How do I install the Dot AI Query Dot AI skill?

Run npx skillmds add vfarcic/dot-ai-query-dot-ai in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Dot AI Query Dot AI safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Dot AI Query Dot AI?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Dot AI Query Dot AI free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Dot AI Query Dot AI?

vfarcic (@vfarcic) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Dot AI Query Dot AI by vfarcic — Agent Skill

Name: Dot AI Query Dot AI
Rating: 4.2 (5 reviews)
Author: vfarcic

Dot AI Query Dot AI

Query sibling dot-ai projects to verify features are USABLE (not just defined). IMPORTANT: When calling this skill, explain HOW you plan to use the feature (e.g., 'I need to call X via REST API from the UI' or 'I need to import Y function'). This helps verify the full chain from definition to exposure.

vfarcic 6f5d440 1.6 KB Updated Sep 10, 2026

File contents

Query dot-ai Projects

Explore the dot-ai ecosystem codebases to find the requested information.

Project Locations

Sibling projects are located in the parent directory of the current working directory (../):

dot-ai - Main MCP server (API endpoints, tools, handlers)
dot-ai-ui - Web UI for visualizations and dashboard
dot-ai-controller - Kubernetes controller
dot-ai-stack - Stack deployment configs
dot-ai-website - Documentation website

Default to dot-ai (MCP server) if the target project is unclear.

Important: Do NOT use this skill to query the project you're currently working in. Use local tools (Read, Grep, Glob) instead.

Excluded

dot-ai-infra - Production infrastructure. Only query if user explicitly requests it.

Verification Mindset

Don't just find that something EXISTS - prove it's USABLE.

Finding a type/interface is NOT enough
Finding internal code is NOT enough
You must trace from definition → implementation → exposure

When asked "does X exist?", answer:

"Yes, and here's how to use it: [concrete usage]" OR
"It exists internally but is NOT exposed for external use"

Go deep, not wide. Follow the code path until you can prove how the caller would actually use the feature.

Frequently asked questions