# blader/humanizer: Wikipedia Pattern Skill to Strip AI Writing Tells > Source: > Published: 2026-11-08 00:00:00+00:00 The [blader/humanizer](https://github.com/blader/humanizer?ref=explainx) repository trended on GitHub in **week 45 of 2026** and shows **about 66.2k stars** on its GitHub page as of November 8, 2026. It is not a model checkpoint. It is an **[agent skill](https://github.com/blader/humanizer/blob/main/SKILL.md?ref=explainx)** that rewrites prose using **[Wikipedia’s Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing?ref=explainx)** — the same pattern list WikiProject AI Cleanup maintains for encyclopedia editors. If you ship docs, changelogs, or blog drafts through **Claude Code** or **Codex**, Humanizer is a concrete answer to a question explainx.ai keeps hearing: **how do I keep agent output from sounding like default ChatGPT cadence** without lying to readers? ## TL;DR | Question | Answer | |---|---| | License | **MIT** (README) | | Primary source for patterns | **[Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing?ref=explainx)** | | Pattern count | **26** in README tables | | Claude Code trigger | **`/humanizer:humanizer`** (plugin path in README) | | Codex install | **`npx skills add blader/humanizer --global --agent codex`** | | Detector evasion? | **Explicitly not a goal** (README) | | Blind test claim | README cites **16/16** judge preference in issue**#229** — community report, not a peer-reviewed benchmark | ## Why GitHub is amplifying it now Trending skills usually ride a **felt pain**. explainx.ai’s [Kevin Boone piece on trusting AI web content](https://explainx.ai/blog/kevin-boone-ai-generated-web-content-trust-gutenberg-2026) documents how readers downgrade pages that read like uniform model voice. Humanizer attacks **style tells**, not factual hallucination — complementary to [harness false-alarm research](https://explainx.ai/blog/andy-hall-ai-audit-agents-false-alarms-malt-r-judge-2026) on audits. The repo README says it is **sponsored by cfo.ai**. Sponsorship does not change the skill mechanics: pattern list, rewrite pass, critique pass, final pass — all described in open **`SKILL.md`**. Compared with [benjitaylor/skills Stageshow](https://explainx.ai/blog/benjitaylor-skills-stageshow-faux-product-ui-agent-skill-react-github-trending-guide-2026) or [claude-animated-shorts](https://explainx.ai/blog/claude-animated-shorts-remotion-threejs-agent-skill-github-trending-guide-2026), Humanizer is **text-only** and **editorial**. It fits next to [jakubkrehel skills for UI](https://explainx.ai/blog/jakubkrehel-skills-better-interface-14-agent-skills-ui-typography-accessibility-github-trending-guide-2026) in a growing **skills marketplace** pattern explainx.ai tracks in [what are agent skills](https://explainx.ai/blog/what-are-agent-skills-complete-guide). ## The before/after the README proves The README’s launch example is a **shared drafts** feature announcement. Before text stacks **Not X but Y**, emoji rockets, **“Let that sink in.”**, and inflated significance. After text states **what shipped**, **what it cost in files**, and **pricing** in plain declarative sentences. That example is marketing prose, but the same patterns show up in **internal RFCs**, **support macros**, and **agent-generated PR descriptions**. Humanizer is aimed at those defaults. ## The five patterns it edits on sight Rounded page with a pen and green spark, matching prose cleanup in agent workflows The README ranks patterns by strength. The top five: 1. **Not X but Y** — “It is not just a feature, it is a shift.” 2. **One-line closers** — dramatic fragments after every section. 3. **Sayings that sound deep** — faux philosophy instead of claims. 4. **Staged run-ups** — “Here is the thing” before the fact. 5. **Arguing with nobody** — straw objections nobody raised. Patterns marked **weak alone** need **clusters** before a rewrite — the README warns careful human writers may use any one deliberately. ## Full pattern map (high level) The README groups all **26 patterns** into six families: | Family | Examples | |---|---| | **A. Staging instead of stating** | Patterns 1–5 above | | **B. Rhythm by rule** | Forced triads, repeated openings, dash spam | | **C. Inflation and borrowed authority** | “Delve,” “testament,” vague associations, fake expert consensus | | **D. Formatting by rule** | Bold decoration, emoji headings | | **E. Chat and draft leftovers** | “Great question!” wrappers, knowledge-limit disclaimers | | **F. Wrong reader** | Re-explaining what the audience already knows | Each row in the README includes **before** and **after** micro-examples — useful when you tune your own **style guides** for agents. ## How the skill runs (workflow) From **`SKILL.md`** and the README: 1. **Mark tells** in the incoming text, strongest first. 2. **Draft** a rewrite without treating the original outline as sacred. 3. **Critique** the draft for remaining tells and factual drift. 4. **Ship** final prose; for files, change**prose only** and leave code, data, frontmatter, and link targets alone. When you paste text interactively, the skill shows **first draft, critique, final** — transparency that helps humans learn patterns, not only outsource editing. **Voice matching:** paste **2–3 paragraphs of your own writing** and Humanizer will mimic rhythm and punctuation quirks, including dashes if your sample uses them. ## Installation paths (copy from README) **Claude Code (plugin):** ``` /plugin marketplace add blader/humanizer /plugin install humanizer@humanizer ``` Requires **Claude Code 2.1.142+** per README; older clients fall back to Skills CLI. **Codex and multi-agent:** ``` npx skills add blader/humanizer --global --agent codex ``` **Every agent the CLI knows:** ``` npx skills add blader/humanizer --global --agent '*' ``` **Claude.ai / Desktop:** download ZIP and upload as a skill in settings — README path for non-CLI users. For install hygiene, mirror checks from [ECC affaan-m harness skills](https://explainx.ai/blog/ecc-affaan-m-agent-harness-71-agents-311-skills-install-risks-github-trending-guide-2026): read **`SKILL.md`**, verify licenses, and know what network calls your agent may still make outside the skill. ## What developers are saying on Hacker News An older HN thread on Humanizer (**item 47109489**) is mostly normative, not benchmark-heavy. Commenter [davydm](https://news.ycombinator.com/item?id=47109503&ref=explainx) called it “another step in the war” they would not champion — a values objection to polishing AI prose. [wps](https://news.ycombinator.com/item?id=47109803&ref=explainx) lamented that automated polish drains meaning from writing. Those reactions are **not** hands-on throughput numbers; they warn that **humanizer culture** can collide with authenticity goals. Use the skill when **clarity** is the goal, not when **voice** is the product. ## Limits you should plan for The README is explicit: - **Detectors** may still flag output — do not use it for academic integrity evasion. - **Facts** must not be invented — it should**ask** when a rewrite needs missing data. - **Technical reference** stays neutral; personal essays keep quirks. Humanizer does not replace [citation checking](https://explainx.ai/blog/how-to-read-hugging-face-model-card-2026)-style discipline or legal review for regulated copy. Keep a human editor on the hook for numbers that appear only once in a draft — pattern stripping does not catch invented statistics. ## Pattern deep dive — inflation and borrowed authority Patterns **12–18** in the README are where enterprise blogs fail reviews. The README calls out overused tokens such as **“delve,” “testament,”** and **“landscape,”** plus **inflated significance** lines like **“marking a pivotal moment.”** Enterprise risk teams increasingly grep for those words after compliance incidents. Pattern **17 — borrowed authority** is especially toxic in B2B copy: **“Experts believe”** without naming an expert, or a **logo wall** of outlets with no linked study. Humanizer’s fix is blunt: **name a real source or delete the claim.** That aligns with explainx.ai’s guidance in [how to read model cards](https://explainx.ai/blog/how-to-read-hugging-face-model-card-2026) — citations must point somewhere inspectable. Pattern **18** swaps **“serves as / features / boasts”** for plain **“is / has.”** It sounds trivial; it removes an entire class of **press-release passive voice** agents love. ## Pattern deep dive — formatting and chat leftovers Patterns **19–25** catch **bold decoration**, **emoji headings**, and **chatbot residue** such as **“Great question!”** wrappers. Those lines often survive multi-agent pipelines when one model drafts and another formats. Pattern **25 — writing about the document** shows up in agent PRs: **“This function was added to replace…”** Humanizer pushes the model to describe **behavior**, not **diff meta**. ## Using Humanizer inside a daily agent loop A practical loop for doc teams: 1. **Draft** with your coding agent under a normal system prompt. 2. **Run**`/humanizer` on paragraphs that face customers or regulators — not on every code comment. 3. **Diff** the prose-only changes; reject any fact edits you did not authorize. 4. **Run** your existing**style linter** and**legal review** — Humanizer is not compliance. If you orchestrate with [loop engineering patterns](https://explainx.ai/blog/loop-engineering-coding-agents-claude-code-guide-2026), add Humanizer as an **optional pass** after factual QA, not before technical QA. Order matters: humanizing hallucinations just produces **polite hallucinations**. ## Comparison — what Humanizer does not replace | Tool or habit | Humanizer overlap | |---|---| | Manual copy edit | Overlaps — Humanizer automates pattern removal | | [AI verification tax](https://explainx.ai/blog/ai-verification-tax-rework-sage-workday-foxit-surveys-how-to-cut-it-2026) workflows | Complements — still need fact checks | | Plagiarism or rights scanners | No overlap | | [Claude Security scans](https://explainx.ai/blog/claude-mythos-5-security-scans-defender-advantage-fund-august-2026) | No overlap — security not voice | | Custom `SKILL.md` voice guides | Can combine — feed your samples for voice match | ## Wikipedia maintenance context Pen tracing a wavy line from stacked letters, echoing Wikipedia’s Signs of AI writing editorial guide WikiProject AI Cleanup does not maintain Humanizer, but both lean on the same [Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing?ref=explainx) page. Editors remove slop from articles; Humanizer removes slop from drafts **before** you paste into CMS tools. That shared origin is a feature: when your comms team asks “why does this read like ChatGPT,” you can point to a **public pattern list** instead of taste arguments. It also means when Wikipedia updates the guide, skill authors may need to **merge upstream pattern changes** — watch the repo CHANGELOG. ## Sponsorship and supply chain The README discloses **cfo.ai** sponsorship. Sponsorship does not change the MIT license or the Wikipedia attribution. Still follow normal supply-chain hygiene from [ECC skills install guidance](https://explainx.ai/blog/ecc-affaan-m-agent-harness-71-agents-311-skills-install-risks-github-trending-guide-2026): read **`SKILL.md`**, check plugin marketplace signatures, and pin versions in team docs. ## Ethics for teams If you edit customer-facing text: - Disclose **AI assistance** where your policy requires it — rewriting does not remove machine origin. - Keep **human review** on numbers, security claims, and comparisons. - Do not use Humanizer to **launder** plagiarized or scraped content — pattern stripping is not rights clearance. ## Related reading *Star counts and install commands match the blader/humanizer README as of November 8, 2026.*