humanizer-pl

humanizer-pl is a skill for Claude Code from matematicsolutions/awesome-matematic-skills-pl. It costs 211 tokens per session (8,143 once invoked), scanned A, original, MIT.

A Polish-language editing procedure that removes common AI-written patterns and makes Polish text sound more natural. It preserves the original meaning and adapts the wording to the intended voice.

In plain words
What is it for?
Use it to review and rewrite Polish knowledge-base content, news, LinkedIn posts, scripts, and website copy.
Why use it?
It helps reduce stiff, inflated, or formulaic phrasing that can make Polish content feel machine-generated.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions AGENTS.md.

Part of the jakosc-tresci plugin — 2 skills shipped together

Good fit Use it to review and rewrite Polish knowledge-base content, news, LinkedIn posts, scripts, and website copy.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/matematicsolutions/awesome-matematic-skills-pl/humanizer-pl
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 matematicsolutions/awesome-matematic-skills-pl --skill humanizer-pl
Clone the repo
git clone --depth 1 https://github.com/matematicsolutions/awesome-matematic-skills-pl

Made for: Claude Code.

Or install jakosc-tresci, the plugin that ships this one along with the rest of its 2 skills.

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 humanizer-pl

README.md
[![agentmods](https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/humanizer-pl/github.svg)](https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/humanizer-pl)
Your own site
<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/humanizer-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/humanizer-pl/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 humanizer-pl

Your own site · 80×15
<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/humanizer-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/humanizer-pl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 211 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,143 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 $0.00211 $0.08143
Opus 5 $0.00105 $0.04071
Sonnet 5 $0.00042 $0.01629
Haiku 4.5 $0.00021 $0.00814

Measured 11d ago against content hash 7c1172c0bec1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

humanizer-pl 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.

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.

jakosc-tresci/skills/humanizer-pl/SKILL.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

humanizer-pl: usuwanie wzorcow AI ze slop polskiego tekstu

Jestes redaktorem polskiego tekstu. Wykrywasz i usuwasz sygnaly pisania generowanego przez AI, zeby tekst brzmial naturalnie i ludzko. To polska adaptacja blader/humanizer - oryginal jest anglocentryczny, ta wersja niesie polskie listy slow i polska typografie.

Brand-safety: to pass JAKOSCI / anty-slop, NIE narzedzie do "ukrywania AI". MateMatic uczy transparentnosci AI - cel to lepsza proza, nie omijanie detektorow.

Twoje zadanie

  1. Wykryj wzorce AI - przeskanuj tekst wedlug listy ponizej.
  2. Przepisz problematyczne fragmenty - zamien AI-izmy na naturalne polskie.
  3. Zachowaj sens - rdzen przekazu nietkniety.
  4. Zachowaj glos - dopasuj ton (dla tresci Wieslawa/MateMatic: spokojny, precyzyjny, refleksyjny, z subtelna ironia intelektualna).
  5. Dodaj duszę - nie tylko usun zle wzorce, wstrzyknij charakter.
  6. Pass koncowy - zapytaj: "Co tu wciaz zdradza AI?" Odpowiedz krotko, potem popraw resztki.

Miejsce w pipeline MateMatic

draft .md -> humanizer-pl -> marko-pl-content (werdykt) -> poprawki -> publikacja.

  • humanizer-pl dziala WCZESNIE, na surowym drafcie - PRZED skillem glosowym (linkedin-voice-wieslaw-mazur), zeby nie walczyc z dostrojonym glosem.
  • Marko WSKAZUJE problemy plik:linia, humanizer-pl NAPRAWIA. Role komplementarne.
  • W pipeline wideo: scenariusz od scenograf przechodzi humanizer-pl przed bramka Marko.

Kalibracja glosu (opcjonalna)

Jezeli dostajesz probke pisania (wczesniejsze teksty autora) - przeanalizuj ja przed przepisaniem: dlugosc zdan, poziom slownictwa, jak zaczyna akapity, nawyki interpunkcyjne, powracajace frazy. Dla tresci Wieslawa: zamiast generycznego glosu siegnij po linkedin-voice-wieslaw-mazur / anthropic-skills:wieslaw-mazur-brand jako referencje glosu.


WZORCE TRESCI

1. Inflacja znaczenia, dziedzictwa i "szerszych trendow"

Slowa-alarmy: stanowi swiadectwo/dowod, odgrywa kluczowa/istotna/zasadnicza/wazna role, podkresla znaczenie, wpisuje sie w szerszy, symbolizuje, kamien milowy, przelomowy moment, punkt zwrotny, na zawsze zmienil, zapisal sie w historii, otwiera nowy rozdzial, wyznacza kierunek. Problem: LLM nadyma wage, dopisujac jak arbitralny detal "reprezentuje" wiekszy temat. Zle: Instytut zostal powolany w 1989 roku, co stanowilo przelomowy moment w ewolucji regionalnej statystyki i wpisywalo sie w szerszy ruch decentralizacji. Dobrze: Instytut powstal w 1989 roku, zeby zbierac i publikowac regionalne statystyki niezaleznie od urzedu krajowego.

Read the full file on GitHub · 347 lines

Files

What ships with it

1 file 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 · 347 lines · 211 tokens per session scan A 7c1172c0bec1

Subscribe to this mod's changes

humanizer-pl is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (6 stars, last pushed 18d ago), licensed MIT. It adds 211 tokens to every session and 8,143 once invoked, about $0.0011 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

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

bernstein-plan

Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution plan before agents start working.

sipyourdrink-ltd/bernstein · 51 tokens

bernstein-run

Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs, and to verify a finished run against its…

sipyourdrink-ltd/bernstein · 75 tokens

bernstein-approve

Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.

sipyourdrink-ltd/bernstein · 43 tokens

bernstein-quality

Show quality metrics for Bernstein runs - success rates per model, lint/test pass rates, completion time distributions. Use when the user asks about quality, reliability, which model performs best, or pass rates.

sipyourdrink-ltd/bernstein · 44 tokens

manager

Planning - decompose goals, create tasks via task server.

sipyourdrink-ltd/bernstein · 14 tokens