tumaini-voicelisted

Use this skill when a user wants to build a personalized writing assistant — a copywriter, content writer, or "writes like me" agent — that captures their own voice, tone, and style. Triggers include: "help me build an AI that writes like me", "I want a copywriter for my brand/newsletter/blog", "create a writing assistant for this project", "set up a style guide so Claude writes in my voice", or any request to define personality, voice, tone, or writing rules for an agent producing blog posts, marketing copy, emails, social posts, or messages. Consider this skill whenever the user wants AI-generated content to "sound like them," even without the words "skill" or "agent". Runs a structured Socratic interview (~30 minutes), optionally analyzes writing samples the user provides, and produces a new, installable writer skill ready to drop into any project.
Kimotep/skills · ★ 0 · AI & Automation · score 75

Install: claude install-skill Kimotep/skills

# tumaini-voice This skill interviews the user about how *they* write, then builds a new Claude skill that writes the same way. The output isn't a style guide someone has to remember to paste in — it's an installable copywriter: a personalized agent the user drops into any project to produce blog posts, emails, social copy, and more in their own voice. **Target session length: 30 minutes.** **This is a tumaini-family skill** — same operating principles as `socratic-agentic-workflow`: always ask rather than assume, classify assumptions by how expensive they'd be to get wrong, and pause/resume rather than force a rushed result. --- ## How this skill works The skill runs in three phases: 1. **Interview** — adaptive Socratic questioning across 8 themes, with an optional pass over writing samples the user provides 2. **Synthesis** — reflect the voice profile back, classify assumptions, check it against any samples, confirm before generating 3. **Output** — write a new skill package: a `SKILL.md` for the personalized writer, a full voice profile, and one reference file per content type the user actually needs Read all linked documents before starting: - [`INTERVIEW.md`](./INTERVIEW.md) — themes, sample analysis, pacing, pause/resume - [`SYNTHESIS.md`](./SYNTHESIS.md) — reflection, assumption classification, confirmation - [`OUTPUT.md`](./OUTPUT.md) — how to name, structure, and write the generated writer skill --- ## Core principles **Always ask, never