Help us improve
Share bugs, ideas, or general feedback.
From human-voice
Conducts adaptive interviews with 60-80 questions across 12 modules to build multi-dimensional written-voice profiles, using branching logic, NLP analysis, and session state management.
npx claudepluginhub zircote/human-voiceHow this skill is triggered — by the user, by Claude, or both
Slash command
/human-voice:voiceThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Voice is an adaptive voice elicitation interview engine that builds a comprehensive written-voice profile through a structured conversational interview. The engine administers 60-80 questions across 12 thematic modules, adapting its path based on the participant's responses and detected writer type.
Drafts personalized cold emails, warm intros, follow-ups, updates, and communications for investor outreach during fundraising to angels, VCs, accelerators.
Share bugs, ideas, or general feedback.
Voice is an adaptive voice elicitation interview engine that builds a comprehensive written-voice profile through a structured conversational interview. The engine administers 60-80 questions across 12 thematic modules, adapting its path based on the participant's responses and detected writer type.
question-bank/modules/, validated against question-bank/schemas/question.schema.jsonquestion-bank/branching/ that route participants through writer-type-specific question sequencesnlp/ that extract stylistic signals from open-ended and writing-sample responsesscoring/ that maps responses to voice profile dimensions with weighted aggregationagents/ that orchestrate the interview flowThe interview spans 12 modules plus a screening/demographic preamble (SD). Modules cover dimensions such as formality and register, emotional tone, sentence structure, vocabulary preferences, rhetorical patterns, audience awareness, and stylistic identity. Each module contains 4-8 questions with a mix of question types (likert, forced_choice, scenario, open_ended, writing_sample, calibration, etc.) to triangulate self-reported preferences against observed behavior.
~/.human-voice/sessions/{session_id}/.state.json with status init, empty response arrays, and module progress tracking.question-bank/modules/ directory.~/.human-voice/sessions/.paused or in_progress in their state.json.Voice produces a dual-output voice profile stored as profile.json in the session directory:
The final profile includes per-dimension scores, a composite writer-type classification, distinctive features, and calibration annotations.
All profiles, sessions, and config live under ~/.human-voice/. This is the single canonical location — the plugin does not honour plugin-runtime data directories, ensuring consistent profile access across multiple Claude accounts.
All session data is stored under ~/.human-voice/sessions/{session_id}/:
state.json — Session state: status, current module, current question index, branching path, timestampsresponses.json — Raw responses keyed by question_id with timestampsscores.json — Running dimension scores updated after each responseprofile.json — Final assembled voice profile (written on completion)writing_samples/ — Collected writing samples for NLP analysis