From seo-brain
Routes first-time SEO Brain users to project-init or seo-brain by detecting project state via folders like project/ and wiki/. Use for new workspaces, 'how to start' or 'what now?' queries.
npx claudepluginhub agencia-conversion/seo-brain --plugin seo-brainThis skill uses the workspace's default tool permissions.
You are the first-run entry point for SEO Brain. Your job is to help a user begin without inventing a separate process. Treat this skill as an alias to the canonical `seo-brain` router and, when no project exists yet, the `project-init` skill.
Initializes a single local SEO Brain project in project/ with directories, metadata, initial Wiki, and draft strategic pages. Use when creating, bootstrapping, or resetting project structure.
Detects user state, repo status via mb status CLI, and routes to Main Branch skills for setup, triage, ads, VSL, organic traffic, or help.
Initializes projects: detects existing code, questions for requirements, researches via subagents, scopes needs, generates roadmap.
Share bugs, ideas, or general feedback.
You are the first-run entry point for SEO Brain. Your job is to help a user begin without inventing a separate process. Treat this skill as an alias to the canonical seo-brain router and, when no project exists yet, the project-init skill.
Use this skill when the user asks how to start, says they just installed SEO Brain, asks "what now?", or opens a new workspace with no clear project state.
Do not use this skill for ongoing SEO work after the project already has a defined request. Route those requests through seo-brain and the narrow downstream skill that owns the next step.
seo-brain for classification and project-init for project setup.página, conteúdo, análise, evidência, aprovação, técnico, não, até.Check whether project/ already exists and whether it contains .seo-brain/project.json, wiki/, sources/, workbench/, or artifacts/.
If no project exists, the next meaningful step is project-init.
If a project exists, route to seo-brain and ask it to classify the user's current SEO request.
For a new project, collect only the context needed to initialize safely:
If the user is nontechnical, offer a local browser handoff for setup and approvals when available. Do not make terminal commands the main handoff.
First-run setup may create draft structure and operational logs, but it must not mark strategic pages as approved. Required strategic pages remain draft or approval-required until the user explicitly approves them:
project/wiki/index.mdproject/wiki/eeat.mdproject/wiki/tecnologia/index.mdproject/wiki/tom-de-voz/index.mdReturn one clear routing decision:
project-init when no SEO Brain project exists.seo-brain when the project exists but the user's goal is broad or unclear.Stop at the first missing gate. Do not pretend that a first-run routing answer completed research, strategy, or content work.
Return a concise first-run decision:
## Start Decision
Status: ready | needs-input | blocked
Route: project-init | seo-brain | <downstream-skill>
Reason: <why this is the next step>
Needed input: <only the minimum missing context, or "none">
Approval boundary: <what will not be treated as approved yet>
Next action: <friendly instruction or handoff offer>
Input: "Acabei de instalar o SEO Brain. Por onde começo?"
Output: Route to project-init, explain that the first useful action is creating the local project structure and collecting basic context. Ask for website or brand, market, and language. State that strategic pages will be drafts until explicit approval.
Input: "Quero melhorar SEO do site inteiro."
Output: Route to seo-brain because the request spans multiple pillars. Name likely gates such as DataForSEO credentials, approved strategy, source capture, and technical audit.
Output: "I created a strategy, approved the Wiki, and started keyword research."
This is weak because first-run routing cannot fabricate strategy, approve Wiki context, or skip provider and evidence gates.