agentleFS
YunghoYungho/family-doctor/general-browser-search/SKILL.md

general-browser-search

Skill2 starsChanged 8 months agoMITView on GitHub

Browse the web and search for health guidelines, authoritative sources, and up-to-date evidence. Use when the user asks for latest guidelines, evidence, authoritative sources on a health topic, or what USPSTF/CDC/WHO/NICE recommends. Triggers on \"guidelines\", \"latest evidence\", \"CDC says\", \"WHO recommends\", \"USPSTF\", \"authoritative source\".

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    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 these sources in order of priority:

    line 21
  2. Distinctive:

    Use web-search to find relevant sources:

    line 35
  3. Distinctive:

    Use webfetch to get content from the most authoritative source:

    line 46
  4. Distinctive:

    Before fetching external sources:

    line 76
  5. Distinctive:

    If user has granted session-wide consent → proceed

    line 77
  6. Distinctive:

    If not → ask: "This searches external sources.

    line 78
  7. Distinctive:

    If user declines → return local-only results

    line 79
  8. Distinctive:

    Only health-topic queries sent

    line 84
  9. Very specific:

    After successful search, write to health/References/:

    line 89

≈ “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

General Browser / Search

Browse the web to find public health guidelines, authoritative sources, and evidence-based information.

When to Use

  • User asks for "latest guidelines on X"
  • User asks what "USPSTF/CDC/WHO/NICE says" about X
  • User asks for "authoritative source" or "official recommendation"
  • User asks for "up-to-date evidence" on a health topic
  • Trigger phrases: "guidelines", "CDC", "WHO", "NICE", "recommendation", "authoritative"

Source Priority

Search these sources in order of priority:

PrioritySourceURL Pattern
1USPSTFsite:uspreventiveservicestaskforce.org
2CDCsite:cdc.gov
3WHOsite:who.int
4NICEsite:nice.org.uk
5PubMed Health / Othergeneral web

How to Execute

Step 1: Search

Use web-search to find relevant sources:

# Search for guidelines
web-search "USPSTF hypertension guidelines 2024"
web-search "CDC vaccination recommendations elderly"
web-search "WHO diabetes management guidelines 2024"

Step 2: Fetch the Top Result

Use webfetch to get content from the most authoritative source:

webfetch --url "https://www.uspreventiveservicestaskforce.org/" --format markdown

Step 3: Extract Key Information

Extract:

  • Publication date
  • Key recommendations (bullet points)
  • URL for citation
  • Source organization name

Output Format

*[Organization] Guidelines: [Topic]*
_Published: [Date]_

**Key Recommendations:**
- [Recommendation 1]
- [Recommendation 2]
- [Recommendation 3]

**Source:** [URL]

Authorization Check

Before fetching external sources:

  • If user has granted session-wide consent → proceed
  • If not → ask: "This searches external sources. Should I proceed?"
  • If user declines → return local-only results

Privacy Note

  • No PII transmitted
  • Only health-topic queries sent
  • Results stored locally in health/References/ with citation

Citation

After successful search, write to health/References/:

# External Reference: [Topic]

**Query**: [original query]
**Date**: [today]
**Source**: [organization]
**URL**: [link]

**Key Findings:**
- [Finding 1]
- [Finding 2]

---
_Source: general-browser-search_

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.