Voice Injection Rewriter
技能 已验证 活跃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.
To transform generic AI-generated text into authentic, voice-consistent content by injecting specific linguistic patterns, rather than applying fake imperfections.
功能
- Rewrites AI drafts to match a specific person's or brand's voice
- Strips AI detection signals from generated content
- Enforces voice consistency across AI-assisted content
- Provides detailed analysis of changes made
- Offers structured output for batch processing or detailed review
使用场景
- Rewriting AI blog posts to match a brand's established voice
- Ensuring consistent tone across AI-generated social media content
- Post-processing AI emails to sound like a specific individual
- Bridging the gap between AI efficiency and authentic brand expression
非目标
- Creating a voice from scratch without any input
- Guaranteeing undetectable output or deceiving AI detectors
- Replacing genuine subject matter expertise
- Working without sufficient voice input
工作流
- Load voice profile (brand memory, samples, or description)
- Scan AI text for detection signals (optional)
- Rewrite text applying voice patterns
- Format output with original, rewritten, changes, and score
实践
- Voice analysis
- Content editing
- AI detection mitigation
- Brand consistency
先决条件
- Voice profile (ClawFu brand memory, brand-voice-learner output, writing samples, or voice description)
- AI-generated text to rewrite
Compliance
- info:GDPRThe skill operates on user-provided text, which may include personal data. However, it does not submit this data to a third party, and there are no explicit sanitization steps documented beyond LLM processing.
安装
npx skills add guia-matthieu/clawfu-skills通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
De Ai Ify
100Remove AI-generated jargon and restore human voice to text. Built from analyzing 1,000+ AI vs human content pieces.
Improve Content
95Use when rewriting or refreshing an existing page that's underperforming. The agent fetches the URL, analyzes the current content, researches the SERP, and rewrites using the full anti-AI-slop ruleset — no data exports needed.
LinkedIn Humanizer
100Scrub AI tells from any text draft OR audit a finished post against the 2026 algorithm heuristic checklist. Tier-based rewriter (forensic / strict / aesthetic / all) plus `--mode audit` for detection-only pass-fail review covering length, hook, CTA, format penalties, AI vocab. Sub-tools: emoji-pattern detector, multi-detector spread tester (GPTZero, Originality.ai, ZeroGPT, Sapling, Copyleaks), rule explainer. Triggers on "humanize", "de-AI", "review this draft", "audit before posting", "is this ready".
Unslop Review
100重写代码审查意见，使其听起来像人类同事所写。消除 "I noticed...", "I was wondering if perhaps...", "It might be worth considering..." 这类企业AI的套话。每条评论都直截了当：地点、问题、具体修复方案。用于用户说“人性化审查”、“减少PR评论中的废话”、“让反馈听起来更人性化”、“审查此PR”、“代码审查”、“/review”、“/unslop-review”时。在审查PR时自动触发。
Avoid Ai Writing
100审计和重写内容以移除 AI 写作模式（“AI 腔”）。在收到“移除 AI 腔”、“清理 AI 写作”、“编辑写作中的 AI 模式”、“审计写作中的 AI 痕迹”或“让这段文字听起来不那么像 AI”等指令时使用此技能。支持仅检测模式，用于标记模式而不进行重写。
Voice Checker
98Reviews lyrics and prose for AI-written patterns (abstract noun stacking, over-explained metaphors, cliche escalation, missing idiosyncrasy, prose AI tells). Advisory Warning/Info severity — flags issues, does not block or rewrite. Use when reviewing lyrics for authenticity or before generation to catch AI-sounding language.