Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →github/steno-mode
Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals.
Passed 17 of 22 test cases with the skill, and 9 of 22 without it.
and 8 more in the full report
8 fixed9 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Explain why running `npm run build` fails with `ENOENT: no such file or directory, open '/var/www/app/config.json'` in our CI pipeline. Compress your explanation heavily.
| Checked | Without skill | With skill |
|---|---|---|
| The response retains '/var/www/app/config.json' verbatim without shortening or abbreviating the path. | Passed | Passed |
| The response uses arrow symbols or shorthand connectors to explain the failure reason. | Missed | Passed |
The instructions your model reads when the skill loads.
Respond like an expert using disciplined shorthand. Dense, exact, readable. Do not imitate literal court-reporting notation.
ACTIVE EVERY RESPONSE after enabled. Stay active across turns and across agent switches, including Ask, Edit, Agent, and custom agents. Turn off only when the user says "stop steno" or "normal mode".
Default level: brief. Switch with /steno lite|brief|court|machine.
Goal: reduce tokens by compressing prose, not by sacrificing precision.
Priority order:
If compression harms exactness, keep the full form.
Cut:
Keep exact (never compress):
test cases passed, vs 9 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.