#169169th of 389 in Skills, plugins and prompts
simpleenglish
Agent skill that makes LLMs write plain English following ASD-STE100 rules
- Stars
- 4.4k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Python
18 on 21 Jul 20264,369 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
An Agent Skills (SKILL.md) package that instructs coding agents to write short, prose-only replies and documents under rules drawn from ASD-STE100 Simplified Technical English, such as 20-word instruction limits, no em-dashes and no hedging verbs. It has a Plain mode by default and a Strict mode that adds STE vocabulary discipline. It also ships a Claude Code plugin with a session hook and output style, a Codex plugin, and a paste-in system prompt.
Who it is for: Teams who want coding agents to write clear docs and replies
Strengths
- Works in any agent that reads the Agent Skills standard; one folder, no dependencies
- Benchmark numbers are committed as raw files and rechecked by a CI script
- Fallback system-prompt block for tools without skill support, with a 60-token version
- Plain and Strict modes; the reply stays Plain in every mode
Weaknesses
- Reply-defect figure (218 to 11) is from 2.0.1; no run exists for 2.1.0 or later
- Judges are Claude models on Claude text, so family bias is possible
- Skills CLI install omits the session hook and output style; the plugin is needed for those
- Not STE-certified, and no dictionary content ships; Strict needs your own copy of the ASD PDF
What it needs
- no GPU
- Needs Node.js (for the Claude Code and Codex hooks)
- Models: Claude, OpenAI GPT-4.1-mini, Agent Skills compatible agents (Claude Code, Cursor, VS Code Copilot, Codex, Gemini CLI, Goose, OpenCode)
Quick answers
Is simpleenglish open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 389| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |