agentleFS
baofeng-techbaofeng-tech/agent-skills-so/aisa-youtube-serp-scout/SKILL.md

aisa-youtube-serp-scout

Skill0 starsChanged 7 months agoMITView on GitHub

Search YouTube videos, channels, and trends through the AIsa YouTube SERP client. Use when the user asks for content research, competitor tracking, or trend discovery without managing Google credentials. Use when: the user needs YouTube search, trend discovery, channel research, or SERP analysis.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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. Distinctive:

    Search YouTube videos, channels, and trends through the AIsa relay for content research, competitor tracking, and trend discovery.

    line 19
  2. Very specific:

    Search videos, channels, and playlists with q

    line 58
  3. Distinctive:

    Run competitor and top-video research from the bundled Python client

    line 61
  4. Distinctive:

    Do not ask for Google credentials or browser cookies.

    line 65
  5. Distinctive:

    Do not claim competitor analysis succeeded before the client returns data.

    line 66
  6. Distinctive:

    Do not assume missing locale values when the user needs a specific market.

    line 67
  7. Very specific:

    All search requests go to api.aisa.one.

    line 71

≈ “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

AIsa YouTube SERP Scout

Search YouTube videos, channels, and trends through the AIsa relay for content research, competitor tracking, and trend discovery.

When to use

  • The user wants YouTube content research, channel discovery, or trend monitoring.
  • The workflow benefits from a bundled Python client for repeated searches.
  • The task can use AISA_API_KEY instead of direct Google API credentials.

When NOT to use

  • The user needs browser automation, local scraping, or account-level YouTube actions.
  • The workflow must avoid sending search requests to api.aisa.one.
  • The request depends on files outside this package.

Quick Reference

  • Required environment variable: AISA_API_KEY
  • Endpoint: https://api.aisa.one/apis/v1/youtube/search
  • Python client: scripts/youtube_client.py

Setup

export AISA_API_KEY="your-key"

Common Commands

curl "https://api.aisa.one/apis/v1/youtube/search?engine=youtube&q=AI+agents+tutorial" \
  -H "Authorization: Bearer $AISA_API_KEY"

python3 scripts/youtube_client.py search --query "AI agents tutorial"
python3 scripts/youtube_client.py search --query "machine learning" --country us
python3 scripts/youtube_client.py competitor --name "OpenAI" --topic "GPT tutorial"

Capabilities

  • Search videos, channels, and playlists with q
  • Filter by country with gl and language with hl
  • Reuse sp tokens for pagination or SERP narrowing
  • Run competitor and top-video research from the bundled Python client

Guardrails

  • Do not ask for Google credentials or browser cookies.
  • Do not claim competitor analysis succeeded before the client returns data.
  • Do not assume missing locale values when the user needs a specific market.

Security Notes

  • All search requests go to api.aisa.one.
  • Required secret: AISA_API_KEY.
  • This package does not include browser automation, local scraping, or account actions.

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.