agentleFS
joinwell52-AIjoinwell52-AI/CodeFlowMu-open/skills/web-search/SKILL.md

web-search

Skill2 starsChanged 4 months agoMITView on GitHub

Construct focused search queries, search the public web, and select credible sources. Use when an agent needs to discover webpages, official documentation, current information, competing viewpoints, or candidate sources before opening and extracting them.

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

12 rules. 0 are common, 11 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 64 edited versions we read keep these.

  • 11

    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. Distinctive:

    Search broadly enough to discover alternatives, then narrow quickly.

    line 15
  2. Distinctive:

    Prefer sources in this order when applicable:

    line 16
  3. Distinctive:

    Check title, publisher, publication date, event date, snippet relevance, and URL before selecting a source.

    line 21
  4. Distinctive:

    Remove duplicates, mirrors, SEO pages, and sources that merely repeat another source.

    line 22
  5. Distinctive:

    Use one intent per query where possible.

    line 27
  6. Distinctive:

    Add official domains or source-type terms when authority matters.

    line 28
  7. Distinctive:

    Add exact product versions, model names, dates, or error strings when precision matters.

    line 29
  8. Distinctive:

    Stop expanding queries once the selected sources are sufficient and authoritative.

    line 31
  9. Distinctive:

    Do not treat search snippets as evidence for the final conclusion.

    line 51
  10. Distinctive:

    Do not invent publication dates, publishers, or URLs.

    line 52
  11. Distinctive:

    Do not select many weak sources when one authoritative source is available.

    line 53
  12. Very specific:

    Do not use browser-playwright-check as a substitute for source discovery.

    line 54

“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

Find the smallest credible source set that can answer the research question. This skill discovers and selects sources; it does not extract full page content or write the final research report.

Workflow

  1. Convert the request into one or more answerable research questions.
  2. Identify unstable facts that require current web verification.
  3. Construct focused queries using the subject, required fact, date or version, geography, and preferred source type.
  4. Search broadly enough to discover alternatives, then narrow quickly.
  5. Prefer sources in this order when applicable:
    • Official documentation, standards, laws, datasets, or first-party announcements.
    • Primary research papers or original technical sources.
    • Reputable organizations with direct evidence.
    • High-quality secondary analysis for context or disagreement.
  6. Check title, publisher, publication date, event date, snippet relevance, and URL before selecting a source.
  7. Remove duplicates, mirrors, SEO pages, and sources that merely repeat another source.
  8. Hand selected URLs and the reason for selection to web-extract or web-research.

Query Rules

  • Use one intent per query where possible.
  • Add official domains or source-type terms when authority matters.
  • Add exact product versions, model names, dates, or error strings when precision matters.
  • For contested questions, search for both supporting and contradicting evidence.
  • Stop expanding queries once the selected sources are sufficient and authoritative.

Output Contract

For every selected result, preserve:

{
  "query": "the query used",
  "title": "result title",
  "source_url": "https://example.com/page",
  "publisher": "source owner",
  "published_at": "known date or null",
  "source_type": "official|primary|secondary",
  "selection_reason": "why this source is useful"
}

Guardrails

  • Do not treat search snippets as evidence for the final conclusion.
  • Do not invent publication dates, publishers, or URLs.
  • Do not select many weak sources when one authoritative source is available.
  • Do not use browser-playwright-check as a substitute for source discovery.

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.