agentleFS
Sign inStart free
beingDurgeshbeingDurgesh/asd-ste100-simplified-technical-english-agent-skill/CLAUDE.md

asd-ste100-simplified-technical-english-agent-skill

CLAUDE.md4 starsChanged 21 days agoMITView on GitHub

This file gives Claude Code the STE100 skill on demand. The skill lives in skills/ste100/SKILL.md. It is a front-matter skill that works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and Antigravity CLI. Load it when the user asks to: - Write or rewrite text in ASD-STE100 Simplified Technical English - Disambiguate text, or rewrite so an agent cannot misread it - Remove jargon, slop, or AI writing from docs, prompts, or replies - Write or check error messages, runbooks,…

We split this CLAUDE.md into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Write or rewrite text in ASD-STE100 Simplified Technical English

    line 12
  2. Distinctive:

    Remove jargon, slop, or AI writing from docs, prompts, or replies

    line 14
  3. Distinctive:

    Write or check error messages, runbooks, incident reports, release notes, commit messages, agent prompts, or UI copy

    line 15
  4. Distinctive:

    Use any of these trigger phrases: "STE", "Simplified Technical English", "plain English", "layman terms", "explain it simply", "no jargon", …

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md 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
CLAUDE.md

CLAUDE.md — ASD-STE100 Skill

This file gives Claude Code the STE100 skill on demand.

Skill

The skill lives in skills/ste100/SKILL.md. It is a front-matter skill that works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and Antigravity CLI.

Load it when the user asks to:

  • Write or rewrite text in ASD-STE100 Simplified Technical English
  • Disambiguate text, or rewrite so an agent cannot misread it
  • Remove jargon, slop, or AI writing from docs, prompts, or replies
  • Write or check error messages, runbooks, incident reports, release notes, commit messages, agent prompts, or UI copy
  • Use any of these trigger phrases: "STE", "Simplified Technical English", "plain English", "layman terms", "explain it simply", "no jargon", "de-slop", "make this readable", "write for non-native readers", "disambiguate this", "controlled-language rewrite"

Default mode

Plain (structural rules only). The skill itself explains the difference between Plain and Strict.

Linter

The repo ships a linter at skills/ste100/scripts/ste-lint.py that checks text against the 53 rules. Run it with:

python3 skills/ste100/scripts/ste-lint.py --selftest
python3 skills/ste100/scripts/ste-lint.py path/to/file.md
python3 skills/ste100/scripts/ste-lint.py --json --baseline 5 file.md

The eval harness at skills/ste100/evals/ste_lint.py walks a directory and lints every .md and .txt file:

python3 skills/ste100/evals/ste_lint.py examples --baseline 5

Dictionary toolchain

The official ASD dictionary is copyrighted and not redistributed. To build the dictionary-backed checker from your own free PDF copy:

pdftotext -layout -enc UTF-8 your_ste100.pdf ste.txt
python3 tools/ste-dictionary/parse_dict.py ste.txt
python3 tools/ste-dictionary/emit.py
python3 tools/ste-dictionary/ste_dict_lint.py --self-test

This produces tools/ste-dictionary/not-approved.tsv, which ste_dict_lint.py uses to flag non-approved words with their approved alternatives.

Tests

python3 -m pytest tests/test_linters.py -q

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