seo-agentic
Inspect how a website can be read and used by browsing agents. Use for agent readiness, accessibility trees, discovery files or…
Set up an SEO task by choosing an outcome and checking available evidence. Use for onboarding the SEO plugin.
$ npx -y skills add agricidaniel/chatgpt-seo --skill get-started --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/get-startedContext preview
The summary Claude sees to decide when to auto-load this skill.
Set up an SEO task by choosing an outcome and checking available evidence. Use for onboarding the SEO plugin.
name: get-started description: "Set up an SEO task by choosing an outcome and checking available evidence. Use for onboarding the SEO plugin." license: MIT
The user's desired SEO outcome and any URL, draft or export already supplied.
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](../../references/operating-contract.md) when this workflow is selected. Use [runtime and data paths](../../references/runtime-and-data.md) when choosing a tool or handling missing data. Recheck relevant [search facts and primary sources](../../references/current-search-facts.md) before date-sensitive claims. For a quantitative diagnostic, read [scoring](../../references/scoring.md); unavailable categories stay unknown.
1. Explain in one sentence that the plugin turns supplied or accessible evidence into a practical SEO plan. 2. If a concrete task and input are already present, start the matching workflow immediately. Do not force an onboarding questionnaire. 3. Otherwise ask one question: what site, page, draft or dataset should we work on? Offer site audit, page improvement, content brief or export diagnosis as examples. 4. Check available browsing, file and execution tools, then describe only the capabilities relevant to this task. 5. For an unavailable account source, offer the applicable export path. Do not request API keys, install runtimes or alter connections. 6. Start with evidence and state the scope. Publisher details can be given if requested; onboarding does not solicit contact information.
A concrete first task or a single useful intake question, followed by immediate progress when the input is available.
No account, payment, email address or publisher contact is needed for the supplied-file workflows.
Turn a page, draft, or SEO export into a sourced fix plan inside ChatGPT. SEO-pro by Daniel Agrici brings focused SEO workflows to the conversation: inspect the evidence, explain the problem, and give you a change you can check.
Inspect how a website can be read and used by browsing agents. Use for agent readiness, accessibility trees, discovery files or…
Audit a website for SEO problems and prioritize a practical fix plan. Use for whole-site audits or a broad request to improve a…
Analyze a supplied backlink profile or verified link sample for coverage, quality, anchors and opportunities. Use for backlink…
Group keywords into useful page targets and an internal-link architecture using intent and available SERP overlap. Use for topic…
Research and draft fair comparison or alternatives pages with verifiable product facts. Use for competitor comparison page…
Create an SEO writing brief or outline from a topic, audience and available search evidence. Use for content briefs before…