Skip to content
Skills Library
Marketing & content · Writing

humanizer

/humanizer

Removes AI writing patterns and injects human quality (specificity, burstiness, precise emotional language) into drafted content. Includes an optional personal-brand mode (voice reference + deterministic eval gate) you can adapt to your own voice. Use when editing drafts so they don't sound like AI. NOT for generating new content, fact-checking, SEO scoring, or research.

Licence
MIT
Last repository change
08.07.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
17
Scripts
2
HTML comments
1
URLs in SKILL.md
2
Deprecation

No signals detected. Repository changed on 08.07.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 2 scripts in this package. Review them before installing, as Claude may execute them.
  • SKILL.md zawiera komentarze HTML (1). Nie widać ich w podglądzie Markdown, a model je czyta.

Scripts: scripts/eval_voice.py, tests/test_eval_voice.py

What it does and when to use it

Removes AI writing patterns and injects human quality (specificity, burstiness, precise emotional language) into drafted content. Includes an optional personal-brand mode (voice reference + deterministic eval gate) you can adapt to your own voice. Use when editing drafts so they don't sound like AI. NOT for generating new content, fact-checking, SEO scoring, or research.

Original author description

Removes AI writing patterns and injects human quality (specificity, burstiness, precise emotional language) into drafted content. Includes an optional personal-brand mode (voice reference + deterministic eval gate) you can adapt to your own voice. Use when editing drafts so they don't sound like AI. NOT for generating new content, fact-checking, SEO scoring, or research.

How it works

  1. Full routing notes
  2. Setup
  3. Brand Context Intake
  4. Personal-brand mode (example — adapt to your own voice)
  5. Phase 1: Remove AI Tells
  6. Phase 2: Inject Human Quality
  7. Output Format
  8. Rules
  9. Learning Loop (every run, automatic — do not ask first)
  10. Credits
Original SKILL.md headings · 156 lines, 1,544 words
SKILL.md preview
---
name: humanizer
version: 4.1.0
description: "Removes AI writing patterns and injects human quality (specificity, burstiness, precise emotional language) into drafted content. Includes an optional personal-brand mode (voice reference + deterministic eval gate) you can adapt to your own voice. Use when editing drafts so they don't sound like AI. NOT for generating new content, fact-checking, SEO scoring, or research."
allowed-tools:
  - Read
  - Write
  - Edit
  - Grep
  - Glob
  - AskUserQuestion
---

# Humanizer: Remove AI Patterns + Inject Human Quality

## Full routing notes

> Removes AI writing patterns and injects human quality — specificity, burstiness, and precise emotional language. Use when editing drafted content, cleaning up LinkedIn posts, product copy, or blog content so it doesn't sound like AI. Two-phase process: Phase 1 removes 33 AI tells (significance inflation, AI vocabulary, em dash overuse, contrastive negation, vague attributions, soulless structure); Phase 2 injects humanity (sentence length variation, specificity via "what kind?" technique, precise emotional language). An optional personal-brand mode (below) adapts the two phases to a specific author's voice, using a scoreable voice-schema gate and a deterministic eval harness. Do not use for generating new content from scratch, fact-checking, SEO scoring, or research. Does not use humanizer tools (gpthuman.ai, WriteHuman) — those are detectable; this skill does structural rewriting.

Two-phase editing skill. Phase 1 removes AI tells. Phase 2 injects specificity, burstiness, and emotional precision. Clean-but-generic is still a failure — both phases are required.

## Setup

Load both reference files before starting:
1. `references/patterns-reference.md` — 33 AI tell patterns with before/after examples
2. `references/specificity-techniques.md` — "What kind?" technique, 7 levers, Emotions Wheel

Both are mandatory. Do not skip either.

---

## Brand Context Intake

Before editing, identify the context. If not supplied, ask:

> "Which context is this for? (a) Personal brand — LinkedIn/X/blog, (b) Analytical deliverable (report/memo/brief), (c) Generic content"

| Context | Risk level | Quality gate |
|---------|-----------|-------------|
| Personal brand (LinkedIn/X/blog) | Highest | Use **Personal-brand mode** below (voice reference + schema gate + eval harness). Always offer 2 variations. Read-aloud test mandatory. At least one thing only the author could know. |
| Analytical deliverable (paired with a `write-report`-style caller before its humanization pass) | Highest | Match the register the document already uses — keep analytical clarity, strip generic AI texture. Zero em-dashes. Preserve evidence tags, codes, and cited numbers untouched — relocate, never delete. |
| Generic content | Standard | Run Phase 1 + Phase 2 only. No voice gate. |

---

## Personal-brand mode (example — adapt to your own voice)

When the draft is the author's own LinkedIn or X post, this mode wraps the two generic
phases with a specific voice and a scoreable gate. It only **rewrites an existing draft**;
generating a post from scratch is out of scope for this skill.

**Required inputs:** `draft` and `channel` (`linkedin` | `x`). Ask for either if missing.
Optional: `purpose`, `known_context` (facts/examples that must be preserved).

**Load, in order, before editing:**
1. `references/voice-schema.md` — a scoreable quality gate template. Fill in the "Banned
   Vocabulary" / "Forbidden Phrases" / dimension descriptions with the author's own rules,
   or use it as shipped as a reasonable generic default.
2. Any voice-reference notes the author already maintains (brand guidelines, prior
   approved posts, a style doc). If none exist yet, ask 2-3 questions about tone,
   audience, and what they never say, and note the answers for next time.

**Workflow:**
1. **Preserve meaning** — capture the core claim, audience, concrete facts, personal
   details, caveats. Mark facts that must not change. If the draft lacks enough
   factual/personal material to feel author-specific, say so under *Residual risks*
   rather than inventing details.
2. **Substance & structure** — lead with the point, cut padded intros / fake balance /
   list symmetry that does not serve the argument. LinkedIn keeps a considered prose
   rhythm unless clearly tactical; X compresses to one idea per tweet.
3. **Voice & humanize** — run Phase 1 + Phase 2 below, then apply the author's voice
   rules from step 1: precise, direct, evidence-first; confident but not certain; no
   corporate-polish theater, no generic AI commentary, no fake certainty; no em-dashes
   if that's one of their rules.
4. **Score & gate** — score the output against `references/voice-schema.md`. When
   editing files/fixtures, run the deterministic harness:
   ```bash
   python scripts/eval_voice.py fixtures --format markdown
   ```
   If not run, state that the scorecard is manual-only.
5. **Capture feedback** — on approve/reject/manual-edit, save before/after to
   `fixtures/before-after/` (approved), `fixtures/aiish/` (rejected), or `fixtures/gold/`
   (strong published). This builds a calibration set over time — don't rely on chat
   history alone.

**Output:** Revised Draft (2 variations) · Scorecard (vs schema) · Deterministic-check
summary · Change notes · Residual risks · Publishability verdict. Never publish or send
on the author's behalf — drafts are review inputs for a human.

---

## Phase 1: Remove AI Tells

Load `references/patterns-reference.md`. Scan for all 33 patterns. Rewrite each flagged section.

**Priority flags** (most common, fix first):
- **Em dashes (—):** Do a mechanical character search for U+2014 before anything else. Every instance outside a code block must be replaced. This is not optional and not stylistic — em dashes are one of the strongest AI detection signals and must be eliminated completely from prose. Replace with: comma (asides), period (strong breaks), colon (heading label-separators). Zero exceptions outside code blocks.
- AI tell-words: delve, unpack, leverage, tapestry, landscape, pivotal, comprehensive, robust, seamless, furthermore, moreover, genuine, genuinely, "it's worth noting," "this underscores"
- **2025-26 cluster** (the delve-era words are fading; these replaced them): unlock, elevate, holistic, nuanced, resonate, align, transformative, dynamic, empower, streamline, harness, paramount, meticulous
- **Contrastive negation** ("It's not just X, it's Y" / "not merely... but...") — the strongest 2025-26 tell. Delete the negated clause, state the claim directly.
- **Self-answered rhetorical questions** ("Why does this matter? Because...") — merge into one declarative
- **Theatrical transitions:** "Here's the thing:", "The result?", "Let's break it down:", "But here's the kicker:", "Ultimately,"
- **"Aims to" / "seeks to" openers** ("This article aims to explore...") — just start with the claim
- Fake citations: "research shows," "experts say," "studies suggest" without a named source
- Significance inflation: "marks a pivotal moment," "enduring testament," "evolving landscape"
- Copula avoidance: "serves as," "stands as," "functions as" → replace with "is"/"are"
- Sycophantic artifacts: "Great question!", "I hope this helps!", "Let me know if..."

---

## Phase 2: Inject Human Quality

Load `references/specificity-techniques.md`. Run all four injection passes:

**Pass 1 — Burstiness**
Find 3+ consecutive sentences of similar length. Break one up or combine two. Target: mix of short punchy sentences (6–8 words) and longer ones. Low burstiness is the strongest AI detection signal.

**Pass 2 — Specificity injection**
For every key claim: ask "what kind?" three times. If the noun or verb can't answer "what kind?", it's not earning its place. Apply the 7 specificity levers (see reference file). Move the content from V1–V2 specificity to V3–V4.

**Pass 3 — Emotional precision**
Find every emotional or evaluative word (good, bad, frustrated, excited, important, effective). Apply the Emotions Wheel: replace with the precise emotion. "I felt bad" → "I felt embarrassed" or "I felt resentful" — each tells a different story.

**Pass 4 — Read-aloud test**
Read the output aloud. Anywhere you stumble or the words feel unnatural in your mouth — fix those. This catches what pattern-matching misses.

---

## Output Format

1. The rewritten text
2. Brief change summary: which patterns removed (Phase 1) + which injections made (Phase 2)

For personal brand context: deliver 2 variations unless the user explicitly asks for one.

---

## Rules

- Load both reference files — mandatory, not optional
- **Em dash search is the first action in Phase 1.** Search for `—` (U+2014) before reading for other patterns. Replace every instance outside a code block. Do not proceed until the count is zero.
- Never deliver Phase 1 only — clean-but-generic is still a failure
- Never do surface-level word substitution — fix the underlying claim, not just the word
- Never add chatbot artifacts to output ("Here is the revised text", "I hope this helps")
- Ask for brand context if not supplied — quality gates differ
- Personal brand: 2 variations by default
- When a noun/verb can't answer "what kind?", flag it explicitly — don't silently substitute
- Humanizer tools (gpthuman.ai etc.) are now detectable — never recommend them

## Learning Loop (every run, automatic — do not ask first)

Run at the end of EVERY invocation. These are low-risk reversible writes; do them, then mention them in one line of the output.

- **If the user approves the output** — save the before/after pair to `fixtures/before-after/` (personal-brand mode) or as an example in `references/patterns-reference.md` under "Saved Examples" (generic mode)
- **If the user rejects the output as still AI-ish** — save it to `fixtures/aiish/` and append a dated entry to `references/learnings.md` (What Has Failed) naming which pattern survived the pass
- **If the user identifies a new pattern** — add it to `references/patterns-reference.md` as the next numbered pattern, same turn
- **If the user says "never do X again"** — add it to the Rules section above and note it in the relevant reference file
- **If the user corrects a specific mistake** — update the relevant pattern's description to prevent recurrence, and log the correction in `references/learnings.md`
- **If the run surfaced nothing** (clean pass, no user reaction yet) — skip silently; no empty entries

---

## Credits

Phase 1 pattern taxonomy originally based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) guide via [github.com/blader/humanizer](https://github.com/blader/humanizer) (MIT licensed). This version extends it with Phase 2 (specificity/burstiness/emotional-precision injection), a personal-brand mode, and a deterministic eval harness.

<!-- Built with Agent Engineer Master — get your own production-ready skill: www.agentengineermaster.com/skill-engineer -->
Files in this package (17)
  • README.md 9 KB
  • SKILL.md 11 KB
  • WARP.md 3 KB
  • evals/evals.json 5 KB
  • evals/judge.md 2 KB
  • evals/rubric.md 4 KB
  • fixtures/aiish/linkedin_aiish.json 1 KB
  • fixtures/before-after/simple_rewrite.json 1 KB
  • fixtures/gold/linkedin_clean.json 1 KB
  • references/edge-cases.md 1 KB
  • references/learnings.md 1 KB
  • references/patterns-reference.md 27 KB
  • references/specificity-techniques.md 7 KB
  • references/voice-schema-rubric.md 1 KB
  • references/voice-schema.md 4 KB
  • scripts/eval_voice.py 7 KB
  • tests/test_eval_voice.py 2 KB

Versions

RepositoryScoreLicence
This page · Agent-Engineer-Master/skill-engineer100MIT
technologyHu/write_wechat_article100MIT
ocha-dap/topo-tools-py100MIT
dotnetdreamer/open-screenshot-generator100MIT
dkarter/dotfiles100MIT
event4u-app/agent-config100MIT
aeondave/malskill100MIT
helx0071/skillsmo100MIT
cowork-os/cowork-os100MIT

Database snapshot: 13.11.2026 · package version 87884c62cb2b (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100humanizer-remove-ai-writing-patterns
    Remove AI writing patterns and add human voice to any text. Use when the user says "humanize this", "make it sound human", "remove AI patterns", "this sounds like AI", "make it natural", "de-slop this", "edit for voice", or when reviewing any drafted text (blog posts, emails,…
  • 95agentic-humanizer
    Humanizes AI text in English and six other languages with a five-pass rewrite workflow, optional voice matching, and Slop or Not Pro scoring when available. Use for /agentic-humanizer.
  • 95agentic-humanizer
    Humanizes AI-generated text with a 5-pass rewrite workflow in English and six other languages, optional saved preferences, and optional stylometric voice matching from a writing sample. Works without Slop or Not. When Slop or Not Pro is reachable, adds on-device AI detector…
  • 95humanizer-he
    Remove AI-generated writing patterns from Modern Hebrew (עברית מודרנית) text. Use when editing or reviewing Hebrew text to make it sound naturally human-written.
  • 100content-humanizer
    Use this skill when the user wants to make AI-generated or stiff content sound more human, natural, specific, clear, and brand-aligned. Trigger phrases include "humanize this," "make this sound less AI," "remove AI tone," "make this more natural," "rewrite for human readers,"…
  • 100ai-humanizer
    Makes AI writing sound like YOU, not a chatbot. Learns your voice from 3–5 samples, rewrites drafts to remove the 2026 AI tells (phrases like "this matters", "rather than simply", "not just X but Y", reflex lists of three, not only em dashes), and gives you a paste-ready prompt…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.