. The informal name is not an instruction to use childish language or talk down to the reader. Apply human explanation and editorial judgment.

Start with the underlying idea and why it exists. Use plain English and normal adult vocabulary. Remove unnecessary jargon; define terms needed to preserve an important distinction. Use concrete examples and explain the important consequence of getting the concept wrong. Short analogies or anecdotes are optional aids, not a substitute for the actual mechanism. Stay concise unless understanding requires more depth; adapt the form to the question instead of imposing a report template.

For example, buying equipment may require removing payment, transferring ownership and recording the accounting entry. A transaction makes those changes behave as one operation: either all succeed or none do. Otherwise a buyer could lose the payment without receiving the equipment. The formal term for this all-or-nothing behavior is atomicity. Do not imply that atomicity alone also establishes concurrency isolation or every other database guarantee.

When the question concerns a repository, read its instructions and index, then the smallest relevant specifications, accepted decisions, implementation and tests. Inspect history when it explains a material design choice. Use existing system/Feature Maps for navigation, checking their provenance and original sources. Explain this project's actual model where evidence establishes it. Distinguish accepted requirements from what code currently does, and established facts from inference or uncertainty. If sources conflict, explain the conflict and its consequence under the repository's authority. If behavior is missing or unverified, say so; generic examples cannot fill that gap.

Cite specifications, code, decisions, tests or history where a reference materially improves trust or traceability. Explain naturally before asking the reader to decode technical detail. Preserve consistent domain terms and meaningful qualifications.

Return the explanation in conversation by default. Do not change files, settle missing product rules or begin implementation merely to explain them. A separately requested write or development action follows the repository's relevant workflow and authorization.

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.