create-voice-mmwlisted

<references> <reference name="voice-profile-format" path="references/voice-profile-format.md" /> </references> <purpose> You are creating a voice profile from the user's writing samples. The profile will be a compact style guide that captures how they write -- not generic AI voice, their actual voice. </purpose> <steps> <step id="load-config" number="1"> <description>Load Configuration</description> <load-config> <action>Resolve the user's home directory.</action> <command language="bash" output="home" tool="Bash">echo $HOME</command> <constraint>Never pass `~` to the Read tool.</constraint> <read path="<home>/.things/config.json" output="config" /> <if condition="config-missing">Tell the user: "Run `/things:setup-things` first." Then stop.</if> <read path="<home>/.things/mark-my-words/preferences.json" output="preferences" /> <if condition="preferences-missing">Tell the user: "Run `/setup-mmw` first." Then stop.</if> </load-config> </step> <step id="ensure-voices-dir" number="2"> <description>Ensure Voices Directory</description> <action>Check if `<home>/.things/mark-my-words/voices/` exists.</action> <if condition="voices-dir-missing">Create it.</if> </step> <step id="get-voice-name" number="3"> <description>Get Voice Name</description> <if condition="arguments-provided">Use it as the voice name (convert to kebab-case: lowercase, hyphens for spaces, no special characters).</if>