Using Hermes-agent's LLM WIKI Skill to Analyze My Blog and Generate Related Recommendations

Preface

I often see some 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 the LLM-WIKI skill to analyze my blog and add related recommendations to each post as well.

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 most connections.

Practice

Initialize WIKI

I chatted with hermes (MIMO v2 pro 2026-4-21)
I'm going to do something. Help me analyze the specific plan. Don't implement it yet, let's discuss first.

There is a website
https://zelikk.blogspot.com/

This website's RSS output is full content
https://zelikk.blogspot.com/rss.xml

Use your llm-wiki skill to create a new WIKI

Ingest every article from this website into this WIKI

Lint and organize this WIKI,
and output results like these
1. For each connection in the WIKI, which page connects to which page
2. Ranking of each page's inbound connection count
inbound connection - a page is linked by other pages
3. Among the pages connected by each page's outbound connections, the 3 pages with the highest counts in list 2, and their respective counts
outbound connection - a page connects to other pages
The entire development and communication process involved many detailed designs, which I won't list one by one. See GitHub for details

Eventually got these several files
1. Page assignment index
index,page,pub_date,raw_url
1,hermes-python,2026-04-21,https://zelikk.blogspot.com/2026/04/hermes-python.html
2. Inter-page connection list
source,target
1,4
3. Individual page connection relationships
rank,index,page,degree,neighbors
1,98,xray-vless-reality-tls-x25519,47,"29|43|74|102|103|131|132|133|144|147|149|150|153|154|155|157|158|160|162|173|174|181|191|194|207|225|243|244|266|268|272|284|287|288|300|308|310|315|321|323|324|338|339|340|422|504|509"
4. Top 3 pages with the highest connection counts among pages connected to each page
index,page,top1_index,top1_page,top2_index,top2_page,top3_index,top3_page
1,hermes-python,13,hermes-agent-oracle-vps-ubuntu-root,10,hermes-agent,4,hermes-agent-telegram-group-topic-agent


Semantic analysis processing all the articles in my blog took quite a while, and a lot of tokens too. Luckily, at that time hermes had a free trial with Xiaomi MIMO v2 pro.

While hermes was busy, I used the web version of free Claude to design a single-page HTML tool.

(Upload 1. the page assignment index file page_index.csv, and 4. the file link_outbound_top3.csv containing the top 3 pages with the highest connection counts among pages connected to each page) and then say

I have these 2 data source files
I need a single HTML page file that displays the content of link_outbound_top3.csv in a different way

Taking
1,hermes-python,13,hermes-agent-oracle-vps-ubuntu-root,4,hermes-agent-telegram-group-topic-agent,10,hermes-agent
as an example of such data,
I want to look up the raw_url content in page_index.csv based on the index, to get results like this
https://zelikk.blogspot.com/2026/04/hermes-python.html
    https://zelikk.blogspot.com/2026/04/hermes-agent-oracle-vps-ubuntu-root.html
    https://zelikk.blogspot.com/2026/04/hermes-agent-telegram-group-topic-agent.html
    https://zelikk.blogspot.com/2026/04/hermes-agent.html

This display tool is also uploaded to GitHub


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 of my blog. As expected, errors occurred.
Then came endless back-and-forth debugging and fixing.

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, learned it, and then applied it to another person's blog, and it worked normally.

========

End


========

GitHub



这是我手工添加的文字, 这一篇是 moonshotai/kimi-k2.6 模型处理的

发表评论

后一页 前一页