agentleFS
Sign inStart free
nurmdrafinurmdrafi/pi-native/skills/web-search/SKILL.md

web-search

Skill4 starsChanged 5 days agoMITView on GitHub

Web search and URL content extraction via the Tavily CLI (tvly). SEARCH current information when no URL is known: 'search for', 'find articles about', 'what's the latest on'. EXTRACT clean markdown/text from specific URLs: 'extract', 'grab the content from', 'pull the text from', 'get the page at', 'read this webpage' — handles JavaScript-rendered pages, up to 20 URLs per call. Workflow: search → extract; --include-raw-content on a search can skip the extract step. NOT deep multi-source research reports (→ research).

  • Pipes a download into a shell

81 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use Video Generation, VLM 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.
  • huang-x-hSkill

    Video Generation

    Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.

    Also in 6 projects that use this

  • huang-x-hSkill

    VLM

    Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or create applications that combine image understanding with conversational AI. Supports image URLs and base64 encoded images for multimodal interactions.

    Also in 6 projects that use this

  • dav-niu474Skill

    gift-evaluator

    The PRIMARY tool for Spring Festival gift analysis and social interaction generation. Use this skill when users upload photos of gifts (alcohol, tea, supplements, etc.) to inquire about their value, authenticity, or how to respond socially. Integrates visual perception, market valuation, and HTML card generation.

    Also in 5 projects that use this

  • dav-niu474Skill

    Podcast Generate

    Generate podcast episodes from user-provided content or by searching the web for specified topics. If user uploads a text file/article, creates a dual-host dialogue podcast (or single-host upon request). If no content is provided, searches the web for information about the user-specified topic and generates a podcast. Duration scales with content size (3-20 minutes, ~240 chars/min). Uses z-ai-web-dev-sdk for LLM script generation and TTS audio synthesis. Outputs both a podcast script (Markdown) and a complete audio file (WAV).

    Also in 5 projects that use this

  • +1 more from huang-x-h
  • +7 more from dav-niu474

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 64 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Search already returned content via --include-raw-content → skip extract.

    line 106

“Common” is measured: kept by at least 6 in 10 of the 64 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-search (tvly)

Two verbs, one CLI: search = no URL yet, extract = have URL.

NeedCommand
Current info, no URLtvly search "query" --json
Known URL contenttvly extract "https://…" --json

Before running

tvly not on PATH → ask before install (unpinned curl | bash):

curl -fsSL https://cli.tavily.com/install.sh | bash && tvly login

On approval: install + tvly login. Declined/failed → stop, report; no retry loops.

Search

# Basic
tvly search "your query" --json

# Advanced, more results
tvly search "quantum computing" --depth advanced --max-results 10 --json

# Recent news
tvly search "AI news" --time-range week --topic news --json

# Domain-filtered
tvly search "SEC filings" --include-domains sec.gov,reuters.com --json

# Full page content (may save extract call)
tvly search "react hooks tutorial" --include-raw-content --max-results 3 --json
OptionDescription
--depthultra-fast, fast, basic (default), advanced
--max-resultsMax results 0-20 (default 5)
--topicgeneral (default), news, finance
--time-rangeday, week, month, year
--start-date / --end-dateDate bounds (YYYY-MM-DD)
--include-domains / --exclude-domainsDomain filter, comma-separated
--countryBoost country results
--include-answerAI answer (basic/advanced)
--include-raw-contentFull page content (markdown/text)
--include-images / --include-image-descriptionsImage results
--chunks-per-sourceChunks per source (advanced/fast depth only)
-o, --outputSave to file
--jsonStructured JSON

Depth: ultra-fast/fast = latency matters; basic = general; advanced = precision/specific facts.

Tips:

  • Budget: --max-results 3, stop after 2-3 searches — synthesize before searching more; extra searches add context tokens every remaining turn, rarely signal.
  • Queries <400 chars — search query, not prompt.
  • Complex queries → sub-queries.
  • Need full page text → --include-raw-content (saves extract call).
  • Stdin: echo "query" | tvly search - --json

Extract

Clean markdown/text from URLs (≤20/call).

# Single URL
tvly extract "https://example.com/article" --json

# Multiple URLs
tvly extract "https://example.com/page1" "https://example.com/page2" --json

# Query-focused (relevant chunks only)
tvly extract "https://example.com/docs" --query "authentication API" --chunks-per-source 3 --json

# JS-heavy pages
tvly extract "https://app.example.com" --extract-depth advanced --json

# Save to file
tvly extract "https://example.com/article" -o article.md
OptionDescription
--queryRerank chunks by relevance
--chunks-per-sourceChunks per URL (1-5, requires --query)
--extract-depthbasic (default) / advanced (JS-rendered)
--formatmarkdown (default) / text
--include-imagesImage URLs
--timeoutMax wait 1-60s
-o, --outputSave to file
--jsonStructured JSON

Tips:

  • basic depth first; advanced fallback when content missing.
  • --query + --chunks-per-source = relevant chunks only, not full pages.
  • Batch >20 URLs into multiple calls.
  • Search already returned content via --include-raw-content → skip extract.

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