What do I need to use Chart?

The data; What you want to show; Series; Title (optional).

Is Chart free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Chart

Q: How do I know the Chart output is good?

The skill verifies itself against its own quality checks: Chart type matches the intent (trend → line, comparison → bar, composition → pie); The JSON is valid and renders without edits (no trailing commas, all strings quoted); Every series' data length equals the number of labels; Units/scale are clear (in the title or series names), and the one-line read states the takeaway.

🔵 Stable🕐 updated 2026-06-30 🔷 SkillSpec L3 pm-visuals

Turn numbers into a chart — bar, line, area, pie, or doughnut. Use when asked to chart or graph data, visualize metrics/trends/breakdowns, or show numbers as a picture instead of a table. Produces a ready-to-render chart spec (renders live in the playground and exports as PNG) plus a one-line read of what the chart shows.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The data — the numbers, with their labels/categories (paste a table, list, or metrics).

▸What you want to show — a trend over time, a comparison between things, or parts of a whole. This decides the chart type.

▸Series — one metric or several (e.g. revenue *and* churn over the same months).

▸Title (optional) — (optional) — what the chart is about.

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Chart type matches the intent (trend → line, comparison → bar, composition → pie)

✓The JSON is valid and renders without edits (no trailing commas, all strings quoted)

✓Every series' data length equals the number of labels

✓Units/scale are clear (in the title or series names), and the one-line read states the takeaway

✓Multiple series are used only when they share the same axis/scale

⚠️ What it refuses to do

Do not use a pie chart for more than ~6 slices or for trends — pies show composition, not change

Do not put units or text inside the numeric `data` array — it breaks the chart

Do not emit invalid JSON (trailing commas, single quotes, comments) — it won't render

Do not mismatch lengths — a series shorter/longer than the labels misaligns the chart

Do not chart numbers you weren't given — flag gaps instead of inventing data points

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Example output

Input: Chart our 2026 H1 metrics: MRR in $k was 120, 138, 151, 167, 180, 201 from Jan to Jun; churned MRR was 8, 9, 7, 11, 9, 8 over the same months. Show the trend for both. · hand-written example

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="chart"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Chart is one of 750 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog