From ai-eng-plugin-dev
Builds Google Gemini API/ADK-backed workflow runners alongside Cursor/OpenCode/Claude variants, with structured outputs and safety-aware tool calling.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-eng-plugin-dev:gemini-agent-sdkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when implementing a Gemini-backed runner for a workflow that also exists for Cursor, OpenCode, Claude, or OpenAI. This repo currently packages Gemini CLI skills/commands, so a Gemini workflow adapter should be added deliberately and kept compatible with the shared workflow contract.
Use this skill when implementing a Gemini-backed runner for a workflow that also exists for Cursor, OpenCode, Claude, or OpenAI. This repo currently packages Gemini CLI skills/commands, so a Gemini workflow adapter should be added deliberately and kept compatible with the shared workflow contract.
docs/gemini-cli-setup.md documents current Gemini CLI packaging.agents/research-runner/ shows the multi-runtime runner pattern to mirror.agents/research-runner/shared/ should hold reusable prompts, templates, and output code.Shared types: agents/research-runner/shared/workflow-contract.ts (WorkflowInput, WorkflowResult, optional safetyNotes).
No Gemini runner exists yet. Add agents/research-runner/gemini/runner.ts (or a new workflow folder) implementing this contract; keep .gemini/skills as CLI distribution only.
agents/<workflow>/gemini/runner.ts or equivalent beside the other harness variants..gemini/skills and .gemini/commands are distribution assets; SDK workflow runners are executable code.blocked with the exact model/safety reason instead of retrying blindly.npx claudepluginhub p/v1truv1us-ai-eng-plugin-dev-plugins-ai-eng-plugin-devGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Reference for writing and editing skills with predictable behavior, covering invocation models, description writing, and information hierarchy.
2plugins reuse this skill
First indexed Jul 8, 2026