offsite
Skill0 starsChanged 30 days agoMITView on GitHub
Plan off-site reach: earned links, digital PR, partnerships, directories, social profiles and community, within search engine spam policies. Use when the user asks about "backlinks", "link building", "PR", "authority", "mentions", "directories", or how to get other sites to talk about them.
In this repository11 other files it gives its agents.
- ai-searchSkill
- content-planSkill
- croSkill
- internationalSkill
- launchSkill
- local-seoSkill
- measureSkill
- plan-applySkill
- schemaSkill
- seo-auditSkill
- setupSkill
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 10
Search engines and AI answers trust what other sites say about a business more than what it says about itself.
- Distinctive: line 38
Use private blog networks, link farms, automated comment or forum links, or expired-domain redirects.
≈ “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
Off-site reach
Search engines and AI answers trust what other sites say about a business more than what it says about itself. The work is to deserve mentions and then ask for them.
Assets worth linking to
Pick one or two the business can make better than anyone:
- data it alone has (salary ranges by sector, placement numbers, survey results), published yearly;
- a guide that answers a hard question fully (visa steps, licensing, costs);
- a free tool or calculator;
- real stories with names and photos, with consent.
Where mentions come from
| Source | How |
| Partners, clients, suppliers | a case study or "our partners" page on their site; ask |
| Industry associations, chambers of commerce | membership listings |
| Local and trade press | send the data asset or a story with a hook; answer journalist requests |
| Universities, training centres | careers and placement resources |
| Directories | the few that matter in the country and industry, same NAP everywhere |
| Social profiles | official LinkedIn, Facebook, Instagram, YouTube; link them from Organization sameAs |
| Communities | answer questions where the audience asks them; disclose who you are |
Track what was sent, to whom, and the outcome in a sheet. Follow up once.
Never
- Buy links, sell links, or trade links in bulk. Paid placements carry
rel="sponsored". - Use private blog networks, link farms, automated comment or forum links, or expired-domain redirects.
- Post as a fake customer or hide that a post comes from the business.
- Send outreach email on the owner's behalf without their yes to each message.
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.