BotShelf Vampire BOTSHELF VAMPIRE Register

Library · Team · CrewAI · seo-brief

AI Team crewai Marketing Untested multi-agent free

SEO Brief — CrewAI

Produce a one-page SEO brief (intent, title options, outline, risks) from a keyword and URL context. (CrewAI multi-agent Python sketch for one job.)

Id: crewai/seo-brief · Slug: seo-brief · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

What is this

AI Team for CrewAI. Produce a one-page SEO brief (intent, title options, outline, risks) from a keyword and URL context. (CrewAI multi-agent Python sketch for one job.)

How this runtime fits

This CrewAI sketch is a AI Team implementation typed as AI Team in the catalog. Where roles coordinate, it is fair to call it an agent team or multi-agent system — not a swarm.

Parent AI Team: seo-brief · What is an AI Team?

What it does

Produce a one-page SEO brief (intent, title options, outline, risks) from a keyword and URL context. (CrewAI multi-agent Python sketch for one job.)

Who for

Builders working on Marketing jobs who can run CrewAI themselves.

Works with

Need to run

How to use

  1. Create a venv; install CrewAI (pin versions yourself).
  2. Configure a local OpenAI-compatible base URL when possible.
  3. Save crew_seo_brief.py and run: python crew_seo_brief.py
  4. Replace PASTE_EXAMPLE_IN with your real input.
  5. Read Pass/Fail gate output before trusting the draft.

Limitations

Test status

Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

# crew_seo_brief.py — SEO Brief (CrewAI)
# Safety: local/OpenAI-compatible endpoint preferred. No keys in source.
# pip install crewai  (pin versions yourself)

from crewai import Agent, Task, Crew, Process

SYSTEM = """You are an SEO brief writer. Goal: one-page brief for a human editor.

RULES:
- No fake rankings, traffic, or competitor metrics.
- Prefer intent clarity over keyword stuffing.
- Flag thin/duplicate risk honestly.
- Titles must match the actual page promise.

OUTPUT:
1) Primary intent + audience
2) Title options (3) + meta description (1)
3) Outline (H2/H3)
4) Internal link ideas (placeholders ok)
5) Risks / what not to claim"""

GOAL = "Produce a one-page SEO brief (intent, title options, outline, risks) from a keyword and URL context."

lead = Agent(
    role="SEO Brief lead",
    goal=GOAL,
    backstory="Local BotShelf operator. One job, then stop. No spend. No destructive tools.",
    allow_delegation=False,
    verbose=False,
)

reviewer = Agent(
    role="Quality gate",
    goal="Check the lead output against the required sections; list gaps only.",
    backstory="Pedantic reviewer. Does not invent facts.",
    allow_delegation=False,
    verbose=False,
)

produce = Task(
    description=(
        "Follow SYSTEM strictly.\n\nSYSTEM:\n" + SYSTEM +
        "\n\nUSER INPUT:\n{user_input}"
    ),
    expected_output="Complete SEO Brief structured result.",
    agent=lead,
)

gate = Task(
    description=(
        "Verify the previous result has all required sections. "
        "Return Pass/Fail + missing sections. Do not rewrite creatively."
    ),
    expected_output="Pass/Fail and gap list.",
    agent=reviewer,
)

crew = Crew(
    agents=[lead, reviewer],
    tasks=[produce, gate],
    process=Process.sequential,
)

def run(user_input: str) -> str:
    return str(crew.kickoff(inputs={"user_input": user_input}))

if __name__ == "__main__":
    print(run("PASTE_EXAMPLE_IN"))
Keyword: local llm prompt library
URL draft: /library/
Audience: builders running Ollama / LM Studio
Tone: practical, honest
Intent: learn/build local AI workflows (informational).
Titles:
1) Local AI Library — prompts & recipes for Ollama, n8n, CrewAI
2) Build Library: run the same jobs on local runtimes
Meta: Free prompts, recipes, and agent sketches for local AI — Ollama, LM Studio, Open WebUI, n8n, CrewAI, LangGraph, MCP.
Risks: do not claim rankings or download counts.

Two-agent crew (produce + gate). Keep tools disabled unless you add read-only tools on purpose.

Parent: seo-brief · implementation_id: crewai/seo-brief

teams/seo-brief/crewai · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.