agentleFS
23jmo23jmo/jmo-skills/skills/ste/SKILL.md

ste

Skill9 starsChanged 33 days agoMITView on GitHub

Explain technical ideas in clear, precise language. Use when an explanation is confusing, jargon-heavy, vague, or hard to follow, or when the user asks for Standard Technical English.

16 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 10

    Distinctive

    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 what the thing does and why it matters.

    line 12
  2. Distinctive:

    Use one main idea per sentence.

    line 13
  3. Distinctive:

    Prefer common, concrete words.

    line 14
  4. Distinctive:

    Prefer active voice and name the actor: say what component performs each action.

    line 16
  5. Distinctive:

    Put steps in the order they happen.

    line 18
  6. Distinctive:

    Use a short example when the idea is abstract.

    line 20
  7. Distinctive:

    Use lists for steps or parallel items.

    line 21
  8. Distinctive:

    Remove filler, vague intensifiers, and decorative jargon.

    line 22
  9. Distinctive:

    Do not make the explanation less accurate just to make it shorter.

    line 24
  10. Distinctive:

    Before finishing, confirm that every pronoun has a clear referent, every technical term is defined or familiar to the intended reader, and …

    line 28

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “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

Clear Technical English

Explain the subject so the reader can understand it on the first pass without losing technical accuracy.

Write the explanation

  • Start with what the thing does and why it matters.
  • Use one main idea per sentence.
  • Prefer common, concrete words. Keep a technical term when it is the correct term, then define it the first time.
  • Expand an acronym the first time you use it.
  • Prefer active voice and name the actor: say what component performs each action.
  • State cause and effect directly.
  • Put steps in the order they happen.
  • Separate confirmed behavior, assumptions, and recommendations.
  • Use a short example when the idea is abstract.
  • Use lists for steps or parallel items. Use prose when the ideas depend on one another.
  • Remove filler, vague intensifiers, and decorative jargon.

Do not make the explanation less accurate just to make it shorter. If a detail is uncertain, say what is unknown and what would verify it.

Check the result

Before finishing, confirm that every pronoun has a clear referent, every technical term is defined or familiar to the intended reader, and each step says what changes and why.

This skill follows the general goals of clear technical communication. It does not certify formal ASD-STE100 compliance.

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.