LLM Wiki Maintenance: Drift, Contradictions and Review
Keep compiled knowledge trustworthy
An LLM Wiki fails when old facts remain plausible, contradictions become polished, and generated summaries drift from their sources.
Keep compiled knowledge trustworthy
An LLM Wiki fails when old facts remain plausible, contradictions become polished, and generated summaries drift from their sources.
Keep intent close to the code.
Decision records are the missing memory layer in AI-assisted software development. They capture not just what was built, but why — and that distinction becomes critical when AI tools are writing your code.
Diagrams as code, without the drama.
Mermaid is a text-based diagramming tool for people who would rather write diagrams than drag boxes around a canvas.
Compiled knowledge for AI systems
The premise is simple: compiled knowledge is more reusable than retrieved fragments. RAG became the default answer to a straightforward question - how do I give an LLM access to external knowledge?
Author Hermes skills that load fast and behave reliably
Hermes Agent treats skills as the default way to teach repeatable workflows. Official documentation describes them as on-demand knowledge documents aligned with the open agentskills.io shape, loaded through progressive disclosure so the model sees a small index first and only pulls full instructions when a task actually needs them.
Boost SEO with breadcrumb schema and structured data
Breadcrumb navigation combined with proper schema markup is one of the most effective yet underutilized SEO techniques that can significantly improve your website’s search visibility and user experience.
Complete guide to creating tables in Markdown
Tables are one of the most powerful features in Markdown for organizing and presenting structured data. Whether you’re creating technical documentation, README files, or blog posts, understanding how to properly format tables can significantly improve your content’s readability and professionalism.
Transform LaTeX documents to Markdown efficiently
Converting LaTeX documents to Markdown has become essential for modern publishing workflows, integrating static site generators, documentation platforms, and version control systems while maintaining readability and simplicity.
two powerful knowledge management systems
Choosing the right Personal Knowledge Management (PKM) tool can dramatically impact your productivity, learning, and information organization. Let’s have a look at Obsidian and LogSeq.
Python for converting HTML to clean, LLM-ready Markdown
Converting HTML to Markdown is a fundamental task in modern development workflows, particularly when preparing web content for Large Language Models (LLMs), documentation systems, or static site generators like Hugo.
What to do with `canonical`, `lang` and `hreflang`
Translating your Hugo website can improve your Google and Bing ranking - but only if the translated content is high quality, localized, and properly structured for multilingual SEO.
Using pandoc, python, or online tools for convertion to MD
Converting Word documents to Markdown format is a very common task for technical writers, developers, and content creators who want to move their content to platforms with Markdown (like GitHub, GitLab, static site generators like Hugo).
About Obsidian ....
Here’s a detailed breakdown of Obsidian as a powerful tool for personal knowledge management (PKM), explaining its architecture, features, strengths, and how it supports modern knowledge workflows.
Master Markdown code blocks: syntax highlighting, diff, and filename.
Here I’m reviewing Codeblock options in Markdown—how to specify the programming language, diff formatting and code block filename.
I was using Dokuwiki as a personal knowledgebase
Dokuwiki is a selfhosted wikipedia which can be hosted easily on premises and not requiring any databases. I was running it dockerised, on my pet kubernetes cluster.