Mikhail Larchanka

What an agent can do with the skills corpus

larchanka/skills: This repository is a collection of independent skills and tools for software development and automation. Each skill is a self-contained…

• Look up how skills implements agent, agent-skill, agent-skills, with answers cited to file and line.
• Reuse a worked example: the commit “Add proper README context and organize skills repository” (12 files · Python).
• Answer from skills's real Python source instead of memory (AI, prompts and agents).

• Where does skills handle “Add proper README context and organize skills repository”?
• How does skills implement agent?
• What does slack-cli do in skills?

Search the GitHub repository larchanka/skills with XERJ (https://hub.xerj.org/corpus/larchanka--skills).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/larchanka/skills skills && git -C skills checkout b80c28f33b0a0af8d34a465e561b81e66339c88b
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./skills --url http://127.0.0.1:9200 --prefix skills --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus larchanka--skills · AI, prompts and agents
Related corpora: agentops, controlflow, invergent-ai/surogates, alvin-reyes/better-agentic-ide
AI search and retrieval with XERJ · Case study: reference coding for agents