Rewrites narration or commentary to match a defined presenter voice and tone, preserving factual content while adapting register, sentence structure, and personality.
How this skill is triggered — by the user, by Claude, or both
Slash command
/autopunk-media-skills:narrator-voice-adapterThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Rewrites existing narration or commentary to match a defined presenter or narrator voice and tone, preserving the factual content while adapting register, sentence structure, and personality.
Rewrites existing narration or commentary to match a defined presenter or narrator voice and tone, preserving the factual content while adapting register, sentence structure, and personality.
Required: The original narration text; a description of the target voice (register, personality, sentence style, emotional range); the documentary's subject and tone Optional: Sample text written in the target voice (a transcript excerpt, a comparable film's narration, or a note written by the presenter themselves); the narrator's name if they are a known public figure whose voice style you are approximating; the sequence context (where this narration falls in the film)
Side-by-side presentation (or clearly labeled Original / Adapted versions if side-by-side is impractical). Each version labeled. Approximate word count for both. Followed by Voice Notes (100–150 words) describing the specific changes made. The adapted version should be usable as a recording script without further editing.
Original narration: "The Mekong River, stretching 4,350 kilometres from the Tibetan Plateau to the South China Sea, passes through six countries and supports the livelihoods of approximately 70 million people. In the past decade, the construction of eleven large-scale hydroelectric dams has fundamentally altered the river's flow, reducing sediment transport and disrupting the annual flood cycle upon which downstream agriculture depends. Scientists have documented a decline of 40 percent in fish biomass in the lower Mekong since 2010."
Target voice: Conversational but authoritative. A presenter who speaks directly to the viewer as an equal — not lecturing, not dumbing down. Uses the first person occasionally. Asks rhetorical questions to pull viewers in. Short sentences. Feels like someone who cares deeply about the subject and assumes the viewer will too.
Documentary subject: Environmental documentary on the Mekong River
Original Version (~80 words)
"The Mekong River, stretching 4,350 kilometres from the Tibetan Plateau to the South China Sea, passes through six countries and supports the livelihoods of approximately 70 million people. In the past decade, the construction of eleven large-scale hydroelectric dams has fundamentally altered the river's flow, reducing sediment transport and disrupting the annual flood cycle upon which downstream agriculture depends. Scientists have documented a decline of 40 percent in fish biomass in the lower Mekong since 2010."
Adapted Version (~75 words)
"4,350 kilometres. Six countries. Seventy million people whose lives depend on what this river does next. The Mekong has always provided. For centuries, that felt like a given.
In the last decade, eleven dams have gone up along its course. The floods that farmers have counted on for generations — the floods that bring the fish, replenish the soil — they don't come the way they used to.
Since 2010, fish in the lower Mekong: down 40 percent."
Voice Notes
The original narration is accurate and well-structured but reads like a briefing document — it presents facts at the viewer rather than inviting them in. The adapted version uses the same figures but restructures them to land as revelation rather than exposition. The opening numerical sequence creates a physical sense of scale before naming the river, reversing the original's order. The first person is implied ("that felt like a given") rather than stated. Short declarative sentences replace compound sentence structures. The final line — "down 40 percent" — is deliberately stripped of its qualifying language to land as an emotional statement rather than a statistical one. If the director requires the full scientific attribution ("scientists have documented"), it can be reinserted without disrupting the voice.
npx claudepluginhub ur-grue/autopunk-media-skills --plugin autopunk-media-skillsTransforms research notes, transcripts, or articles into broadcast-ready voice-over scripts with short sentences, active voice, and timing estimates for picture.
Applies voice profiles like technical-authority, friendly-explainer, or executive-brief to transform content tone, vocabulary, structure, and perspective. Use for rewriting docs, tutorials, or comms in specific styles.
Rephrases or rewrites content to match user's preferred tone, voice, and style using WritingKit and UserProfile JSON. Preserves facts for article drafts.