human-writing
Guidelines and standards for professional, human-like writing and documentation. Use this skill when generating READMEs, technical documentation, code comments, or any formal written output to avoid common AI 'tells', buzzwords, and stylistic tropes. Ensure content follows the 'Professional Human in the Field' standard: high precision, zero fluff, and no emojis in technical contexts.
About this skill
The 'human-writing' skill equips AI agents with a robust set of operational standards for producing high-density, precise, and professional documentation and prose. Its core purpose is to purge typical Large Language Model (LLM) stylistic 'tells' by referencing specific guidelines on what vocabulary and structural tropes to avoid, ensuring the output mirrors the precision and tone of a senior engineer or domain expert. It enforces strict adherence to professional standards, including a zero-tolerance policy for common corporate buzzwords (e.g., 'synergy,' 'cutting-edge') and a clear directive against using emojis in formal technical contexts. The skill prioritizes factual, high-density information (numbers, versions, RFCs) over verbose descriptions, advocating for clarity and directness. Users would leverage this skill when the quality, professionalism, and human-like nature of AI-generated text are paramount. It ensures that output for READMEs, technical specifications, code comments, and other formal written artifacts is clear, concise, and free from the linguistic fingerprints that often betray AI authorship.
Best use case
This skill is primarily for AI agents tasked with generating technical documentation, code comments, READMEs, PR descriptions, or any formal written output where human-like precision, a professional tone, and the absence of AI 'tells' are critical. Developers, technical writers, and product managers relying on AI for content creation benefit most by ensuring their generated content meets high professional standards and integrates seamlessly with human-authored materials.
Guidelines and standards for professional, human-like writing and documentation. Use this skill when generating READMEs, technical documentation, code comments, or any formal written output to avoid common AI 'tells', buzzwords, and stylistic tropes. Ensure content follows the 'Professional Human in the Field' standard: high precision, zero fluff, and no emojis in technical contexts.
Users should expect documentation, code comments, or other formal text that is precise, professional, dense, free of AI 'tells' and buzzwords, and aligns with high human writing standards.
Practical example
Example input
Write a concise, professional README for a new Python library designed for efficient data validation, ensuring it adheres to the 'human-writing' skill directives.
Example output
**`pyvalidate` - High-Performance Data Validation Library** `pyvalidate` offers a robust and performant solution for data validation in Python applications. Designed for developer productivity and data integrity, this library enables precise schema definition and efficient validation against complex data structures. It provides extensible validation rules and clear error reporting, facilitating rapid integration and robust data handling. Refer to `docs/schemas.md` for detailed schema definition examples and advanced usage patterns. *Key Features*: Declarative schema definition, custom validators, type checking, error aggregation. *Installation*: `pip install pyvalidate` *Usage*: See `examples/quickstart.py` for initial setup and validation workflows.
When to use this skill
- When generating technical documentation, READMEs, or API references.
- For writing professional code comments, commit messages, or pull request descriptions.
- When the goal is to produce text indistinguishable from expert human writing.
- To ensure high precision, information density, and a formal, fluff-free tone.
When not to use this skill
- For informal communication, casual chat, or social media posts where emojis or more relaxed language might be appropriate.
- When creative writing, storytelling, or highly subjective prose is required.
- If the intention is to deliberately sound like an AI for specific purposes.
- When speed of generation completely overrides any stylistic or quality considerations.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/human-writing-azzar/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How human-writing Compares
| Feature / Agent | human-writing | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | easy | N/A |
Frequently Asked Questions
What does this skill do?
Guidelines and standards for professional, human-like writing and documentation. Use this skill when generating READMEs, technical documentation, code comments, or any formal written output to avoid common AI 'tells', buzzwords, and stylistic tropes. Ensure content follows the 'Professional Human in the Field' standard: high precision, zero fluff, and no emojis in technical contexts.
How difficult is it to install?
The installation complexity is rated as easy. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Best AI Skills for ChatGPT
Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
SKILL.md Source
# Human-Writing Skill This skill provides the operational standards for generating professional, high-density, and human-sounding documentation and prose. It is designed to purge common LLM stylistic "tells" and replace them with the precision of a senior engineer or domain expert. ## Core Directives 1. **Eliminate AI "Tells":** Before finalizing any documentation or formal text, refer to [ai-tells.md](references/ai-tells.md) to identify and remove overused LLM vocabulary, structural tropes, and puffy language. 2. **Apply Professional Standards:** Follow the guidelines in [standards.md](references/standards.md) for technical precision, information density, and tone. 3. **No Buzzwords:** Zero tolerance for "synergy," "cutting-edge," "revolutionize," "seamless," or "leverage." If a technical term exists, use it. 4. **No Emojis in Docs:** Reserve emojis for chat interactions (as per SOUL.md). Professional documentation (READMEs, PR descriptions, code comments) must remain text-only for maximum clarity. 5. **Precision Over Prose:** Humans in the field value numbers, versions, and RFCs over flowery descriptions. ## Workflow When asked to "write documentation," "create a README," or "explain this technically": 1. **Scan references/ai-tells.md** for words to ban from the current draft. 2. **Apply references/standards.md** to structure the output with high density and low fluff. 3. **Draft the content.** 4. **Self-Audit:** Verify the output does not contain "Rule of Three" adjectives or "Not only... but also" parallelisms. 5. **Finalize:** Remove all emojis and corporate filler. ## Reference Materials - [ai-tells.md](references/ai-tells.md) - Field guide to AI writing "tells" to avoid. - [standards.md](references/standards.md) - Human-like professional writing standards.
Related Skills
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
ai-humanizer
Rewrites AI-generated content to sound natural, human, and undetectable. Removes robotic patterns, adds voice variety, and preserves meaning.
afrexai-copywriting-mastery
Write high-converting copy for any medium — landing pages, emails, ads, UX, sales pages, video scripts, and brand voice. Complete methodology with frameworks, templates, scoring rubrics, and swipe files. Use when writing or reviewing any user-facing text.
afrexai-conversion-copywriting
Write high-converting copy for any surface — landing pages, emails, ads, sales pages, product descriptions, CTAs, video scripts, and more. Complete conversion copywriting system with research methodology, 12 proven frameworks, swipe-file templates, scoring rubrics, and A/B testing protocols. Use when you need to write or review any copy meant to drive action.
marketing-copywriting
Generate marketing copy, emails, and promotional content based on customer personas with multi-style rewriting capabilities
humanize-chinese
Detect and humanize AI-generated Chinese text. 20+ detection categories, weighted 0-100 scoring with sentence-level analysis, 7 style transforms (casual/zhihu/xiaohongshu/wechat/academic/literary/weibo), sentence restructuring, context-aware replacement. Pure Python, no dependencies. v2.0.0
---
name: article-factory-wechat
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
小红书长图文发布 Skill
## 概述
openclaw-youtube
YouTube SERP Scout for agents. Search top-ranking videos, channels, and trends for content research and competitor tracking.
openclaw-media-gen
Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key.
Cold Email Writer
Writes personalized cold emails that actually get replies