The archive · Developer & Business Tools · Product decision · 2026
SimpleEnglish bets a spec, not a prompt, cures AI slop; 3.2k stars
AminBlg's MIT agent skill makes LLMs write with ASD-STE100 aerospace discipline; created 2026-07-21, the repo showed 3.2k stars by 2026-09-04.
SimpleEnglish (AminBlg)
What the business is
SimpleEnglish is a free, MIT-licensed agent skill that makes LLMs write plain English with the discipline of ASD-STE100 Simplified Technical English, the controlled language aerospace has used since 1983: a Plain register by default (prose-only replies, five sentences max, no em-dashes, no openers or closers) plus a Strict mode that adds the STE dictionary, installable in Claude Code, Codex, Cursor, Copilot, Gemini CLI and about 25 more agents.
How it started
AminBlg created the repository on 2026-07-21 around one line: 'your AI writes like a LinkedIn post — make it write like a Boeing manual.' The skill was built against the primary ASD-STE100 Issue 9 text (January 2025), not summaries, because agents without the skill invented rule numbers. The documented rules mirror the standard's numbered constraints: chat replies are prose-only with five sentences maximum, the first sentence answers, and em-dashes, openers and closers are banned; documents cap instructions at 20 words and descriptions at 25, put the condition before the command, and forbid should, would, may and might.
What happened
The project iterated publicly from 1.3.0 to 2.0.1 across 77 commits, with every benchmark reproducible from committed raw files. A self-audit dated 2026-09-02 (WHY-USELESS) found that the earlier headline — 81.3% fewer linter violations across 144 generations — measured rule obedience rather than what a reader sees, so 2.0.1 was rebuilt on reader-visible counts: over-cap sentences, em-dashes, bold, headers and bullets pooled over 16 claude-sonnet-4-6 replies fell from 406 to 58, and document linter violations per 100 words fell from 4.09 to 0.91 (78%). A community audit (issue #4) checked the vocabulary tables against the STE dictionary, and the fix was A/B-tested before it merged.
How it ended up
No company, funding or revenue is documented in the material; as of the 2026-09-04 crawl the project is live at 3.2k stars with v2.0.1 shipping, reproducible evals, and install paths for Claude Code, Codex and other agents.
Background
SimpleEnglish is a free, MIT-licensed open-source agent skill by the GitHub author AminBlg that makes LLMs write plain English with the discipline of ASD-STE100 Simplified Technical English, the controlled language aerospace has used since 1983 so a tired mechanic cannot misread an instruction. The repository was created on 2026-07-21 and carries one-line positioning: 'your AI writes like a LinkedIn post — make it write like a Boeing manual.'
The bet is that a numbered, testable standard beats a generic style prompt. The README's FAQ makes the case directly: 'Clearly' is an opinion, while 'no sentence over 20 words' is a spec, and agents follow specs; a 40-year-old aerospace standard is maintained (Issue 9, January 2025), numbered, and a near-perfect negative of every AI writing tell. Replies are constrained to five sentences of prose with no em-dashes or openers, and documents follow STE's word caps, condition-first order and simple tenses, with a Strict mode adding the dictionary when compliance is named.
Traction ran on evidence rather than press: by the 2026-09-04 crawl the repo showed 3.2k stars (3,177 in metadata), 112 forks and 77 commits about six weeks after creation. A 2026-09-02 benchmark measured 86% fewer visible defects (406 to 58) across 16 claude-sonnet-4-6 replies, a blind judge preferred v2.0.1 over v2.0.0 in 14 of 16 pairs, and an internal audit found the earlier linter-based metric had hidden the slop readers actually saw, so 2.0.1 was rebuilt around reader-visible counts.
No company, funding or revenue appears in the material. As of the crawl the project is a live solo open-source bet in the agent-skills wave: it installs through the Agent Skills standard into Claude Code, Cursor, Copilot, Codex, Gemini CLI and roughly 25 other agents, with every number reproducible from committed raw files.
What has to be true
- Concrete traction: created 2026-07-21, the repo showed 3.2k stars (3,177 in crawl metadata), 112 forks and 77 commits at the 2026-09-04 crawl.
- The bet is explicit and falsifiable: a numbered standard (ASD-STE100) should beat 'write clearly', and the README states why — 'Clearly' is an opinion, a word cap is a spec, and agents follow specs.
- The project audits itself: an internal WHY-USELESS review found the old 81.3% linter metric measured rule obedience, not reader experience, and v2.0.1 was rebuilt on reader-visible defect counts.
- Reproducible evidence: every benchmark ships committed raw files and scoring scripts, and community audit #4 checked the vocabulary tables against the STE dictionary before its fix merged.
What can be applied
If 'write clearly' fails, encode the standard: agents follow numbered specs, and the metric that counts is what a reader sees, not a rule-obedience score.
Aftermath
As of 2026-09-05 the repository is live at 3.2k stars (3,177 in crawl metadata), 112 forks and 77 commits, with v2.0.1 shipping. The README documents two registers — Plain (default) and Strict — installable via the skills CLI, as a Claude Code plugin with an output style, or as a Codex plugin with session hooks, or as a paste-in system prompt. Benchmarks dated 2026-09-02 and the WHY-USELESS self-audit are committed to the repo. No company, funding or revenue appears in the material, so SimpleEnglish remains a solo open-source bet whose commercial outcome is not documented.
Sources
spotted an error? The archive wants to know.
Your turn
You just read one. Describe what you are building, and see who is betting on the same thing.
Free account · 3 free questions · no card