01
It starts by itself
agent-facing text changes. Runs in GitHub Actions or Claude Code routine.
- ↻ agent-facing text changes
pull request touches prompts, tool descriptions or error strings
Clear messages every time your text changes.
Install the ASD-STE100 skill and make it a habit: follow https://gethabit.dev/skills/danyuchn/asd-ste100.md
7K installs5K starsMIT licenceSource on GitHub ↗

ASD-STE100
by danyuchn · 7K installs
The skill
Rewrites text in short, clear, simple English.
Only when you ask.
Fewer mix-ups
Clear messages every time your text changes. Fewer mix-ups for readers and agents.
↻ Runs by itselfevery time your text changes
When does it start? How does it check its work? What does it remember?
Stops after 20 files or 2 rewrite retries per run.
Your agent picks Strict for procedures and errors, STE-flavored for READMEs and changelogs.
It reads the text once before changing anything.
It runs scripts/ste-lint.py with --json on the changed files.
It fixes each flagged sentence and keeps hedges, numbers and safety conditions.
It adds a Kept as-is line where precision needs a longer phrase.
It runs the linter again and records the new count.
It writes only in its own folder and asks you before anything goes out.
Read both lists. If the left one sounds like you, the ASD-STE100 skill helps.
No. It applies the structural rules fully and treats word choice as advice.
No. Hedges are content, and the linter never flags them.
Copy the prompt at the top into your agent. It installs the skill from danyuchn/asd-ste100-skill and sets up the habit. Or run npx skills add danyuchn/asd-ste100-skill --skill asd-ste100.
Yes. It is published under MIT. Habit is free too.
Install the ASD-STE100 skill and make it a habit: follow https://gethabit.dev/skills/danyuchn/asd-ste100.md
All danyuchn skills →More docs skills →
Works in
Made by danyuchn, published under MIT. Habit links to the original and never changes it. Is this your skill?