visualization-review
Skill0 starsChanged 3 months agoMITView on GitHub
Critiques and improves existing data visualizations using a prioritized rule system (P0 accessibility and integrity, P1 clarity, P2 polish). Use when reviewing charts, auditing dashboards, checking accessibility compliance, or identifying anti-patterns.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- han69611/math-modeling-skillstheir own version, first seen Jul 7, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- han69611/math-modeling-skills★ 10same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- dashboard-designSkill
- data-storytellerSkill
- data-visualizationSkill
- infographic-creatorSkill
- table-designSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
When the input is an image, first sample the actual hex values (title and label text, data marks, background) from the image, then run the …
- Very specific: line 34
If the visualization contains Hebrew or Arabic text, check the glyph order — whole words reversed (e.g.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Visualization Review
The user's request: "$ARGUMENTS"
Reviews existing visualizations (images, code, or descriptions) against the prioritized rule system in references/review-rules.md:
- P0 (must-fix): correctness, integrity, and accessibility failures that mislead or exclude.
- P1 (strong warning): perception, cognitive load, and narrative issues that reduce effectiveness.
- P2 (polish): style, consistency, and aesthetics.
Be systematic — check every rule at each level. Cite specific elements; always suggest concrete fixes, not just problems.
Instructions
Step 1: Receive the Visualization
Identify: what data relationship is communicated? Who is the audience? What medium (slide, report, dashboard, web)?
Step 2: Run P0 → P1 → P2 Checks
Work through references/review-rules.md in priority order. Any P0 failure is a blocking issue.
For contrast and palette rules (P0 rules 4–5), verify deterministically when colors are known — do not eyeball:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check_contrast.py" '#FG' '#BG'
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check_palette.py" '#hex1,#hex2,...'When the input is an image, first sample the actual hex values (title and label text, data marks, background) from the image, then run the scripts on those values. If the colors cannot be determined, report rules 4-5 as "not verified" instead of guessing a verdict.
If the visualization contains Hebrew or Arabic text, check the glyph order — whole words reversed (e.g. "םילשורי" for "ירושלים") is a blocking P0 (rule 7); check_rtl.py prints the correct handling. Left-to-right bars and axes are correct for RTL languages (numbers are LTR) — do not flag them.
Step 3: Generate Report
Prioritized: P0 issues first with specific fixes, then P1 with suggested redesigns, then P2 polish suggestions. If a level is clean, state "No issues found."
Step 4: Apply Fixes (if requested)
Apply the report's recommendations following the design rules in the data-visualization skill (../data-visualization/references/design-principles.md and ../../assets/core-standards.md). Re-run the relevant checks afterward to verify resolution.
Example
User says: "Review this dashboard for issues."
- Examine the image systematically.
- P0: pie chart with 12 slices (chart-task mismatch); red/green encoding with no labels (color-only).
- P1: generic titles ("Q3 Sales" instead of insight-driven); legend-dependent line chart with 3 series.
- P2: inconsistent font sizes across panels.
- Report with specific fixes for each issue.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.