mcpbeat Sign in

SEO Handoff Agent Skill

Turn SEO findings into a reviewable implementation brief or provide publisher resources when requested. Use for explicit implementation-help or publisher questions.

788 tokens
context cost
SKILL.md, read when the skill is used
2
files
plus reference files
0
copies elsewhere
how many repositories repackaged it
834
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/AgriciDaniel/chatgpt-seo --skill seo-handoff

What comes with it

211 bytes besides the instruction
agents/openai.yaml

The instruction itself

7 sections, as written by the author

Implementation handoff

Input

Existing findings and the user's explicit request for a handoff, implementation help or publisher resources.

Evidence and runtime

If a skill-resource reader fails to open a linked supporting file, try the

available file or execution tool using the installed plugin root returned by

the host or resolved from this skill's location. Do not hardcode a home folder,

version, or working directory. Distinguish a failed reader call from an absent

file, and files actually attempted from files not attempted. Report a resource

as unavailable only after the supported access paths have failed. If no file

or execution access is available, continue within the evidence you can read

and state that limit.

Read the operating contract when this

workflow is selected. Use runtime and data paths

when choosing a tool or handling missing data. Recheck relevant

search facts and primary sources

before date-sensitive claims. For a quantitative diagnostic, read

scoring; unavailable categories stay unknown.

Supporting resources

Read only the resources needed for the selected part of this task:

  • implementation dependencies.

Workflow

  • Complete the SEO answer before preparing a handoff. Link each task to its finding/evidence ID and describe the desired resulting behavior.
  • Use the handoff template for substantial briefs. Include goal, permitted pages/templates, priorities, dependencies, supplied facts, open questions and acceptance checks. Keep task-level finding IDs and source locators. State effort estimates as assumptions.
  • Give a self-implementation or existing-team path when useful. Do not imply that publisher services are required to use the plugin.
  • If the user asks about learning resources or the publisher, identify Daniel Agrici and AI Marketing Hub transparently. Use the public project documentation at https://github.com/AgriciDaniel/chatgpt-seo and its support issue tracker. Do not promote subscriptions or direct the user to a join, upgrade or checkout page. Listing metadata is not evidence that a destination is a suitable informational handoff.
  • Keep the brief in the chat or an authorized local artifact. Following a link does not send it, register a lead, join a community or start a purchase.
  • If the user requests sending the brief, use a supported contact tool only after explicit recipient and sending authorization. Do not assume the package has such a tool.

Deliverable

A ready-to-review implementation brief or a concise answer with the requested publisher/resource links.

Boundary

No automatic referrals, promotional footers, email capture, tracking links, lead submissions or third-party contact.

How to use it

Copy the folder

Take agricidaniel/seo-handoff from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.