agentleFS
matvej-melikhovmatvej-melikhov/karpathy-llm-wiki/.claude/skills/defuddle/SKILL.md

defuddle

Skill2 starsChanged 6 months agoMITView on GitHub

Очистить веб-страницу от мусора (nav, ads, sidebar, footer) и вернуть дословный текст статьи как чистый markdown. Сохраняет картинки (как URL-ссылки) и формулы LaTeX. Используется в URL ingestion как единственный инструмент очистки. Триггеры: defuddle, clean this page, strip this url, fetch and clean, очисти страницу, выгрузи статью, читаемый markdown из URL.

  • Installs packages

70 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use results-report, wiki-fold and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Galaxy-DawnSkill

    results-report

    This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.

    Also in 3 projects that use this

  • tboome33Skill

    wiki-fold

    Roll up the wiki's journal.md entries into structured fold pages — like 2^k log compaction. Reads the last 2, 4, 8, 16... entries and writes a fold page that summarizes them by extractive summarization (no invention), with backlinks to children. Idempotent at the structural level — re-running with the same window produces a byte-equivalent fold. Use when the user says "fold the log", "rollup recent activity", "compact the log", "/wiki-fold", or after many ingestions when journal.md is becoming too long to read directly.

    Also in 3 projects that use this

  • Clay-HHKSkill

    daily-coding

    Daily coding assistant that auto-triggers when writing/modifying code, providing a core checklist.

    Also in 3 projects that use this

  • Clay-HHKSkill

    kaggle-learner

    This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.

    Also in 3 projects that use this

  • lucasmaher-hashSkill

    knap

    Render Markdown from templates and structured data using Knap CLI. Use when the user asks to apply a Knap template, turn JSON or CSV data into notes, batch-generate Markdown files, or format Defuddle output into a note.

    Also in 3 projects that use this

  • kharlamenkodevSkill

    bug-detective

    Also in 3 projects that use this

  • +1 more from Clay-HHK

The file

Files
SKILL.md

defuddle: очистка веб-страниц

defuddle — CLI-утилита (от kepano, автор Obsidian Minimal theme и Web Clipper). На базе Mozilla Readability + кастомные чистильщики.

Что делает:

  • Принимает URL или локальный HTML
  • Возвращает дословный текст статьи в markdown
  • Сохраняет: текст, заголовки, списки, таблицы, code blocks, формулы LaTeX ($...$, $$...$$), ссылки на картинки (![alt](url))
  • Удаляет: nav, sidebar, ads, cookie banners, footer, share-кнопки, related articles, скрипты, стили

Что НЕ делает: не суммаризирует, не перефразирует, не интерпретирует. Чистый strip + конвертация HTML → markdown.


Установка (зависимость проекта)

npm install -g defuddle

Проверка: defuddle --version (требуется 0.18.x или новее).

defuddle входит в обязательные зависимости проекта — без него URL ingestion не работает. Зависимость от Node.js / npm.


Использование

Очистить URL и получить markdown

defuddle parse https://example.com/article --markdown

Выводит markdown в stdout.

Сохранить в raw/articles/ с frontmatter

Полный flow для URL ingestion:

URL="https://example.com/article"
SLUG="article-slug"
DATE=$(date +%Y-%m-%d)
DEST="raw/articles/${SLUG}-${DATE}.md"

mkdir -p raw/articles
{
  echo "---"
  echo "source_url: ${URL}"
  echo "fetched: ${DATE}"
  echo "---"
  echo ""
  defuddle parse "${URL}" --markdown
} > "${DEST}"

После сохранения файл готов для synthesis workflow.

Очистить локальный HTML

defuddle parse page.html --markdown

Извлечь только метаданные

defuddle parse "${URL}" --json

Выводит JSON с полями: title, description, author, published, content. Полезно для авто-заполнения frontmatter.


Когда использовать

Да:

  • Любой URL ingestion (статья, блог-пост, документация)
  • Длинные тексты с обилием обвеса (Medium, Substack, news-сайты)
  • Когда хочется дословный текст автора, а не суммаризацию

Нет:

  • Источник уже чистый markdown или PDF
  • Страница — dashboard / SPA / структурированные данные (defuddle ожидает article-style)
  • Сайт за anti-bot защитой (defuddle не обходит CAPTCHA / JS-challenges)

Интеграция с ingest

Скилл ingest вызывает defuddle автоматически при URL ingestion. См. секцию "URL ingestion" в .claude/skills/ingest/SKILL.md.

Вручную скачать страницу и затем ingestить:

defuddle parse "${URL}" --markdown > "raw/articles/${SLUG}-$(date +%Y-%m-%d).md"
# затем:
# /ingest raw/articles/${SLUG}-${DATE}.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.