ワンクリックで
figure
Generate a figure using Google Gemini Nano Banana 2 API based on the prompt or surrounding context.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Generate a figure using Google Gemini Nano Banana 2 API based on the prompt or surrounding context.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Find and insert citations to support a claim in the surrounding text.
Router — scan a file for <@skill: prompt> tags and dispatch each to the matching skill subagent.
Produce a revision plan for the surrounding text based on the prompt. Supports multi-turn conversation chains.
Generate and execute a visualization script for a given data file based on user instructions and context.
Apply a preceding plan/output chain to the content, then remove all tags.
Generic text edit — modify surrounding content according to the prompt.
| name | figure |
| description | Generate a figure using Google Gemini Nano Banana 2 API based on the prompt or surrounding context. |
Generate a figure from the prompt and surrounding context.
<@figure ...> tag appears.figure_system_architecture.png).<@figure> tag with a format-appropriate image reference:
.md): .tex): \includegraphics{filename.png}Requires GEMINI_API_KEY environment variable.
Run the entire generate-and-save flow in a single Bash command to avoid redundant API calls. Use single-quoted JSON with the prompt inserted via variable substitution to avoid escaping issues.
source ~/.bashrc && RESPONSE=$(curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"contents": [{
"parts": [{"text": "Generate an image: YOUR_PROMPT_HERE"}]
}],
"generationConfig": {
"responseModalities": ["TEXT", "IMAGE"]
}
}') && echo "$RESPONSE" | python -c "
import json, sys, base64
r = json.load(sys.stdin)
if 'error' in r:
print('API error: ' + r['error'].get('message', 'unknown')); sys.exit(1)
if 'candidates' not in r:
print('No candidates in response'); sys.exit(1)
for part in r['candidates'][0]['content']['parts']:
if 'inlineData' in part:
data = base64.b64decode(part['inlineData']['data'])
with open('OUTPUT_PATH.png', 'wb') as f:
f.write(data)
print(f'Saved {len(data)} bytes')
break
"
The prompt may contain context references wrapped in double backticks ( ``). These point to external resources.
<@figure: a diagram based on the architecture in ``system.md``> — read system.md for context.<@figure: pipeline diagram, save to ``figures/pipeline.png``> — save to figures/pipeline.png. delimiters from the output.GEMINI_API_KEY is not set, warn the user and skip.python (not python3) for base64 decoding. ``) in the prompt before generating.