// Use when rewriting AI-generated text to match a specific person's or brand's authentic voice. Use when AI output sounds generic, corporate, or detectable. Unlike generic "humanizers," this skill requires voice analysis input and produces voice-consistent output, not fake imperfections.
Run a structured 5-pass finishing audit on any website before launch — scoring visual polish, technical foundation, UX completeness, content quality, and cross-device readiness on 100 points. Use when: **Pre-launch** - Final validation before going live; **Post-redesign** - Verify nothing broke during the overhaul; **Client handoff** - Structured proof that the site is ready; **Quarterly review** - Catch accumulated debt; **Single-pass focus** - Run just Pass 2 after a perf sprint
Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumps
Model best-case, worst-case, and likely revenue scenarios with sensitivity analysis for strategic planning. Use when: building financial forecasts; presenting board scenarios; planning headcount around revenue uncertainty; modeling pricing changes impact; preparing investor updates with upside/downside ranges
Use when analyzing server logs to understand how AI crawlers (GPTBot, ClaudeBot, PerplexityBot) interact with your site. Use when optimizing content placement for LLM retrieval, diagnosing why AI search isn't citing your content, or auditing crawl patterns to find optimization gaps.
Use when optimizing for AI search visibility where individual experts and entities outperform generic brand pages. Use when building cross-platform authority for people, organizations, or products that AI models should recognize and cite.
Analyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and minimize CAC. Use when: planning quarterly ad budget allocation, diagnosing underperforming ad channels, deciding whether to scale spend on a channel, calculating marginal ROI across Google Ads, Meta, LinkedIn, or TikTok, rebalancing media mix after performance shifts, or setting up a test-and-scale framework for new channels.
| name | voice-injection-rewriter |
| description | Use when rewriting AI-generated text to match a specific person's or brand's authentic voice. Use when AI output sounds generic, corporate, or detectable. Unlike generic "humanizers," this skill requires voice analysis input and produces voice-consistent output, not fake imperfections. |
| license | MIT |
| metadata | {"author":"ClawFu","version":"1.0.0","mcp-server":"@clawfu/mcp-skills"} |
Transform AI-generated text into authentic, voice-consistent content — not by faking humanity, but by applying real voice patterns from a specific person or brand.
Use this skill when you need to:
This skill is NOT a generic "humanizer." It requires voice input — either from brand-voice-learner output, ClawFu brand memory, or voice samples you provide.
Why this matters: Generic humanizers add fake imperfections (random typos, forced contractions) to trick detectors. That's an arms race you lose. This skill applies YOUR voice patterns — which produces naturally human text because it IS the voice of a real human.
Core Principle: AI text sounds artificial not because it lacks typos, but because it lacks a specific person's vocabulary, rhythm, opinions, and structural habits. The fix is voice injection, not cosmetic imperfection.
Sources:
brand-voice-learner)The 201 insight: Most people try to make AI text "sound human" (generic). The actual skill is making AI text "sound like ME" (specific). The first is commodity. The second is craft.
| Claude Does | You Decide |
|---|---|
| Applies voice patterns to rewrite text | Which voice profile to use |
| Strips AI detection signals | How far to deviate from the original |
| Identifies voice mismatches | Final approval of tone and accuracy |
| Suggests voice-consistent alternatives | Where factual precision overrides voice |
| Runs enforcement checklists | Publication context and audience |
Before using this skill, you need ONE of these:
| Voice Source | How to Get It | Quality |
|---|---|---|
| ClawFu brand memory | get_brand [name] — pre-stored voice profile | Best |
| brand-voice-learner output | Run the analysis skill on 10+ writing samples | Very good |
| 3-5 writing samples | Paste examples of the target voice | Good |
| Voice description | "Analytical, dry, French, no buzzwords, short sentences" | Minimum viable |
Start by establishing the voice you're targeting.
If using ClawFu brand memory:
Load brand voice for [name]. Apply it to rewrite the following text.
If providing samples:
Here are 3 examples of my writing voice:
[Sample 1]
[Sample 2]
[Sample 3]
Extract the voice patterns, then rewrite this AI-generated text to match:
[AI text]
If describing voice:
My voice profile:
- Register: [analytical/casual/authoritative/conversational]
- Sentence length: [short punchy / mixed / long flowing]
- Contractions: [always / sometimes / never]
- Opinions: [strong and stated / subtle / neutral]
- Vocabulary: [technical / accessible / mixed]
- Signature moves: [specific habits — e.g., "Ce n'est pas X. C'est Y."]
- Forbidden words: [list any words you never use]
Rewrite this to match:
[AI text]
Before rewriting, identify what makes the text sound AI-generated.
Structural signals:
Vocabulary signals:
Tonal signals:
Flag template:
AI FINGERPRINT SCAN:
□ Uniform sentence length? [yes/no]
□ Buzzword count: [N] instances
□ Transition density: [N] per paragraph
□ Contractions present? [yes/no]
□ Opinions/personality present? [yes/no]
□ Any sentence you'd never actually say? [list]
Apply the voice profile to the flagged text. This is the core operation.
Pass 1 — Kill AI vocabulary
Replace every AI-default word with the voice-appropriate equivalent:
| AI Default | Generic Human | Voice-Specific (example) |
|---|---|---|
| "Delve into" | "dig into" | Depends on voice — could be "creuser," "regarder de plus près," "explorer" |
| "Leverage" | "use" | Voice may prefer "exploiter," "utiliser," or "s'appuyer sur" |
| "Landscape" | "space" | Voice may prefer "marché," "écosystème," or just name the thing |
| "Robust" | "strong" | Voice may prefer "solide," "fiable," or a domain-specific term |
| "Moreover" | "Plus" | Voice may prefer "Et," "D'ailleurs," or nothing at all |
| "Ensure" | "make sure" | Voice may prefer "vérifier," "s'assurer," or just drop it |
| "Comprehensive" | "full" | Voice may prefer "complet," "exhaustif," or cut the word entirely |
| "It is important to note" | (cut) | Replace with direct statement of the thing |
Pass 2 — Break rhythm uniformity
Pass 3 — Inject voice-specific patterns
Pull from the voice profile:
Pass 4 — Contraction and register pass
Pass 5 — Read-aloud test
Read the full text aloud. For each sentence ask:
If any sentence fails, rewrite that sentence from scratch in the voice.
## Original (AI-generated)
> [The input text]
## Rewritten (Voice: [Name/Brand])
[The rewritten text]
## Changes Made
- **Vocabulary**: [3-5 key word swaps]
- **Rhythm**: [What changed structurally]
- **Voice markers**: [What was injected from the voice profile]
- **Removed**: [What AI signals were stripped]
## Voice Consistency Score
[High/Medium/Low] — [one-line explanation]
If rewriting multiple pieces, skip the detailed output:
[Rewritten text only]
---
*Voice: [Name] | Swaps: [N] | Score: [H/M/L]*
Voice Profile: Matthieu Credou — Analytical-first, dry, short sentences, "Ce n'est pas X. C'est Y." recadrage, no buzzwords, no emojis, 201 level
AI Input:
"In today's rapidly evolving digital landscape, leveraging AI-powered tools has become essential for businesses seeking to maintain their competitive edge. Moreover, organizations that fail to adopt these comprehensive solutions risk falling behind in an increasingly automated marketplace."
Rewritten (Voice: Matthieu):
Tout le monde dit qu'il faut "adopter l'IA" pour rester compétitif. Ce n'est pas un problème d'adoption. C'est un problème de savoir quoi en faire.
La plupart des boîtes installent des outils IA comme on installe un ERP — par obligation, sans stratégie. Résultat : elles automatisent leurs erreurs plus vite.
Changes Made:
Voice Consistency Score: High — matches analytical register, uses signature recadrage, no buzzwords
Voice Profile: Startup brand — casual, contractions always, "Here's the thing" opener, short paragraphs, second person, anti-corporate
AI Input:
"We are pleased to announce that our platform now offers a comprehensive suite of analytics tools designed to empower teams to make data-driven decisions. These robust features include real-time dashboards, automated reporting, and customizable metrics tracking."
Rewritten (Voice: Brand):
Here's the thing — we just shipped analytics. Real dashboards, automated reports, and metrics you actually set up yourself.
No more exporting CSVs at 11pm to make a chart for Monday's meeting. Your data's right there. Live.
Changes Made:
Voice Consistency Score: High — casual, direct, anti-corporate, relatable
Voice Profile: Tech consultant — uses analogies, explains jargon inline, mixed sentence length, "In practice" as a pivot phrase, occasional rhetorical questions
AI Input:
"Implementing a microservices architecture requires careful consideration of service boundaries, inter-service communication protocols, and data consistency patterns. Organizations should ensure that their teams possess the requisite expertise to manage the increased operational complexity inherent in distributed systems."
Rewritten (Voice: Consultant):
Microservices sound great in conference talks. In practice, they mean your team now manages 40 tiny services instead of one big app — and every service needs to talk to every other service without losing data along the way.
The question isn't whether microservices are better. It's whether your team can handle the operational overhead. If you're struggling with one monolith, splitting it into 40 pieces doesn't fix the problem. It multiplies it.
Changes Made:
Voice Consistency Score: High — explains by analogy, rhetorical questions, "In practice" pivot present
This skill makes AI output sound like a specific human — not "human in general." Generic humanization (adding random typos, forced slang, fake imperfections) is:
The goal is authenticity, not deception.
Follow-up prompts:
Methodology:
brand-voice-learner skill (voice analysis methodology)Community Input:
name: voice-injection-rewriter
category: content
subcategory: voice
version: 1.0.0
author: GUIA
source_expert: NN/g Voice Research + ClawFu brand-voice-learner methodology + Cyril Frémont (WhatsApp IA NDD Camp community)
difficulty: intermediate
mode: cyborg
tags: [voice, rewriting, ai-detection, brand-voice, authenticity, humanization, content-editing]
created: 2026-02-10
updated: 2026-02-10