voice-refine
Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.
Best use case
voice-refine is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.
Teams using voice-refine should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/voice-refine/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How voice-refine Compares
| Feature / Agent | voice-refine | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# Voice Refine Skill
Transform verbose, stream-of-consciousness voice dictation into structured,
token-efficient prompts for Claude Code.
## When to Use
- Input from voice dictation (Wispr Flow, Superwhisper, macOS Dictation)
- Verbose text >150 words
- Contains filler words, repetitions, or tangents
- Natural speech patterns that need structure
## Transformation Pipeline
```
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
```
## Output Format
```markdown
## 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]
```
## Flags
| Flag | Effect |
|------|--------|
| `--confirm` | Show refined prompt before sending to Claude (default) |
| `--direct` | Send refined prompt directly without confirmation |
| `--verbose` | Keep more detail, less compression |
| `--en` | Output in English (default: matches input language) |
## Usage Examples
### Basic Usage
```
/voice-refine
Alors euh j'aimerais que tu m'aides à faire un truc, en fait j'ai une API
qui renvoie des données utilisateurs et je voudrais les afficher dans un
tableau React, mais attention il faut que ça soit paginé parce que y'a
beaucoup de données, genre des milliers d'utilisateurs, et aussi faudrait
pouvoir trier par nom ou par date d'inscription, ah et on utilise Tailwind
dans le projet donc faut que ça matche avec ça...
```
### With Flags
```
/voice-refine --direct --en
[voice input in any language → sends English prompt directly]
```
## Compression Metrics
| Metric | Target |
|--------|--------|
| Token reduction | 60-70% |
| Information retention | >95% |
| Structure clarity | High |
## Filtering Rules
**Remove**: filler words ("euh", "um", "like", "basically"), repetitions, tangents, hedging ("maybe", "probably" unless relevant), politeness padding ("please", "could you").
**Preserve**: technical requirements, constraints, existing code context, expected output format, edge cases, business logic rules.
## See Also
- `guide/ai-ecosystem.md` - Voice-to-Text Tools section
- `examples/before-after.md` - Full transformation examplesRelated Skills
talk-stage6-revision
Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.
talk-stage5-script
Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.
talk-stage4-position
Generates 3-4 strategic talk angles with strength/weakness analysis, title options, CFP descriptions, and a peer feedback draft, then enforces a mandatory CHECKPOINT for user confirmation before scripting. Use when deciding how to frame a talk, preparing a CFP submission, or choosing between multiple narrative angles.
talk-stage3-concepts
Builds a numbered, categorized concept catalogue from the talk summary and timeline, scoring each concept HIGH / MEDIUM / LOW for talk potential with optional repo enrichment. Use when you need a structured inventory of concepts before choosing a talk angle, or when assessing which ideas have the strongest presentation potential.
talk-stage2-research
Performs git archaeology, changelog analysis, and builds a verified factual timeline by cross-referencing git history with source material. REX mode only — skipped automatically in Concept mode. Use when building a REX talk and you need verified commit metrics, release timelines, and contributor data from a git repository.
talk-stage1-extract
Extracts and structures source material (articles, transcripts, notes) into a talk summary with narrative arc, themes, metrics, and gaps. Auto-detects REX vs Concept type. Use when starting a new talk from any source material or auditing existing material before committing to a talk.
talk-pipeline
Orchestrates the complete talk preparation pipeline from raw material to revision sheets, running 6 stages in sequence with human-in-the-loop checkpoints for REX or Concept mode talks. Use when starting a new talk pipeline, resuming a pipeline from a specific stage, or running the full end-to-end preparation workflow.
skill-creator
Scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources. Use when creating a custom skill, standardizing skill structure across a team, or packaging a skill for distribution.
rtk-optimizer
Wrap high-verbosity shell commands with RTK to reduce token consumption. Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens.
release-notes-generator
Generate release notes in 3 formats (CHANGELOG.md, PR body, Slack announcement) from git commits. Automatically categorizes changes and converts technical language to user-friendly messaging. Use for releases, changelogs, version notes, what's new summaries, or ship announcements.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
landing-page-generator
Generate complete, deploy-ready landing pages from any repository. Use when creating a homepage for an open-source project, building a project website, converting a README into a marketing page, or standardizing landing pages across multiple repos.