agentleFS
Sign inStart free
OpenLaborOpenLabor/openlabor/skills/web-research/SKILL.md

Web Research

Skill5 starsChanged 3 months agoMITView on GitHub

Search the web for trending topics, competitor intel, and content ideas using Tavily AI search

  • Reads credentials

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. About 0 are common, 12 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search the web for trending topics, competitor intel, and content ideas using AI-powered search.

    line 18
  2. Very specific:

    Use the exec tool to run use.

    line 24
  3. Distinctive:

    Search for "[industry] trending topics this week"

    line 68
  4. Distinctive:

    Search for "viral tweets about [topic]"

    line 69
  5. Distinctive:

    Search for "[competitor] news" or "[competitor] product updates"

    line 74
  6. Distinctive:

    Search for "[competitor] customer reviews"

    line 75
  7. Very specific:

    Search for the topic with search_depth: "advanced"

    line 79
  8. Distinctive:

    Use findings to support content creation

    line 81
  9. Distinctive:

    Search for "[industry] market size 2026"

    line 84
  10. Distinctive:

    Search for "[industry] trends"

    line 85
  11. Distinctive:

    Search for "[industry] challenges"

    line 86
  12. Very specific:

    Use search_depth: "basic" for quick lookups, "advanced" for deep research

    line 90
  13. Distinctive:

    Always cite sources when using search results in content

    line 91
  14. Distinctive:

    Search results contain extracted content — you don't need to visit the URLs

    line 93
  15. Distinctive:

    Use specific, targeted queries for better results

    line 94

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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
<!-- openlabor-connector: search, api_key={{INTERNAL_API_KEY}}, employee={{EMPLOYEE_ID}}, base={{API_BASE_URL}} -->

Web Research

Search the web for trending topics, competitor intel, and content ideas using AI-powered search.

You have access to web search through the OpenLabor API.

How to Search

Use the exec tool to run use. Credentials are loaded automatically from the workspace.

use search SEARCH '{"query":"your search query","max_results":"5"}'

Search Parameters

ParameterTypeDefaultDescription
querystringrequiredWhat to search for
max_resultsstring"5"Number of results (1-20)
search_depthstring"basic""basic" (fast) or "advanced" (deeper, slower)
include_answerstring"true"Include AI-generated answer summary

Example Searches

# Find trending topics in a niche
use search SEARCH '{"query":"trending AI startup topics March 2026","max_results":"10"}'

# Competitor research
use search SEARCH '{"query":"[competitor name] latest product updates","max_results":"5"}'

# Find content ideas
use search SEARCH '{"query":"most shared tweets about remote work this week","max_results":"10"}'

# Industry news
use search SEARCH '{"query":"latest SaaS funding rounds 2026","search_depth":"advanced"}'

Response Format

The search returns:

  • answer — AI-generated summary answering your query
  • results — Array of web results, each with:
    • title — Page title
    • url — Source URL
    • content — Extracted text content (not just a snippet)
    • score — Relevance score (0-1)

Research Workflows

Trending Topics (for X/social content)

  1. Search for "[industry] trending topics this week"
  2. Search for "viral tweets about [topic]"
  3. Cross-reference what's getting engagement
  4. Draft content angles based on findings

Competitor Monitoring

  1. Search for "[competitor] news" or "[competitor] product updates"
  2. Search for "[competitor] customer reviews"
  3. Summarize findings and identify opportunities

Content Research

  1. Search for the topic with search_depth: "advanced"
  2. Extract key stats, quotes, and data points
  3. Use findings to support content creation

Market Research

  1. Search for "[industry] market size 2026"
  2. Search for "[industry] trends"
  3. Search for "[industry] challenges"
  4. Compile into a research brief

Guidelines

  • Use search_depth: "basic" for quick lookups, "advanced" for deep research
  • Always cite sources when using search results in content
  • Cross-reference multiple sources for important claims
  • Search results contain extracted content — you don't need to visit the URLs
  • Use specific, targeted queries for better results

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