chart-choice
Pick the chart the data and the point actually need — the question-to-chart mapping (comparison, trend, composition, distribution, relationship), the honesty rules (axes, baselines, dual-axis traps), and the one-chart-one-point discipline. Use when asked what chart should I use, make this data visual, why does this chart feel misleading, or fix this graph for the deck. Produces the chart verdict with its reasoning, the honesty checklist applied, and the labeling that lets the chart travel without its author.
npx skills add mohitagw15856/pm-claude-skills --skill chart-choice --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Chart Choice Skill Chart choice is a sentence-completion exercise: the chart exists to make *one stated point* legible in three seconds, and the point's grammar picks the form — comparing things (bars), change over time (lines), parts of a whole (stacked/100% bars — pie only under five slices), distribution (histogram), relationship (scatter). Most bad charts are either the wrong form for the point, or the right form dressed dishonestly: truncated bar axes, dual axes engineered for drama, 3D anything. The skill picks the form, then runs the honesty pass. ## What This Skill Produces - **The chart verdict** — the form, chosen from the point's grammar, with the reasoning stated - **The honesty pass** — axes, baselines, sorting, and the dual-axis/3D vetoes applied - **The labeling spec** — title-as-the-point, direct series labels, the source line — so the chart survives being screenshot out of context - **The alternative** — when the honest answer is "this wants a table, not a chart" ## Required Inputs Ask for these if not provided: - **The point, as a sentence:** "show the data" isn't chartable; "East region drove the Q2 recovery" is — the sentence picks the chart, and extracting it
- What This Skill Produces
- Required Inputs
- Framework: The Choice and Honesty Rules
- Output Format
- The Verdict
- The Honesty Pass
- The Labeling Spec
- The Three-Second Test
- Quality Checks
- Anti-Patterns
What does the chart-choice skill do?
Pick the chart the data and the point actually need — the question-to-chart mapping (comparison, trend, composition, distribution, relationship), the honesty rules (axes, baselines, dual-axis traps), and the one-chart-one-point discipline. Use when asked what chart should I use, make this data visual, why does this chart feel misleading, or fix this graph for the deck. Produces the chart verdict with its reasoning, the honesty checklist applied, and the labeling that lets the chart travel without its author.
How do I install it?
Run `npx skills add mohitagw15856/pm-claude-skills --skill chart-choice --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From mohitagw15856/pm-claude-skills, a repository with 1,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.