Quick reference for the Caffeine Data Intelligence agent to query an OQL-exposing canister (schema() + execute()) through the `icp` CLI against the project's `backend` canister: read the schema, form JSON queries (filter / order / paginate / aggregate / dotted-path edges), and parse the Candid result rows.
Install
npx skills add caffeinelabs/skills --skill extension-querying-oqlnpx skills add caffeinelabs/skills --skill extension-querying-oql -a claude-code -gnpx skills add caffeinelabs/skills --skill extension-querying-oql -a codex -ggemini skills install https://github.com/caffeinelabs/skills.git --path skills/extension-querying-oqlgh skill install caffeinelabs/skills extension-querying-oqlgit clone --depth 1 https://github.com/caffeinelabs/skills /tmp/caffeinelabs__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/caffeinelabs__skills/skills/extension-querying-oql ~/.claude/skills/extension-querying-oql # Claude Code
cp -R /tmp/caffeinelabs__skills/skills/extension-querying-oql ~/.agents/skills/extension-querying-oql # Codex, Cursor, Gemini CLI, Copilot, OpenCode