Projects
Here are some of the key solutions and projects I’ve developed to solve real-world business challenges.
Status: Under active development
ClawBot is an Agentic Ops manager built on OpenClaw. It orchestrates a crew of specialist agents behind a single MCP gateway to run weekly SEO audits, daily OSINT monitoring, real‑time support, and automatic KB gap closure. It can also onboard new e‑shops and keep Drupal/Hugo content in sync.
Highlights:
- Unified MCP gateway with 20+ tools (RAG CMS, SEO crawler, OSINT, Sales)
- Scheduled ops: weekly SEO, daily OSINT, daily support gap review
- CMS/RAG integration: Drupal content + knowledge base updates
- Automation: background tasks, reminders, and canvas previews
- Dockerized stack; works locally or in CI
Source: https://github.com/siva01c/clawbot
Status: Under active development
A curated set of Claude plugins and examples that wire conversational AI into developer and ops workflows.
Scope:
- Web automation helpers and scraping patterns
- API integration scaffolds and best practices
- Local developer utilities for faster iteration
Source: https://github.com/siva01c/claude-plugins
The client has a content management system for multiple websites. Article authors previously had to manually fill in the SEO title and description, make corrections, search for synonyms, translate text, and perform other text-related tasks.
I proposed and developed AI assistants that perform specific operations with a single click of a button. This helped authors write articles faster and with higher quality. Thanks to this solution, it became possible to autofill SEO data, check grammar, translate text, and perform other text operations defined in the button’s prompt.
The client has a system for managing content on multiple websites. The system contains hundreds of thousands of articles, and the client wanted to remove outdated SEO content. The SEO content consisted of paragraphs with different headers and different links.
I created an export of all articles for a certain subscriber. Then I used OpenRefine to find and refine articles containing SEO content. After that, I created a .csv file with a list of affected articles. This .csv file was used as a data source for a custom form, which created queue items for the affected articles. Then I created a custom module that processed the queue and automatically removed or modified the SEO content in each article based on defined rules.
Authors of articles had to find images on photostock websites. They had to search for images, download them, and upload them to the CMS.
I wrote a custom module that allows authors to search for images on photostock websites directly from the CMS. The module uses the photostock API to search for images and display them in a modal window. Authors can select images and insert them into the article by single click. In the background, the module downloads, crops, and uploads the images to S3.
Authors are now able to find and use images on the same page where they write the article. This automated process has also great benefits for the image licence management.
The client has an e-shop with tens of products. All products were listed on product comparison tools Heureka.cz and Zbozi.cz. There were also PPC ads for each product. Managing the price strategy and ads involved a lot of manual work.
I created a system for monitoring product prices and an algorithm to adjust e-shop prices according to trends and e-shop requirements. In the next step, I created automated PPC ads with dynamic descriptions and current product prices.
