agentleFS
michele-orsini-71michele-orsini-71/claude-skills/repeat-it-as-im-5/SKILL.md

repeat-it-as-im-5

Skill0 starsChanged 6 months agoMITView on GitHub

Repeat your last response in the simplest possible English, then keep replies short for the rest of the session. Strip metaphors, idioms, and vivid language; use the most common words; write one short sentence per idea; cut anything that adds no information; stop pre-explaining and listing unasked options. Use when the developer invokes /repeat-it-as-im-5, or says "say that simpler", "explain it like I'm 5", "plain English version", "too complicated, simplify it", "short answers", or asks you to repeat your last answer in simpler words or to keep answers brief.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Be brief. Cut anything that adds no information: Remove filler, hedges, and repeated points.

    line 18
  2. Distinctive:

    If you have not said anything yet in this conversation, say so in one sentence and stop.

    line 24
  3. Distinctive:

    Keep the same meaning and the same facts.

    line 25
  4. Distinctive:

    Keep needed structure. If the original was a list of steps, the rewrite stays a list of steps, with each step in plain short sentences.

    line 26
  5. Distinctive:

    Keep code blocks as they are.

    line 27

≈ “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

Take your previous response and write it again, simpler. Output only the rewritten version. Do not add a preface, an apology, or a note about what you changed.

The rules

Apply all four to the rewrite:

  1. No metaphors, no idioms, no vivid language. Say the plain fact. If a phrase only works as a picture in the reader's head, replace it with the literal meaning. "Low-hanging fruit" becomes "the easiest one". "Under the hood" becomes "inside".
  2. Use the most common English words. Write like a textbook for a beginner, not a blog post. Pick the short, common word over the long, rare one. "Use" not "utilize". "Start" not "commence". "Show" not "demonstrate". Expand or drop jargon; if a technical term is needed, define it in one short sentence.
  3. One idea per sentence. Short sentences. Break long sentences apart. Each sentence says one thing. Avoid clauses joined by "which", "while", or semicolons. If a sentence has two ideas, make it two sentences.
  4. Be brief. Cut anything that adds no information. Remove filler, hedges, and repeated points. Remove words like "basically", "essentially", "in order to", "it is worth noting that". If the rewrite is shorter than the original and says the same thing, that is correct.

What to repeat

Rewrite your own most recent response — the last thing you said before this skill was invoked.

  • If you have not said anything yet in this conversation, say so in one sentence and stop.
  • Keep the same meaning and the same facts. Do not add new claims. Do not drop a fact just to be shorter; drop only words that carry no information.
  • Keep needed structure. If the original was a list of steps, the rewrite stays a list of steps, with each step in plain short sentences.
  • Keep code blocks as they are. The rules apply to the prose, not to code.

Scope

This skill does two things:

  1. Rewrite the last response using the four rules above (skip if you have not said anything yet).
  2. Turn on short-answer mode for the rest of the session. After the rewrite, keep every reply short by default. Give the answer in as few sentences as it takes. Do not pre-explain, do not list options you were not asked for, do not add background. The four rules still apply to every reply.

Short-answer mode stays on until the developer turns it off (for example "normal mode", "you can be verbose again", or "stop short answers"). The developer will ask for more detail when they want it.

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.