rampstackco/claude-skills / skills/content-repurposing
content-repurposing
VerifiedCross-format content adaptation. Turning one substantial piece into many derivative formats (blog series, email sequences, social posts, webinars, podcasts, video shorts) without losing the original's value or producing AI-slop variants. The discipline of adaptation per medium rather than mass-blast distribution. Triggers on content repurposing, content adaptation, cross-format content, content atomization, content multiplication, content distribution across formats, source-piece-to-derivative, video shorts from blog, email from whitepaper, podcast from article, blog series from research. Also triggers when a flagship piece is shipping but the team has not planned how to extend it across formats, when repurposing is happening but the derivatives feel mass-produced, or when AI-assisted repurposing is producing slop variants of strong source pieces.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 360 B |
| SKILL.md | skill md | 23.7 KB |
| references/aeo-extraction-patterns.md | markdown | 10.4 KB |
| references/common-repurposing-failures.md | markdown | 10.5 KB |
| references/cross-promotion-patterns.md | markdown | 9.5 KB |
| references/format-adaptation-patterns.md | markdown | 13.4 KB |
| references/per-format-constraints.md | markdown | 10.5 KB |
| references/repurposing-pipeline-templates.md | markdown | 11.4 KB |
| references/sequencing-and-cadence-patterns.md | markdown | 11.2 KB |
| references/source-piece-selection-criteria.md | markdown | 10.9 KB |
| references/voice-consistency-across-formats.md | markdown | 10.7 KB |
references/voice-consistency-across-formats.md
View on GitHub# Voice consistency across formats
What stays constant and what adapts. The voice audit per derivative. The AI-repurposing voice problem and the discipline that prevents it.
Voice is the most visible casualty of careless repurposing. The source piece may have specific voice characteristics; derivatives generated without strong voice discipline drift toward AI-default or platform-default register. Audiences detect the drift even when they cannot articulate it; the cross-format set reads as work from different brands rather than as a coherent program.
---
## What stays constant
The brand-voice elements that should survive every format adaptation.
**The brand's POV on the topic.** If the source piece argues a specific position, the derivatives carry the same position. A derivative that hedges where the source committed, or that takes a different angle than the source, breaks the cross-format coherence.
**Distinctive vocabulary.** Brand-specific terms, framings, and phrasings that signal "this is from this brand." If the source uses a particular word for a concept, derivatives use the same word. If the source has a recognizable phrase, derivatives carry the phrase.
**Level of conviction or hedging.** Brands have characteristic stance positions. Some brands commit; some hedge thoughtfully; some are confrontational. The derivatives carry the brand's stance pattern even when format conventions might pull toward different stance defaults.
**Audience-respect register.** Brands address audiences in specific ways: peer-to-peer, expert-to-novice, alongside-the-reader. The register stays consistent across formats; derivatives that suddenly talk down to the audience break voice coherence.
**Anti-patterns the brand avoids.** If the brand does not use particular framings (motivational filler, generic-content-marketing voice, hype-driven language), derivatives also avoid them. Anti-pattern adherence is part of voice.
---
## What adapts per format
Voice elements that should adjust to the medium.
**Sentence length and structure.** Spoken voice differs from written. Email voice differs from blog voice. Social-post voice differs from email voice. The brand's voice characteristics survive through these adaptations, but the surface-level sentence patterns change.
- Print: medium sentences with occasional layered constructions.
- Email: shorter sentences, more direct address.
- Spoken (podcast, video): conversational rhythm with natural pauses and asides.
- Social: tight phrasing in first lines, paragraph breaks frequent.
**Density.** Visual formats can carry less per minute than text formats. A short video cannot fit the density of a paragraph; the same point in video form has more breathing room.
**Conversational vs declarative register.** Podcasts are conversational; whitepapers are declarative. The brand's POV stays the same in both; the framing register adapts.
**Direct-address frequency.** "You" usage varies by format. Emails often use "you" frequently; whitepapers may use "the reader" or "marketers" more often. The shift is appropriate; pulling email voice into a whitepaper or vice versa would feel off.
**Visual element usage.** Some formats use visuals heavily (social, video); others rely on text (email, long-form). Voice adapts to whether visuals are doing some of the work.
---
## The voice audit per derivative
A short framework for verifying voice consistency.
1. **Read or watch the derivative as if encountering it cold.** Could a reader who knows the brand identify this as the brand's work? If yes, voice is working.
2. **Compare to the source piece.** Does the derivative carry the source's POV, vocabulary, and stance? Where it differs, is the difference appropriate format adaptation or unwanted drift?
3. **Check against the brand's voice anti-patterns.** Is the derivative slipping into framings the brand normally avoids? AI-default voice often slips in through derivatives.
4. **Check sentence-level patterns.** Sentence length, paragraph length, direct-address frequency, vocabulary. Are they format-appropriate but brand-recognizable?
5. **Read aloud (for written derivatives) or read the script (for spoken derivatives).** Does it sound like the brand's voice as the brand would speak it?
The voice audit is one of the easiest to skip and one of the most consequential. Pieces that pass everything else but fail voice audit damage the cross-format coherence.
---
## The AI-repurposing voice problem
AI-assisted repurposing is particularly prone to voice drift.
**The pattern.** The source piece has specific voice characteristics. AI generation of derivatives is asked to "summarize this for LinkedIn" or "turn this into emails." The AI produces derivatives that are technically related to the source but written in AI-default voice rather than the source's distinctive voice.
**Why it happens.** AI generation regresses to model defaults unless the writer actively pulls it back. Without strong voice prompts, the derivatives sound like the AI's voice using the source's content. Multiple derivatives generated without voice anchor compound the drift; by the tenth derivative the cross-format set has lost the source's voice entirely.
**The cure.**
- **Voice guidelines as prompt input.** Every AI generation includes the brand voice guidelines as context. Generic prompts produce generic outputs.
- **Sample text as voice anchor.** Feed the AI 2-3 paragraphs of the source piece in their original voice. AI mimics what it sees more than what it is told.
- **Per-derivative voice review.** Each derivative gets a voice audit. Drift detected gets revision. The audit is non-negotiable.
- **Rewrite the bland.** Any sentence that could appear in any other piece on the topic gets rewritten in voice. Voice lives in the specific.
See `ai-content-collaboration` for the broader voice-preservation discipline that applies across AI-assisted content workflows. The repurposing-specific application is that voice drift compounds across multiple derivatives in ways that single-piece AI generation does not.
---
## When format conventions pull against brand voice
Sometimes a format's conventions push toward voice that does not match the brand.
**LinkedIn motivational tone.** LinkedIn rewards a particular kind of motivational and personal-narrative content. Brands with crisp analytical voice may resist the convention; the right answer is usually to maintain voice rather than to drift into LinkedIn-default motivational tone, even at cost of platform-specific engagement.
**TikTok's high-energy delivery.** TikTok rewards high-energy short-form delivery. Brands with measured analytical voice may not fit naturally; the right answer may be to skip TikTok rather than to produce content that sounds wrong for the brand.
**Podcast-host conversational warmth.** Some podcast styles reward warm conversational delivery; a brand with confrontational analytical voice may struggle to produce derivatives that fit. The right answer may be to format-fit (use a different format) or to produce derivatives that hold the brand's voice even at engagement cost.
**The discipline.** Format-fit decisions are upstream of voice-adaptation decisions. If a format genuinely cannot accommodate the brand's voice, skipping the format is sometimes the right answer; voice integrity matters more than universal cross-format presence.
---
## Voice prompts for AI-assisted repurposing
When AI generates derivatives, the prompts should carry voice instructions.
**Components of a voice prompt.**
- 2-3 paragraphs of the source piece in original voice as anchor.
- A short voice description (3-5 specific characteristics).
- A short anti-pattern list (3-5 framings the brand avoids).
- Per-format adjustments (sentence length, register, direct-address frequency).
**A worked prompt example pattern.** "The source piece below is in the brand's voice. Convert it into [target format]. The voice characteristics to preserve: [specific characteristics]. The anti-patterns to avoid: [specific anti-patterns]. The format adaptations: [format-specific]. Source piece: [text]."
The discipline is including the voice instructions in every derivative generation, not assuming the AI will infer voice from the source alone. AI tools differ in how well they infer voice from samples; the safest discipline is explicit voice instruction.
---
## Voice consistency across multiple writers or AI generators
Programs with multiple writers or AI generators producing derivatives have a multi-source voice drift problem.
**The risk.** Writer A produces three derivatives in slightly different voice from writer B's four derivatives, plus AI generates two more in default voice. The cross-format set has three voice variants, none of them quite the source's voice.
**The discipline.**
- **Single voice owner.** One person reviews all derivatives in the cross-format set for voice consistency. Catches drift across writers.
- **Voice library.** Documented brand voice with examples; all writers and AI generators reference the same library.
- **Calibration sessions.** Periodically, multiple writers (or writers plus the editorial lead) review derivatives together and reconcile voice expectations.
Programs with sophisticated voice discipline can run multi-writer derivative production without losing voice; programs without discipline produce voice variants that audiences notice.
---
## Common voice failures in repurposing
**AI-default drift.** Derivatives sound like the AI's voice rather than the brand's voice. Cure: stronger voice prompts; per-derivative review.
**Platform-default drift.** Derivatives sound like the platform's default register rather than the brand's voice. Cure: voice-over-platform-fit discipline; sometimes skip the platform.
**Cross-derivative drift.** Each derivative is fine alone but the cross-format set reads as voice variants. Cure: single voice owner across the set.
**Source-voice loss.** Derivatives carry the source's content but not the source's voice characteristics. Cure: voice anchor with sample text from the source.
**Voice-only-on-source.** The source piece has voice; the derivatives default to generic. Cure: voice discipline applies to derivatives, not just to the source.
---
## Methodology-level choices that stay in the public skill
The constant-vs-adapting voice elements, the voice audit, the AI-repurposing voice problem and its cure, the format-vs-voice tension, the multi-writer voice discipline, the common voice failures.
## Implementation choices that stay internal
Specific voice-prompt templates per AI tool. Specific voice-library documentation in the team's writing system. Specific calibration session formats. Specific reviewer dashboards that surface cross-derivative voice variation. The team's own conventions for voice-vs-format tradeoffs. These vary by team, AI tooling, and brand voice maturity.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |