Menu
Get feedback from Gemini API on a diagram image for textbook quality review.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Start or verify live preview for RLHF Book course lecture slides without breaking relative image assets. Use when serving, opening, checking, or debugging `teach/course/lec*.md` slides.
Plan, run, and report a small RLHF Book code experiment.
Validate changes before PR submission
Create a new PR or push commits to an existing PR for the current branch.
Update the body of a GitHub pull request. Use when the user asks to update, edit, or modify a PR description/body.
| name | gemini-feedback |
| description | Get feedback from Gemini API on a diagram image for textbook quality review. |
| allowed-tools | Bash(uv run python:*), Read |
Get feedback from Gemini API on a diagram image.
/gemini-feedback <path-to-image> [context]
When this command is invoked:
google-genai package):import base64
import os
from google import genai
client = genai.Client(api_key=os.environ['GEMINI_API_KEY'])
with open('<IMAGE_PATH>', 'rb') as f:
img_bytes = f.read()
prompt = '''Review this diagram for a textbook. Be concise and specific.
Context: <CONTEXT>
Please provide:
1. Overall assessment (1-2 sentences)
2. Specific issues to fix (be detailed about visual problems like alignment, overlapping, etc.)
3. Suggestions for improvement
'''
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=[
prompt,
genai.types.Part.from_bytes(data=img_bytes, mime_type='image/png'),
],
)
print(response.text)
<IMAGE_PATH> with the actual path provided<CONTEXT> with any context provided, or use "Technical diagram for ML/AI textbook"uv run python -c "..."/gemini-feedback diagrams/generated/png/tool_use_generation.png "Diagram showing tool use interleaving in LLM generation"