Chart Generator

Chart Generator

Why this skill exists

Choosing the wrong chart type is the most common data visualization mistake. This skill picks the right chart for the data shape and produces clean, labeled, publication-quality output — not matplotlib defaults.

When to use

• User has data (CSV, JSON, or described) and wants it visualized
• User requests a specific chart type
• User wants to generate charts for a report or presentation

Step-by-step procedure

Step 1 — Pick the right chart type

| Data shape | Best chart | |---|---| | One number over time | Line chart | | Comparing categories | Bar chart (vertical) or horizontal bar | | Part-of-whole ( 5 slices — use a bar chart instead. Never use 3D charts — they distort perception.**

Step 2 — Load data

import pandas as pd
import json

# From CSV
df = pd.read_csv("/mnt/user-data/uploads/data.csv")

# From JSON
with open("/mnt/user-data/uploads/data.json") as f:
    data = json.load(f)
df = pd.DataFrame(data)

# From user-described data (build inline)
df = pd.DataFrame({
    "Month": ["Jan", "Feb", "Mar", "Apr", "May"],
    "Revenue": [12000, 15000, 13500, 18000, 21000],
})

Step 3 — Generate charts

Bar chart:

import matplotlib.pyplot as plt
import matplotlib.ticker as mticker

fig, ax = plt.subplots(figsize=(10, 6))
bars = ax.bar(df["Category"], df["Value"], color="#4F86C6", edgecolor="white", linewidth=0.5)

# Labels on bars
for bar in bars:
    height = bar.get_height()
    ax.text(bar.get_x() + bar.get_width()/2, height + 0.5,
            f"{height:,.0f}", ha="center", va="bottom", fontsize=10)

ax.set_title("Category Comparison", fontsize=16, fontweight="bold", pad=15)
ax.set_xlabel("Category", fontsize=12)
ax.set_ylabel("Value", fontsize=12)
ax.yaxis.set_major_formatter(mticker.FuncFormatter(lambda x, _: f"{x:,.0f}"))
ax.spines[["top", "right"]].set_visible(False)
ax.set_facecolor("#fafafa")
fig.tight_layout()
plt.savefig("/mnt/user-data/outputs/bar_chart.png", dpi=150, bbox_inches="tight")
plt.close()

Line chart (time series):

fig, ax = plt.subplots(figsize=(12, 6))
ax.plot(df["Date"], df["Value"], color="#2E86AB", linewidth=2.5, marker="o", markersize=5)
ax.fill_between(df["Date"], df["Value"], alpha=0.1, color="#2E86AB")

ax.set_title("Trend Over Time", fontsize=16, fontweight="bold", pad=15)
ax.set_xlabel("Date", fontsize=12)
ax.set_ylabel("Value", fontsize=12)
ax.spines[["top", "right"]].set_visible(False)
plt.xticks(rotation=45)
fig.tight_layout()
plt.savefig("/mnt/user-data/outputs/line_chart.png", dpi=150, bbox_inches="tight")
plt.close()

Scatter plot:

fig, ax = plt.subplots(figsize=(9, 7))
scatter = ax.scatter(df["x"], df["y"], c=df.get("group", "#4F86C6"),
                     alpha=0.7, s=60, edgecolors="white", linewidth=0.5)

ax.set_title("Correlation Analysis", fontsize=16, fontweight="bold", pad=15)
ax.set_xlabel("X Variable", fontsize=12)
ax.set_ylabel("Y Variable", fontsize=12)
ax.spines[["top", "right"]].set_visible(False)
fig.tight_layout()
plt.savefig("/mnt/user-data/outputs/scatter.png", dpi=150, bbox_inches="tight")
plt.close()

Heatmap (correlation matrix):

import seaborn as sns

corr = df.select_dtypes(include="number").corr()
fig, ax = plt.subplots(figsize=(10, 8))
sns.heatmap(corr, annot=True, fmt=".2f", cmap="RdYlGn",
            center=0, linewidths=0.5, ax=ax,
            annot_kws={"size": 10})
ax.set_title("Correlation Matrix", fontsize=16, fontweight="bold", pad=15)
fig.tight_layout()
plt.savefig("/mnt/user-data/outputs/heatmap.png", dpi=150, bbox_inches="tight")
plt.close()

Interactive chart with Plotly (HTML output):

import plotly.express as px

fig = px.bar(df, x="Category", y="Value", color="Group",
             title="Interactive Bar Chart",
             template="plotly_white",
             color_discrete_sequence=px.colors.qualitative.Set2)

fig.update_layout(font_family="Arial", title_font_size=18)
fig.write_html("/mnt/user-data/outputs/chart.html")
print("Interactive chart saved as HTML")

Step 4 — Multi-chart dashboard

fig, axes = plt.subplots(2, 2, figsize=(14, 10))
fig.suptitle("Data Dashboard", fontsize=18, fontweight="bold", y=1.02)

# Add each chart to a subplot
# axes[0][0] = chart 1, axes[0][1] = chart 2, etc.

plt.tight_layout()
plt.savefig("/mnt/user-data/outputs/dashboard.png", dpi=150, bbox_inches="tight")

Edge cases

| Situation | Fix | |-----------|-----| | Dates not parsed | pd.to_datetime(df["date"]) | | Too many categories (> 15) | Use horizontal bar + show top N + "Other" | | Negative values in bar chart | Set ax.axhline(0, color="black", linewidth=0.8) | | Very different scales | Use dual Y-axis with ax.twinx() | | Missing values in time series | df.interpolate() or show gaps explicitly | | Matplotlib not installed | pip install matplotlib seaborn plotly --break-system-packages |

Output format

Always report:

• Chart type chosen and why
• X/Y axes and what they represent
• Output file path(s)
• Key insight from the chart (1 sentence: "Revenue peaks in Q4 with $21k")

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: prasad-nimbalkar
• Source: prasad-nimbalkar/claude-agent-skills
• License: MIT

Install and usage instructions live in the source repository linked above.