agentleFS
Sign inStart free
CodeWithBehnamCodeWithBehnam/cc-docs/skills/content-research/native-web-search/SKILL.md

native-web-search

Skill2 starsChanged 8 months agoMITView on GitHub

Trigger native web search. Use when you need quick internet research with concise summaries and full source URLs.

  • Installs packages

4 other projects use a version of this, 4 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 4 are common, 0 are distinctive, and 2 are very specific to this project.

  • 4

    Common

    Most of the 4 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Common:

    Use this skill to run a fast model with native web search enabled and get a concise research summary with explicit full URLs.

    line 8
  2. Common:

    Run from this skill directory:

    line 16
  3. Common:

    search the internet for the requested topic

    line 39
  4. Common:

    No extra npm install is required.

    line 46
  5. Very specific:

    If module resolution fails, set PI_AI_MODULE_PATH to @mariozechner/pi-ai's dist/index.js path.

    line 47
  6. Very specific:

    If OAuth helper resolution fails, set PI_AI_OAUTH_MODULE_PATH to @mariozechner/pi-ai's dist/oauth.js path.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 4 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

Native Web Search

Use this skill to run a fast model with native web search enabled and get a concise research summary with explicit full URLs.

Script

  • search.mjs

Usage

Run from this skill directory:

node search.mjs "<what to search>" --purpose "<why you need this>"

Examples:

node search.mjs "latest python release" --purpose "update dependency notes"
node search.mjs "vite 7 breaking changes" --purpose "prepare migration checklist"

Optional flags:

  • --provider openai-codex|anthropic
  • --model <model-id>
  • --timeout <ms>
  • --json

Output expectations

The script instructs the model to:

  • search the internet for the requested topic
  • provide a concise summary for the given purpose
  • include full canonical URLs (https://...) for each key finding
  • highlight disagreements between sources

Notes

  • No extra npm install is required.
  • If module resolution fails, set PI_AI_MODULE_PATH to @mariozechner/pi-ai's dist/index.js path.
  • If OAuth helper resolution fails, set PI_AI_OAUTH_MODULE_PATH to @mariozechner/pi-ai's dist/oauth.js path.
  • For OAuth providers, the script can fall back to a still-valid cached access token from ~/.pi/agent/auth.json.

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