# AI Humanizer Agent Skill > Write human-sounding X long-form posts and threads with a 24-pattern AI detector that eliminates robotic language. Publish authentic content that avoids AI slop—start free in seconds. - Canonical: https://nanoskill.ai/ru/skills/ai-humanizer-agent-skill - Markdown: https://nanoskill.ai/ru/skills/ai-humanizer-agent-skill.md - Author: ericosiu - Published: 2026-09-02T03:00:00.000Z - Updated: 2026-09-02T09:56:44.347Z - Language: ru - Source type: github - Popularity signal: 2755 ## Sources - https://github.com/ericosiu/ai-marketing-skills/tree/main/x-longform-post ## Install ```shell npx skills add https://github.com/ericosiu/ai-marketing-skills/tree/main/x-longform-post ``` ## About The AI humanizer skill for X helps marketers, founders, and thought leaders turn robotic drafts into authentic long-form posts that pass both AI detectors and audience skepticism. Instead of generic, fluff-filled threads, you get a structured, human-sounding article that feels like it was written by a real expert—because it was. The built-in 24-pattern checklist flags and fixes every telltale sign of AI writing, from overused buzzwords to vague attributions, so your content actually gets read and shared. What sets this skill apart is its focus on real publishing quality, not just grammar. It includes a proven post skeleton designed for X virality—hook, setup, problem, lesson, ASCII diagram, and uncomfortable truth. The ASCII diagram generator turns complex processes into eye-catching, monospace-friendly visuals that stop the scroll. And because voice matters, you can customize the entire output to match your personal brand by filling in a simple voice template. Typical users include solo founders sharing contrarian industry takes, marketing teams drafting threads that replace lengthy blog posts, and content creators who want to humanize AI drafts before going live. Whether you’re documenting a process, explaining a lesson learned, or building thought leadership one post at a time, this skill cuts out the editing guesswork and outputs a publication-ready long-form post in seconds. ## Key features - **24-pattern AI detector**: Instantly catch and fix AI clichés like significance inflation, negative parallelism, and banned vocabulary before you publish. - **ASCII diagram generation**: Make complex systems and workflows visual with monospace-friendly diagrams that break up text walls and boost engagement. - **Voice customization**: Match your personal brand by filling in a voice template—the skill adapts to your tone, vocabulary, and style automatically. - **Proven post skeleton**: Every draft follows a hook, setup, sections, diagram, uncomfortable truth, and payoff structure designed for X virality. ## Use cases - **Generate contrarian X articles**: Founders and marketers use the skill to turn hot takes into data-backed, scroll-stopping long-form posts that spark debate. - **Humanize AI-generated drafts**: Run any draft through the 24-pattern checklist and rewrite flagged sections—shipping only when the score hits 90+. - **Create visual explanations with ASCII diagrams**: Use built-in diagram prompts to explain pipelines, funnels, or before/after processes in a format that stands out on timelines. - **Customize voice for personal branding**: Thought leaders can clone their tone by filling in voice traits and sample posts, ensuring every output sounds unmistakably like them. ## Result preview See a polished X long-form post report with a humanizer audit log, score dashboard, and final thread you can copy and publish immediately. ![the demo of ai humanizer agent skill](https://file.nanoskill.ai/ai-humanizer-agent-skill-demo-1.png) ![the demo of ai humanizer agent skill](https://file.nanoskill.ai/ai-humanizer-agent-skill-demo-2.png) ![the demo of ai humanizer agent skill](https://file.nanoskill.ai/ai-humanizer-agent-skill-demo-3.png) ![the demo of ai humanizer agent skill](https://file.nanoskill.ai/ai-humanizer-agent-skill-demo-4.png) ## Result walkthrough ### Step 1：Install Add the skill to your agent. ![the step of ai humanizer agent skill](https://file.nanoskill.ai/ai-humanizer-agent-skill-step-1.png) ### Step 2：Describe Your Topic Share your topic, contrarian angle, and target audience — the skill generates a full X thread structure with hooks, ASCII diagrams, and key arguments. ![the step of ai humanizer agent skill](https://file.nanoskill.ai/ai-humanizer-agent-skill-step-2.png) ### Step 3：Get Your Humanized Post Receive a report with your original draft, a 24-pattern AI detection audit, before/after rewrites, a humanizer score dashboard, and a final X-ready thread. ![the step of ai humanizer agent skill](https://file.nanoskill.ai/ai-humanizer-agent-skill-step-3.png) ## Skill definition # X Long-Form Post Writer + Humanizer Write long-form X (Twitter) articles and threads that actually sound human. Includes a 24-pattern AI writing detector that catches and eliminates AI slop before you publish. Most AI-generated content dies on the timeline because it *reads* like AI. This skill fixes that by running every draft through a humanizer checklist based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI-generated_content) research. ## What It Does 1. Takes a topic + contrarian angle 2. Generates a structured long-form post with ASCII diagrams 3. Runs the 24-pattern humanizer checklist 4. Rewrites any sections that trigger AI patterns 5. Outputs a post ready to paste into X ## The Humanizer The real value here. 24 specific patterns that reveal AI-generated text: | Pattern | Example | Fix | |---------|---------|-----| | Significance inflation | "pivotal moment", "is a testament" | State the fact plainly | | Negative parallelism | "It's not X. It's Y." | Say what it IS directly | | Banned vocabulary | "leverage", "landscape", "robust" | Use normal words | | Vague attributions | "Experts believe..." | Name the expert or drop it | | Promotional language | "boasts a vibrant..." | Use specific numbers instead | | AI vocabulary clustering | 3+ banned words in one paragraph | Rewrite the paragraph | **Scoring:** Start at 100, deduct per pattern violation. Ship at 90+. Rewrite from scratch below 75. Full checklist with all 24 patterns and deduction weights in `SKILL.md`. ## Quick Start Drop `SKILL.md` into your Claude Code project: ```bash cp x-longform-post/SKILL.md your-project/.claude/skills/x-longform-post.md ``` Then ask Claude Code: - "Write an X article about why most companies waste money on brand awareness" - "Draft a thread on how I replaced my marketing team's manual reporting with AI agents" - "X post: contrarian take on why SEO isn't dead, it just changed" ## Voice Customization Default voice: direct, contrarian, data-backed. To match your personal brand: 1. Copy `references/voice-template.md` to your project 2. Fill in your voice traits, vocabulary, and a sample post 3. Reference it when generating ## Structure Every post follows this skeleton: 1. **Hook** (1-2 lines): Contrarian claim or surprising stat 2. **Setup** (2-3 lines): Quick credibility/context 3. **Sections**: Problem, what happened, lesson 4. **ASCII diagram**: At least one per post (renders in monospace on X) 5. **Uncomfortable truth**: The thing nobody wants to say 6. **Payoff**: Worth it? Yes, here's why. ## ASCII Diagrams Every post includes at least one code-block diagram. These break up text walls and make systems visual: ``` Pipeline Before: Lead → SDR → AE → Close ↓ (60% drop) Pipeline After: Lead → AI Score → Route │ │ │ ▼ ▼ ▼ Nurture SDR(top) Auto-close only (small deals) ``` ## Requirements This is a prompt-based skill (no Python dependencies). Works with any Claude Code or AI coding agent setup. ## License MIT ---
**🧠 [Want these built and managed for you? →](https://singlebrain.com/?utm_source=github&utm_medium=skill_repo&utm_campaign=ai_marketing_skills)** *This is how we build agents at [Single Brain](https://singlebrain.com/?utm_source=github&utm_medium=skill_repo&utm_campaign=ai_marketing_skills) for our clients.* [Single Grain](https://www.singlegrain.com/?utm_source=github&utm_medium=skill_repo&utm_campaign=ai_marketing_skills) · our marketing agency 📬 **[Level up your marketing with 14,000+ marketers and founders →](https://levelingup.beehiiv.com/subscribe)** *(free)*
## FAQ ### What is the AI Humanizer skill for X? It’s a Claude Code skill that writes long-form X posts and threads while running every draft through a 24-point AI detection checklist to remove robotic patterns. ### How does the humanizer work? It scans your draft for 24 specific AI writing patterns—like significance inflation or banned vocabulary—then deducts points and rewrites flagged sentences until the text sounds natural. ### What AI patterns does it detect? Patterns include overused phrases ('leverage', 'pivotal moment'), negative parallelism ('It’s not X. It’s Y.'), vague attributions, promotional language, and clustering of AI vocabulary. ### How is the AI score calculated? Start at 100 and deduct weighted points per pattern violation. Ship at 90 or above; below 75 means a full rewrite. The scoring table is in the skill file. ### Can I customize the writing voice? Yes. Copy the voice template, fill in your traits and a sample post, and reference it when generating. The skill adjusts tone, vocabulary, and style accordingly. ### Is the AI Humanizer skill free? Yes, it’s open-source under the MIT license. You can copy the skill file into any Claude Code project and start using it immediately at no cost.