Introduction
I often see blogs that have a "Related Recommendations" section at the end of each article.
A few days ago, I used the LLM-WIKI skill, so I thought about using it to analyze my blog and add related recommendations to each post.
Approach
Save my blog pages as WIKI pages,
Use the LLM-WIKI skill to lint and analyze these pages, establishing connections between them,
Count the connection counts for all pages,
For each page, among its connected pages, find the 3 pages with the highest connection counts.
Practice
Initialize WIKI
I chatted with hermes (MIMO v2 pro 2026-4-21)
...
The entire development process involved lots of detailed design discussions, which I won't list one by one. See GitHub for details
Eventually, I got several files:
1. Page index
2. Inter-page connection list
3. Individual page connection relationships
4. Top 3 pages with highest connection counts
Processing all blog posts with semantic analysis took quite a while and lots of tokens. Luckily, hermes had a free trial for Xiaomi MIMO v2 pro at that time.
...
With the help of this tool, I manually edited my blog posts one by one, adding things like "Related Recommendations", "Recommended Reading", "Also Check Out", "See Also" at the end of each article.
:D
Friends who know coding will definitely know that there are countless ways to automatically display data like this. However, my interest isn't there, so I didn't spend more energy on it.
XD
Maintaining WIKI
Two days later, my blog had 2 new articles, and the RSS feed also had 2 new entries.
I asked hermes to summarize the previous work into a skill, then process the new RSS content. As expected, errors occurred.
Then came endless back-and-forth debugging.
btw, hermes's free Xiaomi model promotion ended, but there's a new free option: moonshotai/kimi-k2.6
Eventually, it was completed. I tested this skill under a new hermes system and applied it to another person's blog, and it worked normally.
========
End
========