Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →florianbruniaux/voice-refine
Transform verbose voice input into structured, token-efficient Claude prompts.
Passed 22 of 23 test cases with the skill, and 6 of 23 without it.
and 22 more in the full report
16 fixed6 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
Here is a voice transcript in French: 'Alors euh en fait on a un bug sur la recherche Algolia dans l'application Vue 3, quand on tape plus de trois caractères ça freeze.' Transform this voice transcript with the `--en` flag applied.
| Checked | Without skill | With skill |
|---|---|---|
| Outputs section titles and body content in English. | Missed | Passed |
| Filters out French filler phrases like 'Alors euh'. | Missed | Passed |
The instructions your model reads when the skill loads.
Transform verbose, stream-of-consciousness voice dictation into structured, token-efficient prompts for Claude Code.
1. DEDUPE → Remove repetitions and filler words
2. EXTRACT → Identify core requirements and constraints
3. STRUCTURE → Organize into standard sections
4. COMPRESS → Reduce to ~30% of original while preserving intent
## Contexte
[Project context, existing stack, relevant files]
## Objectif
[Single sentence: what needs to be built/changed]
## Contraintes
- [Constraint 1]
- [Constraint 2]
- [etc.]
## Output attendu
[Expected deliverables: files, format, tests]
test cases passed, vs 6 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.