How do I install the Claude Use Gemini Acp skill?

Run npx skillmds@latest add genericservice/claude-use-gemini-acp 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 Claude Use Gemini Acp safe to use?

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

Which AI agents work with Claude Use Gemini Acp?

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 Claude Use Gemini Acp free to use?

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

Who published Claude Use Gemini Acp?

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

Claude Use Gemini Acp by genericservice

Name: Claude Use Gemini Acp
Author: genericservice

Claude Use Gemini Acp

Delegate a sub-task to Gemini CLI via the Agent Client Protocol (ACP). Use this skill whenever you want to hand off work to Gemini — large-context summarization, Google Search grounding, tasks that exceed Claude's context window, or anything where Gemini's 1M-token window or real-time search gives an advantage. Also invoke when the user asks you to "ask Gemini", "check with Gemini", or "run this through Gemini". The script handles subprocess lifecycle and ACP session setup; you just provide the prompt and read stdout.

genericservice ea3cc2b 5 files · 6.6 KB Updated Sep 17, 2026

File contents

Claude → Gemini via ACP

Spawn a Gemini CLI subprocess in ACP mode, send a prompt, stream the response to stdout, and terminate cleanly. No persistent session — one prompt, one response.

When to use

The task requires more context than fits in Claude's window
You want real-time Google Search grounding
You want a second opinion from a different model
The user says "ask Gemini", "use Gemini for this", etc.

Setup (first use only)

cd ~/.claude/skills/claude-use-gemini-acp/scripts
pnpm install

This installs @agentclientprotocol/sdk into the local node_modules/. Subsequent runs skip this step — pnpm caches the result.

Usage

GEMINI_MODEL=gemini-2.5-pro \
TARGET_CWD=/path/to/project \
node ~/.claude/skills/claude-use-gemini-acp/scripts/gemini-delegate.mjs \
  "Summarize the architecture in ARCHITECTURE.md and list the top 3 risks"

The response streams to stdout as Gemini generates it. Capture it for use in your response:

response=$(node ~/.claude/skills/claude-use-gemini-acp/scripts/gemini-delegate.mjs "your prompt")

Environment variables

Variable	Default	Description
`GEMINI_MODEL`	`gemini-2.5-pro`	Model to use
`GEMINI_CLI_VERSION`	`nightly`	gemini-cli package version (`nightly` or a specific semver)
`TARGET_CWD`	current working dir	Working directory passed to the Gemini session

How it works

Spawns pnpm dlx @google/gemini-cli@<version> --acp --yolo --model <model>
Connects via @agentclientprotocol/sdk's ClientSideConnection + ndJsonStream
Sends initialize → newSession → prompt over the ACP session
Streams agent_message_chunk deltas to stdout as they arrive
Terminates the subprocess once the prompt response completes

The --yolo flag (-y) auto-approves all tool calls inside Gemini's session.

Prompt construction tips

Include all relevant context in the prompt string — this is a fresh session with no prior history
Reference files by absolute path if you want Gemini to read them (it can use its filesystem tools)
Keep prompts focused: one clear task per invocation
For multi-step work, do multiple sequential invocations rather than one sprawling prompt

Error handling

If the script exits non-zero, check stderr for:

pnpm dlx download failures (network, auth)
Gemini auth errors (gemini auth login may be needed)
ACP initialization failures (version mismatch)

The script does not retry — if something fails, surface the error to the user and suggest re-running after fixing the root cause.

---name: claude-use-gemini-acpdescription: Delegate a sub-task to Gemini CLI via the Agent Client Protocol (ACP). Use this skill whenever you want to hand off work to Gemini — large-context summarization, Google Search grounding, tasks that exceed Claude's context window, or anything where Gemini's 1M-token window or real-time search gives an advantage. Also invoke when the user asks you to "ask Gemini", "check with Gemini", or "run this through Gemini". The script handles subprocess lifecycle and ACP session setup; you just provide the prompt and read stdout.---# Claude → Gemini via ACPSpawn a Gemini CLI subprocess in ACP mode, send a prompt, stream the response to stdout, and terminate cleanly. No persistent session — one prompt, one response.## When to use- The task requires more context than fits in Claude's window- You want real-time Google Search grounding- You want a second opinion from a different model- The user says "ask Gemini", "use Gemini for this", etc.## Setup (first use only)```bashcd ~/.claude/skills/claude-use-gemini-acp/scriptspnpm install```This installs `@agentclientprotocol/sdk` into the local `node_modules/`. Subsequent runs skip this step — pnpm caches the result.## Usage```bashGEMINI_MODEL=gemini-2.5-pro \TARGET_CWD=/path/to/project \node ~/.claude/skills/claude-use-gemini-acp/scripts/gemini-delegate.mjs \ "Summarize the architecture in ARCHITECTURE.md and list the top 3 risks"```The response streams to stdout as Gemini generates it. Capture it for use in your response:```bashresponse=$(node ~/.claude/skills/claude-use-gemini-acp/scripts/gemini-delegate.mjs "your prompt")```## Environment variables| Variable | Default | Description ||---|---|---|| `GEMINI_MODEL` | `gemini-2.5-pro` | Model to use || `GEMINI_CLI_VERSION` | `nightly` | gemini-cli package version (`nightly` or a specific semver) || `TARGET_CWD` | current working dir | Working directory passed to the Gemini session |## How it works1. Spawns `pnpm dlx @google/gemini-cli@<version> --acp --yolo --model <model>`2. Connects via `@agentclientprotocol/sdk`'s `ClientSideConnection` + `ndJsonStream`3. Sends `initialize` → `newSession` → `prompt` over the ACP session4. Streams `agent_message_chunk` deltas to stdout as they arrive5. Terminates the subprocess once the prompt response completesThe `--yolo` flag (`-y`) auto-approves all tool calls inside Gemini's session.## Prompt construction tips- Include all relevant context in the prompt string — this is a fresh session with no prior history- Reference files by absolute path if you want Gemini to read them (it can use its filesystem tools)- Keep prompts focused: one clear task per invocation- For multi-step work, do multiple sequential invocations rather than one sprawling prompt## Error handlingIf the script exits non-zero, check stderr for:- `pnpm dlx` download failures (network, auth)- Gemini auth errors (`gemini auth login` may be needed)- ACP initialization failures (version mismatch)The script does not retry — if something fails, surface the error to the user and suggest re-running after fixing the root cause.

Frequently asked questions