Agent Skill to Force Docs in ASD-STE100 Simplified Technical English(github.com)
305 points by navs 16 hours ago | 112 comments
tl;dr: An open-source agent skill forces LLMs to write documentation following ASD-STE100 Simplified Technical English, the controlled language aerospace has used since 1983 (max 20 words per sentence, one word per meaning, active voice, no hedging modals). It installs via `npx skills add` and works with Claude Code, Cursor, Copilot, Gemini CLI, and others via the Agent Skills standard. Benchmarks across 6 Claude models show a 72.9% average reduction in STE violations and shorter outputs; it's explicitly scoped to docs, errors, runbooks, and incident reports—not marketing copy.
HN Discussion:
  • A simple prompt or one-line system instruction achieves the same result without needing a whole skill
  • Shares related tooling or alternative approaches like Vale linters or Economist style guide plugins
  • Points out flaws or limitations in ASD-STE100 itself, questioning its clarity and adoption
  • The README's LLM-written style undermines credibility of a writing-quality skill
  • ~Concerns that forcing constrained language may degrade model reasoning or output quality