How do I install the Gemini Er skill?

Run npx skillmds@latest add graph-robots/gemini-er 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 Gemini Er 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 Gemini Er?

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 Gemini Er free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Gemini Er?

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

Gemini Er by graph-robots — Agent Skill

Name: Gemini Er
Author: graph-robots

Gemini Er

Open-vocabulary 2D object detection via the Gemini Robotics-ER API — one call returns pixel-space bounding boxes with labels and scores for a text query. Use when a workflow needs a detection box to seed segmentation (e.g. sam3.segment_box) or coarse localization without any local GPU model.

graph-robots 9f5ce47 5 files · 271.4 KB Updated Sep 17, 2026

File contents

gemini-er

API-backed 2D detection on Gemini Robotics-ER. Zero GPU. The canonical perception recipe (from the dev tree's perceive_gemini_er workflow script) is: gemini-er.detect → best box by score → sam3.segment_box on the full frame at that box → depth projection → OBB fit.

Install

uv sync --extra gemini-er    # google-genai  (pip: pip install -e ".[gemini-er]")
export GOOGLE_API_KEY=...    # or GEMINI_API_KEY

Config

Env	Meaning	Default
`GAP_GEMINI_ER_MODEL`	Gemini model name	`gemini-robotics-er-1.5-preview`
`GOOGLE_API_KEY` / `GEMINI_API_KEY`	API key (SDK default resolution)	—

Contract

gemini-er.detect(image, query) returns {"detections": [{"box": BoundingBox2D, "label": str, "score": float}]}:

box is pixel-space {x1, y1, x2, y2} (top-left → bottom-right), clamped to the image bounds. The model emits the Gemini box_2d convention ([ymin, xmin, ymax, xmax] normalized 0–1000); conversion happens here.
score defaults to 1.0 when the model reports none — callers select the best detection with max(..., key=score).
No match (or unparseable model output) → empty detections, never an error. Treat empty as "object not visible".

When to use

Detection boxes for open-vocabulary prompts, no local weights.
Prefer molmo.point_prompt when a single click point is enough, and vlm.query_yes_no for semantic checks without localization.

---name: gemini-erdescription: Open-vocabulary 2D object detection via the Gemini Robotics-ER API — one call returns pixel-space bounding boxes with labels and scores for a text query. Use when a workflow needs a detection box to seed segmentation (e.g. sam3.segment_box) or coarse localization without any local GPU model.license: MIT---# gemini-erAPI-backed 2D detection on Gemini Robotics-ER. Zero GPU. The canonicalperception recipe (from the dev tree's `perceive_gemini_er` workflow script)is: `gemini-er.detect` → best box by `score` → `sam3.segment_box` on the fullframe at that box → depth projection → OBB fit.## Install```bashuv sync --extra gemini-er # google-genai (pip: pip install -e ".[gemini-er]")export GOOGLE_API_KEY=... # or GEMINI_API_KEY```## Config| Env | Meaning | Default ||-----------------------|------------------------------------------|----------------------------------|| `GAP_GEMINI_ER_MODEL` | Gemini model name | `gemini-robotics-er-1.5-preview` || `GOOGLE_API_KEY` / `GEMINI_API_KEY` | API key (SDK default resolution) | — |## Contract`gemini-er.detect(image, query)` returns`{"detections": [{"box": BoundingBox2D, "label": str, "score": float}]}`:- `box` is pixel-space `{x1, y1, x2, y2}` (top-left → bottom-right), clamped to the image bounds. The model emits the Gemini `box_2d` convention (`[ymin, xmin, ymax, xmax]` normalized 0–1000); conversion happens here.- `score` defaults to 1.0 when the model reports none — callers select the best detection with `max(..., key=score)`.- No match (or unparseable model output) → empty `detections`, never an error. Treat empty as "object not visible".## When to use- Detection boxes for open-vocabulary prompts, no local weights.- Prefer `molmo.point_prompt` when a single click point is enough, and `vlm.query_yes_no` for semantic checks without localization.

Frequently asked questions