voice-input-processor
A pre-processor skill for input that arrives via voice-to-text or as unstructured, free-flowing thought. Use when receiving long, complex, or voice-to-text input that may contain jumbled word order, misheard or substituted words, or unclear structure. Automatically applies to substantial input (roughly 3+ sentences) showing signs of voice-to-text errors or non-linear thinking. Also triggers manually when the user says things like process this, clean this up, interpret this, or make sense of this. Interprets input charitably, corrects errors, extracts clear meaning, and produces two outputs: a
npx skills add majiayu000/claude-skill-registry --skill voice-input-processor --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Voice Input Processor A pre-processing skill that turns messy, voice-to-text or free-flowing input into clean, structured understanding — before any action is taken. This skill is a **pre-processor only**. It does not write blog posts, reports, or final documents. Its sole job is comprehension and clarity. It feeds cleanly into whatever comes next — whether that is Claude acting directly, or a downstream skill taking over. --- ## Understanding This Kind of Input People communicating via voice-to-text, or thinking out loud, are not confused or unclear in their thinking. The ideas are often rich, well-reasoned, and intelligent. The *expression* is where friction occurs. Common patterns to expect and work with: - **Word substitutions** — voice-to-text mishearing produces wrong but phonetically similar words (e.g. "lords" instead of "Claude", "work" instead of "word", "hand off" instead of "handoff") - **Non-linear structure** — the core point may arrive before or after the context that explains it; ideas loop back on themselves - **Imprecise vocabulary** — the right word may not come easily; a near-enough word is used instead; read for intent - **Incomplete sentences** — thought mov
- Understanding This Kind of Input
- When to Apply
- Core Principles
- Processing Layers
- Layer 1 — Interpret
- Layer 2 — Extract
- Layer 3 — Produce Two Outputs
- Layer 4 — Confirm
- Handoff Behaviour
- What This Skill Does Not Do
What does the voice-input-processor skill do?
A pre-processor skill for input that arrives via voice-to-text or as unstructured, free-flowing thought. Use when receiving long, complex, or voice-to-text input that may contain jumbled word order, misheard or substituted words, or unclear structure. Automatically applies to substantial input (roughly 3+ sentences) showing signs of voice-to-text errors or non-linear thinking. Also triggers manually when the user says things like process this, clean this up, interpret this, or make sense of this. Interprets input charitably, corrects errors, extracts clear meaning, and produces two outputs: a
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill voice-input-processor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.