agentleFS
Sign inStart free
weselbenweselben/RooForge/skills/ste100/SKILL.md

ste100

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Write human-facing text in ASD-STE100 Simplified Technical English — short sentences, approved words, one meaning per word. Governs PR bodies, docs, and issue/PR comments; chat replies and commit messages are not in scope (caveman-commit owns commits).

10 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

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All text that faces other humans — PR bodies, issue comments, docs — goes out in STE100.

    line 9
  2. Distinctive:

    Prefer the short approved word: "use" not "utilize", "show" not "demonstrate".

    line 24
  3. Distinctive:

    Every thing gets one technical name, used consistently.

    line 26
  4. Distinctive:

    No contractions. No idioms.

    line 27

“Common” is measured: kept by at least 6 in 10 of the 10 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

STE100

All text that faces other humans — PR bodies, issue comments, docs — goes out in STE100. Commit messages are the exception: caveman-commit owns those. Short, direct, unambiguous. The reader is busy; the text does the work, not the reader.

Leading word: terse. STE100 prose is terse by construction: short sentences, one meaning per word, no filler.

Core rules

Sentences:

  • One topic per sentence. One instruction per sentence.
  • Max 20 words per instruction, 25 per description.
  • Max 6 sentences per paragraph.
  • Imperative mood: "Restart the server", not "The server should be restarted".
  • Active voice. The actor is in the sentence.

Words:

  • One word for one meaning, everywhere. "check" on line one is never "test" on line ten.
  • Prefer the short approved word: "use" not "utilize", "show" not "demonstrate".
  • Verbs as verbs, nouns as nouns. No noun-verb drift.
  • Every thing gets one technical name, used consistently. First use may define it.
  • No contractions. No idioms. No phrasal ambiguity.

Tense and mood:

  • Present tense for what is true. Past tense for what is done. Future tense only when the event is truly later.
  • "must" = obligation, "can" = capability, "should" = recommendation.

Examples

  • ❌ "In this PR we've implemented a brand new caching layer in order to facilitate improved performance across the board"
  • ✅ "This PR adds a cache layer. It decreases the response time of the API."
  • ❌ "You might want to consider updating your dependencies, as there could potentially be vulnerabilities"
  • ✅ "Update the dependencies. Two have known vulnerabilities."
  • ❌ "This PR description was written to explain the changes made to the authentication module"
  • ✅ "fix(auth): accept tokens with trailing whitespace"

Extended rules

For the full writing-rule digest — approved verb list, word-count limits per text type, punctuation, warnings and notes format — read RULES.md. Load it when the text is long-form (docs, reports) or when a sentence resists the core rules.

Boundaries

STE100 shapes the prose the agent produces. It does not strip required format (commit type prefixes, PR headings, AI-attribution trailers) and does not censor facts. If the user asks for a different tone ("formal", "marketing"), the user wins for that text.

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