Skip to content

itachi-re/claude-skills / humanizer

humanizer

Verified

Rewrites or drafts prose so it reads like a person wrote it, not an LLM — strips out AI vocabulary tells (delve, boast, intricate, testament, leverage, robust, seamless), robotic structures ("not X, but Y," rule-of-three padding, dangling "-ing" clauses, fake-suspense openers, phantom attribution like "critics argue"), uniform sentence rhythm, em-dash overuse, and mechanical bold/bullet formatting — without overcorrecting into forced typos or performed quirkiness. ALWAYS consult this before finalizing any prose for a human reader: emails, texts, DMs, social posts, comments, forum replies, essays, articles, cover letters, scripts, or creative writing. Trigger by default, even if the user never says "humanize" or mentions AI detection. Does NOT apply to code, raw data/JSON, or structured technical docs where a plain register is correct.

FileKindSize
SKILL.mdskill md6.1 KB
references/banned-words.mdmarkdown2.5 KB

references/banned-words.md

View on GitHub
# AI vocabulary tells — reference list

Loaded on demand from `SKILL.md`. None of these words are banned outright — they're normal English words. The tell is *clustering*: when several of these show up in the same paragraph, or when one shows up in a context where a simpler word would do, that's the LLM accent showing. Use this list to scan a draft, not to write toward.

## Core cluster (most persistent across model generations)

additionally · boast(s) · bolstered · crucial · delve · emphasizing · enduring · garner · intricate / intricacies · interplay · key · landscape · meticulous / meticulously · pivotal · underscore · tapestry · testament · valuable · vibrant

## Newer cluster (crept in as the above got memed/flagged)

align with · enhance · fostering · highlighting · showcasing · leverage · synergy · holistic · elevate · streamline · empower · robust · seamless · scalable · innovative · transformative · game-changer · groundbreaking · cutting-edge · next-gen · frictionless · adaptive · data-driven

## Verb-y filler ("unlocking the future" energy)

unlock · harness · unleash · redefine · revolutionize · accentuate · pioneering · trailblazing · optimize

## Intensifier drift (most recent)

"quiet" / "whisper" used as a vague mood-setter ("a quiet revolution," "whispers of change")
"concrete" used reflexively as a hedge in arguments about evidence ("no concrete evidence," "provide concrete examples")

## Promotional-drift phrases

"rich cultural heritage" · "enduring legacy" · "stands as a testament to" · "plays a significant role in" · "a pivotal moment in" — these assert importance instead of demonstrating it. If the thing is actually significant, show why; don't just label it that way.

## Vague attribution phrases (phantom sourcing)

"critics argue" · "observers have noted" · "industry reports suggest" · "studies show" (with no study named) · "experts agree"

## Formulaic transitions (fine occasionally, a tell when they're the only connective tissue used)

moreover · furthermore · in addition · that said · on the other hand (overused as a default pivot rather than because a real contrast exists)

## Notes on drift over time

This list isn't static — labs tune against the most obvious tells, so the cluster shifts every few months (e.g. "delve" was extremely common in 2023–early 2024, then dropped off sharply once it became a meme). Treat this as a living list: if you notice a new word clustering in your own output that isn't here yet, add it.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall