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.
npx skills add Desko77/cursor-1c-skills --skill humanize-ai-textgit clone --depth 1 https://github.com/Desko77/cursor-1c-skillsWrote 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.
[](https://agentmods.dev/skills/desko77/cursor-1c-skills/humanize-ai-text)<a href="https://agentmods.dev/skills/desko77/cursor-1c-skills/humanize-ai-text"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/humanize-ai-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.
<a href="https://agentmods.dev/skills/desko77/cursor-1c-skills/humanize-ai-text"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/humanize-ai-text.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00329 | $0.05812 |
| Opus 5 | $0.00164 | $0.02906 |
| Sonnet 5 | $0.00066 | $0.01162 |
| Haiku 4.5 | $0.00033 | $0.00581 |
Grade A, and why
humanize-ai-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 6d 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.
This is a copy
86% identical to humanize-ai-text — 40 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/humanize-ai-text - переписывание AI-текста в живой стиль
Превращает текст с маркерами LLM-генерации (ровный ритм, лестница H2/H3, буллеты вместо прозы, дежурные вступления и заключения) в текст с человеческой интонацией, не теряя смысл, числа и термины.
Когда использовать
Триггерные фразы пользователя:
- "убери AI-стиль", "не как ChatGPT", "не как нейросеть"
- "перепиши по-человечески", "сделай естественно", "сделай живым"
- "убери воду", "убери штампы", "убери LLM-маркеры"
- "причеши текст", "оживи текст"
Автотриггер при анализе входного текста:
- Заголовки H2/H3 на каждый второй абзац в коротком документе.
- Буллеты с симметричной структурой и одинаковой длиной пунктов.
- Стоп-фразы из таблицы ниже ("в современном мире", "давайте погрузимся" и т.п.).
- Эмодзи-маркеры в начале пунктов (галочки, ракеты, стрелки).
- Дежурные "надеюсь, это поможет!" / "дайте знать, если есть вопросы!".
- Серия предложений одинаковой длины подряд (4+).
Режимы работы
| Режим | Триггер | Что делает |
|---|---|---|
| Inline | аргумент - произвольный текст | Переписанный текст выводится в чат |
| File | аргумент - путь к существующему .md файлу | Результат сохраняется рядом с суффиксом -human.md |
| Interactive | аргумент пустой | Спросить у пользователя текст или путь |
| Встроенный | скил вызван другим агентом как шаг задачи | Отдать ТОЛЬКО итоговый текст |
Встроенный режим - когда результат идет дальше в чужую работу: описание pull request, сообщение коммита, кусок документации. Ни черновика, ни разбора, ни резюме правок: вызывающему нужен текст, а не отчет о переписывании.
Алгоритм определения режима - как в /prompt-enhancer:
- Пустой аргумент - Interactive.
- Read удалось прочитать аргумент - File.
- Read вернул "не найден" - Inline (аргумент целиком как текст).
Технический регистр: включен по умолчанию
Сверх поиска признаков генерации скил проверяет ТЕХНИЧЕСКИЙ РЕГИСТР. Проверка включена всегда,
отключается ключом --no-technical либо словами пользователя "без проверки регистра".
What ships with it
6 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.
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.
- 6d ago First seen · 309 lines · 329 tokens per session scan A 6c93bc54a921
humanize-ai-text is a skill published in the GitHub repository Desko77/cursor-1c-skills (55 stars, last pushed 8d ago), licensed MIT. It adds 329 tokens to every session and 5,812 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to humanize-ai-text, differing in 40 lines, and is treated as a copy.
Other skills, from other repositories
composing-1c-queries
A guide for writing queries in the 1C:Enterprise query language. It covers how to select, filter, join, group, and summarize data from 1C catalogs, documents, and registers.
humanize-ai-text
A writing aid for rewriting text produced by language-model agents into a more natural human style. It keeps the original meaning, facts, numbers, and technical terms.
transcribe
A tool for turning video and audio recordings into written text, with optional speaker identification and video analysis.
1c-form-compile
A builder for managed 1C forms, the screens users work with in the 1C business-software platform. It creates the Form.xml file from a JSON description or from an object's metadata.
1c-web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses scripted actions to navigate screens, fill forms, read tables and reports, and apply filters.
lmstudio-api
A reference for controlling LM Studio through its HTTP API. LM Studio is a local app that runs downloaded AI models on your computer.