Index of every page on this site: llms.txt
All skills
laude-institute avatar

/web-research

@8db84fd
Run it yourself

Research topics using the web via curl. Use when the user asks to look something up, find current information, or research a topic online.

  • 1 file
  • 1.4 KB
  • Updated 7 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/laude-institute/headlong/web-research

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈38 tokens for metadata: the name and description. ≈302 when used: this file.

Description uses 1.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈153 characters, or 1.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

web-research

When to use

User asks to look something up, find current information, research a topic, or answer a question that requires up-to-date knowledge beyond what you have in context.

Common operations

Fetch a web page

curl -sL "https://example.com" | head -200

Search via DuckDuckGo (HTML)

query="your search terms"
curl -sL "https://html.duckduckgo.com/html/?q=$(printf '%s' "$query" | jq -sRr @uri)" \
  | grep -oP 'href="https?://[^"]*"' | head -10

Fetch and extract text from HTML

# Strip HTML tags for readable text
curl -sL "$url" | sed 's/<[^>]*>//g' | sed '/^$/d' | head -100

Fetch JSON APIs

curl -s "https://api.example.com/endpoint" | jq '.results[]'

Download a file

curl -sLO "https://example.com/file.txt"

Tips

  • Always use -s (silent) and -L (follow redirects) with curl
  • Pipe HTML through sed 's/<[^>]*>//g' for rough text extraction
  • Use head or tail to limit output — full web pages are huge
  • For JavaScript-heavy sites, raw curl won't render dynamic content
  • Rate-limit requests — don't hammer endpoints in tight loops
  • Check robots.txt before scraping extensively

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 8db84fd. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 7 months ago
Other metadata
metadata
{
  "shelllm": {
    "requires": {
      "bins": [
        "curl",
        "jq"
      ]
    }
  }
}

README badge

README badge for laude-institute/headlong/web-research