agentleFS
Sign inStart free
ykotikykotik/cli-power-skills/skills/web-research/SKILL.md

web-research

Skill1 starsChanged 7 months agoMITView on GitHub

Use when extracting article text from news URLs or downloading video or audio with metadata

45 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use data-analysis, meeting-notes 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.
  • shanggqmSkill

    data-analysis

    数据分析技能，提供结构化的数据查询、统计分析和报告生成工作流。当用户需要查询数据库、进行数据统计分析、生成分析报告时使用。按规范输出原始数据、计算结果、Markdown报告和HTML可视化报告。

    Also in 5 projects that use this

  • claude-office-skillsSkill

    meeting-notes

    >

    Also in 4 projects that use this

  • MicrosoftSkill

    web-search

    Also in 5 projects that use this

  • kongyo2Skill

    prompt-engineering

    Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. This skill should be used when users request prompt creation, optimization, or improvement for any LLM task, or when users need help translating vague requirements into effective prompts through collaborative dialogue and iterative refinement.

    Also in 4 projects that use this

  • rogue-dev-studioSkill

    browser-automation

    Canonical browser automation and web UI verification: Playwright, agent browser CLIs, and CDP-based tooling in one playbook.

    Also in 3 projects that use this

  • JetBrainsSkill

    brand-guidelines

    Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 38 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer newspaper4k over curl + HTML parsing for article extraction — handles boilerplate removal, metadata extraction automatically

    line 87
  2. Distinctive:

    Prefer yt-dlp over browser downloads — supports 1000+ sites, can extract metadata without downloading

    line 88

“Common” is measured: kept by at least 6 in 10 of the 38 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Web Research

When to Use

  • Extracting clean article text and metadata from a news/blog URL
  • Downloading video or audio from supported sites with full metadata
  • Getting video/audio metadata without downloading the media

Tools

ToolPurposeStructured output
newspaper4kExtract article text, title, authors, date from URLsPython object (access .title, .text, .authors)
yt-dlpDownload video/audio from 1000+ sites--dump-json for metadata JSON

Patterns

Extract article text from a URL

python3 -c "
from newspaper import Article
a = Article('https://example.com/news/article')
a.download()
a.parse()
import json
print(json.dumps({'title': a.title, 'authors': a.authors, 'date': str(a.publish_date), 'text': a.text[:2000]}, indent=2))
"

Extract multiple articles

for url in "https://example.com/article1" "https://example.com/article2"; do
  python3 -c "
from newspaper import Article
import json
a = Article('$url')
a.download()
a.parse()
print(json.dumps({'url': '$url', 'title': a.title, 'text': a.text[:1000]}))
"
done

Get video metadata without downloading

yt-dlp --dump-json "https://www.youtube.com/watch?v=VIDEO_ID" | jq '{title, duration, view_count, upload_date}'

Download audio only (best quality)

yt-dlp -x --audio-format mp3 "https://www.youtube.com/watch?v=VIDEO_ID"

Download video (best quality, specific format)

yt-dlp -f "bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]" "https://www.youtube.com/watch?v=VIDEO_ID"

Download with metadata and subtitles

yt-dlp --write-info-json --write-subs --sub-langs en "https://www.youtube.com/watch?v=VIDEO_ID"

List available formats for a video

yt-dlp -F "https://www.youtube.com/watch?v=VIDEO_ID"

Pipelines

Get video metadata → query with DuckDB

yt-dlp --dump-json "https://www.youtube.com/@channel/videos" --flat-playlist | head -20 > videos.jsonl
duckdb -c "SELECT title, view_count, duration FROM read_json_auto('videos.jsonl') ORDER BY view_count DESC LIMIT 10"

Each stage: yt-dlp dumps playlist metadata as JSONL, DuckDB queries for top videos by views.

Prefer Over

  • Prefer newspaper4k over curl + HTML parsing for article extraction — handles boilerplate removal, metadata extraction automatically
  • Prefer yt-dlp over browser downloads — supports 1000+ sites, can extract metadata without downloading

Do NOT Use When

  • Need to interact with a web page (click, scroll, fill forms) — use web-crawling skill (Playwright)
  • Real-time search with the WebSearch tool available — prefer the built-in tool for conversational search
  • Downloading copyrighted content without authorization
  • Target site requires authentication — use web-crawling skill with login automation

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.

Check your setup, free