Agent-Skills.md

Agent Skills: Gemini Agent SDK / Gemini Workflow Adapter

Build Gemini-backed agent workflows and adapters. Use for Google Gemini API/ADK-style runners, Gemini CLI workflow parity, tool calling, structured outputs, or adding a Gemini variant beside Cursor/OpenCode/Claude runners.

agent-sdkgeminigoogleworkflow-runner
user-invokedID: v1truv1us/ai-eng-system/gemini-agent-sdk

Repository

v1truv1us/ai-eng-system
v1truv1usLicense: MIT
73

Install this agent skill to your local

pnpm dlx add-skill https://github.com/v1truv1us/ai-eng-system/tree/HEAD/skills/gemini-agent-sdk

Skill Files

Browse the full folder contents for gemini-agent-sdk.

Download Skill

Loading file tree…

skills/gemini-agent-sdk/SKILL.md

Skill Metadata

Name
gemini-agent-sdk
Description
Build Gemini-backed agent workflows and adapters. Use for Google Gemini API/ADK-style runners, Gemini CLI workflow parity, tool calling, structured outputs, or adding a Gemini variant beside Cursor/OpenCode/Claude runners.

Default output: return only the result, blockers, and required evidence. Omit preambles, process narration, repeated context, confidence scores, and follow-up offers. Use at most five bullets unless a required artifact or schema needs more.

Gemini Agent SDK / Gemini Workflow Adapter

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.

Local references

  • 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.

Workflow adapter contract

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.

Implementation rules

  1. Use official Gemini docs for current SDK names and APIs. Do not rely on memory for package names, auth, tool-calling, or streaming semantics.
  2. Mirror the existing runner layout. Add agents/<workflow>/gemini/runner.ts or equivalent beside the other harness variants.
  3. Keep CLI packaging separate. .gemini/skills and .gemini/commands are distribution assets; SDK workflow runners are executable code.
  4. Use structured responses for machine decisions. Parse JSON for handoffs, verdicts, and next actions.
  5. Treat safety blocks as workflow states. Return blocked with the exact model/safety reason instead of retrying blindly.
  6. Verify claims outside the model. File checks, git checks, and test commands belong to deterministic runner code.
  7. Keep prompts shared. Only put Gemini-specific prompt adaptations in the Gemini adapter.

Good fits

  • Research and synthesis variants
  • Provider comparison workflows
  • Workflows where Gemini is selected by model policy

Poor fits

  • Repo mutation without a local verification harness
  • Assuming Gemini CLI skills are the same thing as a Gemini SDK runner