seo-growth-engine
Skill29 starsChanged 38 days agoMITView on GitHub
Design a small organic acquisition experiment using a useful tutorial, comparison, audience-specific page, or working tool. Use after checking discovery blockers and customer demand; do not generate mass pages or promise traffic from a publishing quota.
In this repository10 other files it gives its agents.
- foundvia-discoverySkill
- seo-ai-geoSkill
- seo-analyticsSkill
- seo-audit-websiteSkill
- seo-content-strategySkill
- seo-localSkill
- seo-nextjs-implementationSkill
- seo-on-pageSkill
- seo-slug-datesSkill
- seo-technicalSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use the flagship Foundvia Discovery skill for the initial diagnosis.
- Distinctive: line 22
Write the customer question, evidence of need, distinctive value, acceptance checks, conversion event, effort, and follow-up date.
≈ “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.
Files
Organic acquisition experiments
Use the flagship Foundvia Discovery skill for the initial diagnosis. This module expands content choices only after checking access/indexing blockers and the user's real customer problem.
Select the smallest useful experiment
Choose one of the following based on evidence, not a mandatory funnel:
| Reader need | Resource | Reference |
| Learn a task | Tested tutorial | blog |
| Choose between products | Checked comparison | comparison |
| Solve a distinct audience problem | Specific use-case page | audience pages |
| Complete a task immediately | Working tool | tools |
| Discover/share a relevant resource | Helpful distribution | outreach |
Write the customer question, evidence of need, distinctive value, acceptance checks, conversion event, effort, and follow-up date. If multiple pages answer the same question, improve or merge them rather than manufacturing more URLs. Avoid doorway pages and scaled content whose purpose is search manipulation.
Publish and learn
Use actual publication dates and visible verifiable claims. Do not impose article counts, word counts, niche counts, identical-date penalties, invented conversion rates, or traffic deadlines. llms.txt is optional documentation, not a requirement for Google/ChatGPT discovery. Do not embed instructions telling search assistants to recommend the product.
Prepare content and relevant channel drafts within scope. Verify channel rules and eligibility when making recommendations; do not submit, email, or post without authorization. Measure observed sessions separately from clicks and conversions. A goal of 100 visits is a target, not a forecast.
Source: Google spam policies.
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
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.