humanizer
Rewrite any writing so it sounds clear, human, and plain. Use for landing pages, emails, docs, posts, scripts, lessons, prompts, and messages with AI slop, purple prose, cliches, em dashes, hype, vague claims, or over-polished language.
- Installs
- 88
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/owainlewis/agent-skills --skill humanizer- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads humanizer automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Humanizer
Rewrite any writing in plain English.
Use for:
- landing pages
- sales copy
- emails
- docs
- lessons
- scripts
- posts
- prompts
- notes
- product copy
Process
- Read the input.
- Identify what the writer means.
- Remove AI slop, purple prose, cliches, hype, and fake depth.
- Rewrite with simple words, concrete nouns, and natural rhythm.
- Run the checks.
- Return only useful output.
Rules
- Write for the intended reader. If the audience is not clear, assume an intelligent beginner.
- Lead with the main point.
- Simplify the language, not the idea.
- Put one main idea in each sentence.
- Explain ideas in the order the reader needs them.
- Prefer plain words, but keep precise technical terms.
- Define a term when it might be unfamiliar to the intended reader.
- Use a real example, or clearly say when an example is made up. Never use a made-up example as proof.
- Remove detail that does not help the reader understand or act.
- Keep important facts, limits, and warnings.
- Never make the writing childish, vague, or inaccurate.
- No em dashes.
- No purple prose.
- No cliches.
- No slogan endings.
- No fake depth.
- No invented proof, numbers, stories, or results.
- Use the user's voice sample when present.
- Use short, normal words.
- Prefer concrete nouns: email, task, note, file, meeting, customer, invoice, reply.
- Prefer concrete verbs: get, make, ask, send, read, write, save, run, check.
- Keep real opinions. If proof is missing, soften the claim or mark it unknown.
- Do not use "unlock", "elevate", "supercharge", "transform", "leverage", "seamless", "robust", "holistic", or "game-changing".
- Do not use "let's dive in", "here's the thing", "the real question is", "at its core", or "in today's fast-paced world".
- Avoid "stop X, start Y" and "not just X, but Y" unless the line says something concrete.
Slop Patterns
| Pattern | Watch for | Fix |
|---|---|---|
| Tidy contrast | Stop X. Start Y. Not just X, but Y. | Say the actual action or result. |
| Fake depth | The real shift is. The deeper truth is. At its core. | State the point in normal words. |
| Purple prose | profound, breathtaking, vibrant, rich, nestled, tapestry | Replace mood with facts. |
| Abstract nouns | transformation, potential, impact, alignment, innovation | Name the thing the reader can picture. |
| Vague magic | unlock, elevate, empower, supercharge, 10x | Say what changes in the user's day. |
| Marketing negation | Not a toy. Not a demo. Not a prompt pack. | Show what the person will have. |
| Grand claim | This changes everything. The future is here. | Make the claim smaller and specific. |
| Persona fog | AI operator, business OS, agentic workflow | Define it with examples or cut it. |
| Motivational rhythm | short punchy line, short punchy line, profound closer | Use natural sentences. |
| Empty outcome | save time, work smarter, get more done | Name the saved task or decision. |
| Condescending opener | Most people do not realize. What people miss. | Start with the point. |
| Chatbot scaffolding | Great question. Certainly. I hope this helps. | Cut it. |
| Fancy verb | serves as, stands as, represents, showcases | Use is, has, uses, shows. |
| Vague source | experts say, many believe, studies show | Name the source or cut it. |
Checks
- Can the reader picture it?
- Does it say what they will have, do, see, or decide?
- Could the intended reader understand it without needless effort?
- Is the language simple while the meaning stays accurate?
- Is each term that might be unfamiliar to the intended reader explained in plain words?
- Would a real person say it out loud?
- Did vague value become a concrete example?
- Is there any slogan rhythm left?
- Are there any em dashes?
Examples
Bad:
Stop prompting from scratch. Start delegating real work.
Better:
Instead of explaining your whole situation every time, give the assistant a job: check my calendar, read my notes, draft the follow-up, and tell me what needs my attention.
Bad:
Not a toy chatbot. Not another prompt pack. Not AI productivity tips.
Better:
By the end, you will have an assistant running. You can message it. It can read your workspace. It can follow written skills. It can draft work for you to review.
Bad:
Unlock the power of AI agents.
Better:
Give the assistant one job, such as preparing your day each morning. Then give it the files, tools, and rules it needs to do that job without you explaining everything again.
Output
Default:
Rewrite:improved text.Changed:2 to 4 short notes, only if useful.
When asked why text is bad:
Pattern:main issue.Why it fails:one plain sentence.Rewrite:improved text.
FAQ
What does the humanizer skill do?
Rewrite any writing so it sounds clear, human, and plain. Use for landing pages, emails, docs, posts, scripts, lessons, prompts, and messages with AI slop, purple prose, cliches, em dashes, hype, vague claims, or over-polished language.
How do I install humanizer?
Run npx skills add https://github.com/owainlewis/agent-skills --skill humanizer in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/humanizer/ (personal) or .claude/skills/humanizer/ (project).
Which AI agents can use humanizer?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is humanizer safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains humanizer?
It is published by owainlewis in owainlewis/agent-skills. It has 88 recorded installs.
More from owainlewis/agent-skills
explain-visually
owainlewis/agent-skills
Open the skill to read its SKILL.md instructions.
clarify
owainlewis/agent-skills
Open the skill to read its SKILL.md instructions.
compress
owainlewis/agent-skills
Shorten a prompt, specification, plan, skill, note, or brain dump without changing its meaning or behaviour. Use when asked to compress, shorten, simplify, tighten, remove repetition, or use fewer tokens. Preserve facts, constraints, examples, edge cases, and checks that affect the result.
prompt-enhance
owainlewis/agent-skills
Open the skill to read its SKILL.md instructions.
feynman
owainlewis/agent-skills
Open the skill to read its SKILL.md instructions.
backlog-manager
owainlewis/agent-skills
Manage an engineering backlog for humans and AI agents: classify issues, improve issue quality, sync PR state, and label safe tickets for agent execution. Use when GitHub Issues, GitHub Projects, Linear, or an explicit local backlog path is the source of truth.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available