unslop-text

unslop-text is a skill for Claude Code from randommonicle/claude-skills. It costs 242 tokens per session (3,442 once invoked), scanned A, original, Apache-2.0.

A writing-editing skill that removes patterns often associated with AI-generated prose and leaves the wording in a deliberate human voice.

In plain words
What is it for?
Use it to revise drafts, documentation, and other prose where you want to remove assistant boilerplate, clichéd wording, and repetitive sentence patterns.
Why use it?
It helps make text sound less formulaic without imposing a fixed house style or writing the content for you.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the ash plugin — 43 skills, 3 hooks shipped together

Good fit Use it to revise drafts, documentation, and other prose where you want to remove assistant boilerplate, clichéd wording, and repetitive sentence patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/randommonicle/claude-skills/unslop-text
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add randommonicle/claude-skills --skill unslop-text
Clone the repo
git clone --depth 1 https://github.com/randommonicle/claude-skills

Made for: Claude Code.

Or install ash, the plugin that ships this one along with the rest of its 43 skills, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for unslop-text

README.md
[![agentmods](https://agentmods.dev/badge/skills/randommonicle/claude-skills/unslop-text/github.svg)](https://agentmods.dev/skills/randommonicle/claude-skills/unslop-text)
Your own site
<a href="https://agentmods.dev/skills/randommonicle/claude-skills/unslop-text"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/unslop-text/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for unslop-text

Your own site · 80×15
<a href="https://agentmods.dev/skills/randommonicle/claude-skills/unslop-text"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/unslop-text.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 242 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00242 $0.03442
Opus 5 $0.00121 $0.01721
Sonnet 5 $0.00048 $0.00688
Haiku 4.5 $0.00024 $0.00344

Measured 11d ago against content hash 2d896cc1f9b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

unslop-text scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/unslop_text_scan.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

unslop-text/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

unslop-text

Read this first, because the most common misunderstanding sinks the whole thing.

This skill does not write well for you, and it has no house style. It does two narrow things. It removes the specific cues that make text read as machine-written, and, where the text reads as AI because nobody ever chose a voice, it forces a deliberate one. Argument, taste, and what you actually want to say are still yours. A guardrail is not a writer.

Most of the work is the first thing, and most of the first thing is mechanical. This is where text differs from a website. A UI has no correct look, so its skill can only ever say "make a deliberate choice." Prose is not like that. Nearly every cited tell has a plain correct fix that needs no taste at all: the em dash becomes a comma or a period, delve into becomes look at, the sycophantic opener gets cut, the as an AI boilerplate gets deleted, the "in conclusion" recap goes. These are not style calls and there is no voice to invent. You remove the tic and write the plain sentence a person would write. So lead with the plain fix. Reserve the deliberate-voice work below for the genuinely stylistic choices, and for prose that reads as empty because nobody decided what it was.

The trap to avoid (this is the whole point)

The failure mode of every anti-AI-writing effort is replacing one default register with another. The 2024 tell was the smooth corporate voice: the em dash, "delve," "it's not just a tool, it's a partner," a bulleted list for everything, a tidy "in conclusion." The 2026 over-correction is its mirror image, the "trying not to sound like AI" voice: staccato three-word fragments, forced lowercase, a "here's the thing" or "look" cold open, a swear dropped in to seem casual, and the truly desperate move of pasting fake typos to beat a detector. People clock the second one just as fast. One auditor in the data flagged deliberately-inserted typos ("excyted," "annownce") as themselves a tell.

Treat the over-corrected register as its own tell, the way a cream-and-serif redesign is its own tell. The most common way to fail this skill is to apply its rules too hard and land in that second voice. Watch three moves in particular. Conspicuous em-dash avoidance: the fix for a dash is a comma or a period, not an ellipsis, not a colon, and not a visibly contorted sentence that bends around the gap, because the bending is as legible as the dash was. Manufactured casualness: a "honestly," a lowercase "i," a "lol" bolted onto writing that is otherwise formal reads as costume, not voice. And rhythm that is uniform in a new way: all-short sentences are as mechanical as all-medium ones. Evenness is the tell, whichever length it settles on. The over-corrected register is documented as a catalog entry in references/tells.md so the human pass checks for it by name.

Read the full file on GitHub · 217 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 217 lines · 242 tokens per session scan A 2d896cc1f9b8

Subscribe to this mod's changes

unslop-text is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 5d ago), licensed Apache-2.0. It adds 242 tokens to every session and 3,442 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens