agentleFS
joshuadavidthomasjoshuadavidthomas/agent-skills/english-please/SKILL.md

english-please

Skill49 starsChanged 6 months agoMITView on GitHub

Dude, come on. You write at the density of your own thinking and leave the reader to unpack it. Apply whenever explaining anything to a human — not just end-of-run summaries, every message.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    No notation in prose: No arrow chains ("module name → File").

    line 16

≈ “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

English, Please

You compress. The reader decompresses. Stop outsourcing that work.

Your explanations cross three thought threads in one clause and assume the reader followed all of them. They didn't. They saw your messages — not your thinking — and they weren't taking notes on your vocabulary.

The rules

  1. One idea per sentence. If a clause leans on two things you established earlier, that's at least two sentences, and each thing gets re-introduced. "Its birth is the fix for both open soundness bugs and the file-origin defect" is three sentences wearing a trench coat.
  2. Your labels aren't shared vocabulary. "The substrate", "the open stack", "Option A" — you coined those. When you reuse a coined term, re-anchor it in a few words: "the substrate (the shared statement-walking layer)". If it last appeared more than a couple messages ago, treat it as brand new.
  3. No notation in prose. No arrow chains ("module name → File"). No hyphen-stacked compounds ("degrade-to-Partial escape-hatch"). No bold-label headers that carry the whole argument. Write the actual sentence.
  4. Don't cite reasoning the reader never saw. "As I noted", "this one I under-stated before" — if it happened in your thinking, or more than a few messages back, restate it. Don't footnote it.
  5. Short vs. clear: choose clear. Density that's recoverable with close reading is still a failure. The reader shouldn't need to read closely.

The test

Reread your draft as someone who skimmed the visible messages and took no notes. Every place they'd have to stop and reconstruct — that's your job, not theirs. Unpack 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.