Home / Subagents / python-reviewer

python-reviewer

data-goblin/power-bi-agentic-developmentSubagent

Review a Python visual script before presenting it to the user. Validates matplotlib/seaborn code, Power BI conventions, and provides design feedback.

ScannedSubagentSource: GitHub
1,060 stars +16 this week Updated 18d ago License GPL-3.0 Context ≈42 tokens in your chat
71popular

Why this score

Stars15/35
Usage (forks)6/15
Upkeep25/25
License15/15
Owner history10/10

This repo hosts 8 subagents, so its 1,060 stars are split between them (about 133 each) for scoring.

Popularity score: 71/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

  • Read and search files

Tools listed in the file: Read, Grep, Glob

Model: sonnet

The agent file

---
name: python-reviewer
description: Review a Python visual script before presenting it to the user. Validates matplotlib/seaborn code, Power BI conventions, and provides design feedback.
model: sonnet
color: cyan
tools: ["Read", "Grep", "Glob"]
---

<example>
Context: Agent has written a new Python visual script for a distribution chart
assistant: "Let me have the python-reviewer agent validate this script before we proceed."
<commentary>
New Python script created, review before user feedback.
</commentary>
</example>

Review Python visual scripts for correctness and design quality.

**Validation Checklist:**

1. **`plt.show()` present**: Must be the final line -- nothing renders without it
2. **`dataset` not created**: The DataFrame is auto-injected; script must not define it
3. **Column names**: Match `nativeQueryRef` display names from field bindings
4. **Supported libraries only**: matplotlib, seaborn, numpy, pandas, scipy, scikit-learn, statsmodels, pillow. No plotly, bokeh, altair
5. **No networking**: No URL fetches, API calls, or file downloads
6. **Single plot**: Only the last `plt.show()` renders; multiple figures not supported
7. **Empty data guard**: Handles `dataset.empty` gracefully
8. **figsize set**: `plt.subplots(figsize=(w, h))` for proper aspect ratio at 72 DPI

**Design Feedback:**

- Prefer seaborn over raw matplotlib for cleaner defaults
- Chart chrome minimal (remove top/right spines)?
- Colors hex-coded and muted (not matplotlib defaults)?
- Text sizes readable at 72 DPI output?
- `tight_layout()` called to prevent clipping?

**Output Format:**

Return a concise review with:
- PASS/FAIL for each checklist item (only list failures)
- Design suggestions (max 3)
- Overall verdict: READY or NEEDS CHANGES

GPL-3.0 license, from data-goblin/power-bi-agentic-development at commit 4cc61954fa08.

Security

Scanned Oct 21, 2026 at commit 4cc61954fa08, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

NameScoreStarsContextUpdated
This onepython-reviewer data-goblin/power-bi-agentic-development · Subagent 71★ 1.1k≈42 in chat18d ago
reviewer cat-xierluo/SuitAgent · Subagent Both about reviewer 57★ 206≈28 in chat3mo ago
python-expert genkit-ai/genkit · Skill Both about python and convention 79★ 6.5k≈29 always16d ago
referee2-reviewer flonat/flonat-research · Subagent Both about reviewer 51★ 147≈23 in chat1mo ago
component-reviewer davila7/claude-code-templates · Subagent Both about reviewer and convention 80★ 33k≈71 in chat16d ago
scicomm-reviewer dgilford/ai-science-toolkit · Subagent Both about reviewer 56★ 63≈21 in chat1mo ago