talking-head-podcast-recut
Provider-independent production workflow for recutting long talking-head, podcast, interview, webinar, panel, lecture, livestream, founder call, or customer-call footage into short clips, highlight reels, trailers, audiograms, captioned vertical videos, and social cutdowns. Use when an agent must ingest source recordings, transcribe and diarize speakers, select quotes without misrepresentation, preserve context, handle consent/rights/disclosures, clean jump cuts and audio, add captions, graphics, lower thirds, b-roll, platform variants, synthetic-media boundaries, review packets, delivery spec
Profile →npx skills add calesthio/generative-media-skills --skill talking-head-podcast-recut --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Turns existing speech-led media into derivative edits (clips, highlight reels, trailers, audiograms, captioned vertical videos, and social cutdowns) with a focus on editorial integrity, rights handling, and review standards. It supports transcription, speaker diarization, quotes without misrepresentation, consent disclosures, and delivery specs. The workflow emphasizes preserving context and maintaining an audit trail from final frame back to source timecodes.
How it works
- Intakes a production brief with required fields (sources, deliverables, platforms, rights, approvals, risk notes) and creates a production ledger template.
- Ingests source media by preserving originals and recording metadata; generates high-quality audio for transcription; creates a timestamped transcript with speaker diarization; builds a speaker map including consent and usage.
- Marks unusable or restricted sections; lightly normalizes transcript for readability while preserving verbatim layers for quotes.
- Builds searchable markers for topics, emotions, claims, proofs, story beats, objections, and audience questions.
- Applies an intake-driven rights, consent, and disclosure gate with escalation triggers for unknown high-risk items and a documented set of platform/disclosure guidelines.
- Provides quote selection criteria and clip-structure heuristics (single-idea vertical clip, two-speaker exchanges, highlight reels, audiograms, testimonials) and detailed edit craft rules for A-roll assembly, B-roll/graphics, and captioning.
- Defines accessibility and caption workflows, including speaker IDs, non-speech audio cues, and delivery of burned-in and sidecar captions.
- Addresses audio cleanup and loudness standards (ITU-R BS.1770, EBU R 128, ATSC A/85) and recommends repair order to prioritize speech intelligibility.
When to use it
Use when you need to recut long talking-head content into multiple derivative formats while preserving truthful representation, managing rights/disclosures, and delivering platform-ready assets with captions and accessibility considerations.
What it can touch
- Tools specified: claude-code, codex, copilot, cursor
- Ingested source media, transcripts, speaker maps, diarization data, and generated assets (clips, captions, lower thirds, b-roll, graphics)
- Delivery packets and review documentation
Caveats
- All rights and disclosure escalations are governed by the listed criteria; outcomes depend on client-provided briefs and approvals.
- No explicit legal advice is provided; escalation triggers are outlined for rights and consent concerns.
- Platform-specific policy changes may require re-checking at production time.
# Talking-Head Podcast Recut Use this skill to turn existing speech-led media into truthful, useful derivative edits. The central obligation is editorial integrity: every cut must remain faithful to what the speaker meant in the source recording, and every commercial, synthetic, legal, or rights risk must be surfaced before publishing. This is provider-independent. Use whatever local or hosted too
What does the talking-head-podcast-recut skill do?
Provider-independent production workflow for recutting long talking-head, podcast, interview, webinar, panel, lecture, livestream, founder call, or customer-call footage into short clips, highlight reels, trailers, audiograms, captioned vertical videos, and social cutdowns. Use when an agent must ingest source recordings, transcribe and diarize speakers, select quotes without misrepresentation, preserve context, handle consent/rights/disclosures, clean jump cuts and audio, add captions, graphics, lower thirds, b-roll, platform variants, synthetic-media boundaries, review packets, delivery spec
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill talking-head-podcast-recut --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.