Make a canister's data queryable by the Caffeine Data Intelligence agent. Use whenever an app stores structured data (Maps/Lists/arrays of records) that should be answerable in natural language — "top customers", "revenue by region", "active projects". Adds a discoverable `schema()` and a JSON `execute()` query endpoint via the `caffeineai-oql` mops package's `Expose` mixin.
Install
npx skills add caffeinelabs/skills --skill extension-oqlnpx skills add caffeinelabs/skills --skill extension-oql -a claude-code -gnpx skills add caffeinelabs/skills --skill extension-oql -a codex -ggemini skills install https://github.com/caffeinelabs/skills.git --path skills/extension-oqlgh skill install caffeinelabs/skills extension-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-oql ~/.claude/skills/extension-oql # Claude Code
cp -R /tmp/caffeinelabs__skills/skills/extension-oql ~/.agents/skills/extension-oql # Codex, Cursor, Gemini CLI, Copilot, OpenCode