voice-input-processor

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 moves faster than speech; words get dropped
• Thinking out loud — the input may include the user working something out as they speak, not just stating a conclusion

Trust the intelligence behind the input even when the surface expression is imperfect. Your job is to bridge the gap, not to judge the quality of what was said.

---

When to Apply

Apply automatically when input:

• Is 3 or more sentences long and shows signs of voice-to-text errors or non-linear structure
• Contains words that appear to be misheard substitutions
• Is a memo, set of instructions, or block of ideas being handed over for processing

Apply on manual trigger when the user says:

• "Process this"
• "Clean this up"
• "Interpret this"
• "Make sense of this"
• Or any similar phrase indicating they want their input clarified before action