Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →athola/voice-learn
Improves a voice profile by learning from manual edits. Use after editing generated text to refine registers and close voice drift over time.
Passed 15 of 20 test cases with the skill, and 5 of 20 without it.
and 11 more in the full report
11 fixed6 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
When analyzing user edits during style learning, which two stages should be compared to isolate user preferences from automated AI advisory recommendations?
| Checked | Without skill | With skill |
|---|---|---|
| Compares post-review (stage 2) against post-edit (stage 3). | Missed | Passed |
The instructions your model reads when the skill loads.
Learn from user edits to improve the voice profile over time.
scribe:voice-extract)scribe:voice-review)Every piece flows through three stages:
The learning agent compares stages 2 and 3 (post-review vs post-edit) to identify patterns in what the user changed. These patterns inform register and rule updates.
voice-learn:snapshots-loaded - All three stages readtest cases passed, vs 5 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.