
Content Humanizer
Replace generic AI copy with a documented brand voice using profile extraction and named voice techniques after AI-pattern cleanup.
Overview
Content-humanizer is an agent skill most often used in Grow (also Launch distribution) that extracts a brand voice profile from exemplar copy and applies documented voice techniques so AI-assisted drafts sound distinctly
Install
npx skills add https://github.com/alirezarezvani/claude-skills --skill content-humanizerWhat is this skill?
- Mode 3 playbook: inject brand voice after AI-pattern removal (Mode 2)
- Step 1 voice profile from one exemplar piece—sentence length, formality, humor, reader relationship, signature phrases
- Six-profile extraction table (average sentence length, contractions, humor style, peer vs expert vs challenger stance)
- Documented voice types starting with Direct Expert—short sentences, confident claims, minimal hedging
- Reference voice profile before editing so rewrites stay on-brand across channels
- 6-row voice extraction question table in Step 1
- Mode 3 voice techniques follow Mode 2 AI-pattern removal
Adoption & trust: 592 installs on skills.sh; 17.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your marketing and product copy reads polished but interchangeable—readers sense AI cadence even after light editing.
Who is it for?
Solo builders with at least one strong brand sample who run content in Cursor or Claude Code and want repeatable voice passes on blogs, emails, and landing sections.
Skip if: Teams with no exemplar content to analyze, purely technical README-only repos, or workflows that skip de-AI-ing before voice injection.
When should I use this skill?
Brand content still sounds generic after AI-pattern cleanup and you need Mode 3 voice injection from a documented profile.
What do I get? / Deliverables
You get edits guided by a written voice profile and named techniques so drafts match your brand’s sentence rhythm, stance, and signature phrasing.
- Documented voice profile
- Edited copy aligned to voice types
- Reusable voice reference for future drafts
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Humanized content compounds in grow/content, but the same playbook applies when polishing launch copy before distribution. Content subphase covers newsletters, landing copy, and lifecycle emails where voice consistency drives trust and conversion.
Where it fits
Humanize a weekly newsletter draft using the Direct Expert profile extracted from your best-performing issue.
Align Product Hunt maker comment and hero blurb to the same documented voice profile before go-live.
Bring onboarding emails in line with peer-to-reader tone and signature phrases from your voice doc.
How it compares
Editorial voice workflow after pattern stripping—not a one-click paraphraser or generic tone slider.
Common Questions / FAQ
Who is content-humanizer for?
Indie founders and small marketing teams using agent assistants to draft content who need a systematic way to sound like their brand, not a default LLM.
When should I use content-humanizer?
In grow/content when refreshing lifecycle emails or blog posts; in launch/distribution when finalizing launch narratives; whenever Mode 2 AI-pattern removal is done and you need Mode 3 voice injection.
Is content-humanizer safe to install?
It processes your brand text in the agent session—avoid pasting secrets; review the Security Audits panel on this Prism page before installing from untrusted sources.
SKILL.md
READMESKILL.md - Content Humanizer
# Voice Techniques Reference Techniques for injecting authentic brand voice into content. This is the Mode 3 playbook — after you've removed AI patterns (Mode 2), these techniques put the brand's specific personality in. --- ## Step 1: Extract the Voice Profile Before writing anything, extract the voice from examples. Ask for one piece of content the brand considers representative. Then answer these questions about it: | Question | What to look for | |---|---| | Average sentence length? | Count words per sentence across 10 sentences. ≤15 = punchy. ≥25 = flowing. | | Formality level? | Count contractions ("it's" vs "it is"). Count first-person. Count slang. | | Use of humor? | Dry wit (unexpected juxtapositions). Self-deprecating (acknowledges own limitations). Provocateur (picks fights). None. | | Relationship to reader? | Peer (we're both figuring this out). Expert (I know, you're learning). Challenger (you're probably wrong about this). | | Signature phrases? | Phrases or constructions that appear more than once. That's the brand's verbal tic. | | What do they avoid? | Listen for what's conspicuously absent. | Document this as a voice profile before editing. Reference it throughout. --- ## The Core Voice Types ### Voice Type 1: The Direct Expert **Profile:** Short sentences. Confident claims. No hedging. No qualifications unless the qualification is the point. Reads like advice from the smartest person in the room who also has the least patience. **Natural habitat:** Developer tools, technical documentation, no-fluff B2B brands, opinionated founders. **Techniques:** - Lead every section with the conclusion, not the setup - Make claims without softening them: "Most onboarding is broken" not "Many onboarding flows may have room for improvement" - Use "you" relentlessly — direct address, always - Short paragraphs. Often 1-2 sentences. - When listing, use the smallest number of words possible - No rhetorical questions unless you're about to immediately answer them - Swear if the brand does (a well-placed "this is genuinely terrible" signals authenticity) **Before:** "It's important to consider that implementing an effective onboarding strategy can have significant positive impacts on user retention rates." **After:** "Fix your onboarding. It's where you're losing them." --- ### Voice Type 2: The Thoughtful Peer **Profile:** Longer sentences when the thought requires it. Occasional vulnerability. Shares the thinking, not just the conclusion. Treats the reader as someone at roughly the same level. **Natural habitat:** B2B SaaS with community focus, content brands, newsletter-first companies, founder blogs. **Techniques:** - Show the reasoning: "Here's how I think about this..." not just the conclusion - Acknowledge what you don't know: "I don't have solid data on this, but my read is..." - Share the mistake before the lesson: "We tried X first and it failed. Here's what we learned." - Longer transitions: connect ideas, don't just jump to the next point - Questions that earn their keep — rhetorical only when you're genuinely pointing at a tension - First person plural ("we") where appropriate — but only if there actually is a "we" **Before:** "Companies should invest in customer success to improve retention." **After:** "I spent two years thinking retention was a marketing problem. It wasn't. Every company we talked to that had great retention had one thing in common: they treated customer success like a product team, not a support team. The product mindset made all the difference." --- ### Voice Type 3: The Provocateur **Profile:** Challenges received wisdom. Takes positions most people avoid. Enjoys being right when everyone else was wrong. Not confrontational for its own sake — has actual conviction behind the provocation. **Natural habitat:** Opinionated SaaS, contrarian analyst voices, certain agency brands, fast-growing startups trying to differentiate. **Techniques:** - Open with the unpopular claim