Index of every page on this site: llms.txt
All skills
Run it yourself

Rewrites AI-sounding prose so it reads like a person wrote it, removing AI tells (em dashes, 'it's not X, it's Y', model vocabulary, stock openers) while keeping every fact. Use when the user says 'humanize this', 'de-slop', 'this sounds like AI', 'robotic', 'like ChatGPT', or 'too many em dashes', or asks why a draft feels off. For a report without a rewrite, see house-style. For matching a specific person's voice, see brand-voice. For a new post, see article.

Use this Skill: https://skilld.dev/gh/rightblogger/bloggingskills/humanize

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesexample.md

≈937 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Worked example: humanizing a slopped paragraph

One annotated rewrite, because the hard part isn't spotting a single tell, it's untangling a paragraph where they stack. Read this before a heavy de-slop.

Before (almost every sentence is a tell)

In today's rapidly evolving digital landscape, choosing the right project management tool isn't just important, it's absolutely critical. Let's dive in. The truth is simple: most teams are drowning. Not in work. Not in deadlines. In tools. Here's the kicker: the very software meant to help is quietly suffocating their productivity. Studies show that teams waste countless hours every week. It's worth noting that this is a pervasive issue. Think of it as a tax on every single thing you do. So what's the solution? A unified platform. From scrappy startups to sprawling enterprises, organizations everywhere are leveraging robust, cutting-edge solutions to streamline their workflows and unlock their team's full potential. In conclusion, the right tool can be a genuine game-changer.

What's wrong, in order of damage:

  • Banned opener ("In today's rapidly evolving digital landscape").
  • Negative parallelism and fragments ("isn't just important, it's critical"; "Not in work. Not in deadlines. In tools.").
  • Pedagogical and false-suspense filler ("Let's dive in", "Here's the kicker", "The truth is simple", "It's worth noting").
  • Magic adverbs and stakes inflation ("quietly suffocating", "absolutely critical").
  • Vague attribution and filler quantity ("Studies show", "countless hours").
  • Self-answered question ("So what's the solution? A unified platform.").
  • Patronizing analogy ("Think of it as a tax").
  • False range ("From scrappy startups to sprawling enterprises").
  • AI-ese pileup ("leveraging robust, cutting-edge solutions to streamline ... unlock ... full potential").
  • Signposted conclusion and a banned noun ("In conclusion", "game-changer").

Because most sentences are tells, this is a Scope case (Method step 6): rewrite from the argument, don't patch sentence by sentence. The argument is small and true: teams lose time to tool sprawl, and consolidating onto one platform helps.

After (same length, same claim, human)

Picking a project management tool is one of those decisions that quietly shapes how a team spends its days. Get it wrong and the cost compounds.

Most teams lose more time to their tools than to their workload. The software that promised to speed things up ends up slowing everyone down: an hour lost switching apps, another hunting for a file. Over a week that adds up, and it works like a tax on everything the team is trying to ship.

The fix is usually consolidation. Startups and large companies alike are moving their work onto one platform instead of stitching five together. When the tool fits, the hours spent switching apps come back.

What changed, and why:

  • Kept the one real idea (tool sprawl wastes time; consolidating helps) and the one concrete image (the "tax"), since that was the draft's best line. Cut only the "Think of it as" frame around it.
  • Removed every banned phrase, the false range, and the AI-ese stack.
  • Replaced "Studies show countless hours" with a concrete, honest picture ("an hour lost switching apps") instead of a fake statistic. If a real number existed it would go here; since none was given, the rewrite doesn't invent one. When a fact you need is missing, flag it to the user rather than launder it into vagueness.
  • Varied sentence openings and lengths so no rhythm repeats.

Note: "quietly" survives once, where it does real work rather than inflating. One instance is fine. The original's problem was the pile-up, not any single word.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning23d3 checks · Risk SAFE
  • Gen Agent Trust Hub23d

    The skill is safe to use. It provides stylistic guidelines and reference examples to help an AI rewrite text to sound more human. No malicious code, network activity, or unauthorized file access was detected.

  • Socket23d

    No alerts

  • Snyk23d

    Risk: MEDIUM · 1 issue

Signed by skilld at d2bfb76. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 3 days ago
metadata
{
  "version": "0.4.0"
}

README badge

README badge for rightblogger/bloggingskills/humanize