Index of every page on this site: llms.txt
All skills
tristanmanchester avatar

/display-quantitative-information

@3323bc9
by Tristan Manchestertristanmanchester/agent-skills3 stars
2
Run it yourself

Design, critique, or implement quantitative graphics, scientific figures, dashboards, and evidence tables. Use for display choice, scale/encoding integrity, uncertainty, and accessible chart handoff. Do not use for decorative illustration or general data cleaning without a quantitative display.

Use this Skill: https://skilld.dev/gh/tristanmanchester/agent-skills/display-quantitative-information

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referenceslanguage-and-variation.md

≈538 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Language and Variation

Agents are prone to producing the same critique shape repeatedly. That makes reviews feel generic and can obscure the actual diagnosis.

Vary by evidence

Each critique should sound like it came from the chart being reviewed. Mention the actual variables, units, denominator, visual encoding, scale choice, audience, and medium. Domain vocabulary should replace generic phrasing, not decorate it.

A public-health chart may need incidence, population denominator, confidence interval, age adjustment, and reporting lag. A materials or imaging figure may need scale bars, calibration, voxels, segmentation, sample preparation, registration, and measurement uncertainty.

Avoid fixed replacement habits

Do not recommend the same substitute for every flaw. A pie chart does not always become a bar chart; a multi-line chart does not always become small multiples; a legend does not always become direct labels. Diagnose the task first, then choose.

Good recommendations have a mechanism: "use an interval dot plot because the zero baseline is not meaningful and the uncertainty intervals need comparison" is stronger than "replace bars with dots."

Make examples non-pasteable

Examples in this skill show patterns, not text to reuse. When adapting an example, change the domain nouns, numerical context, chart type, evidence, and recommendation order.

Response-shape variation

Pick a shape that fits the task:

  • A fast verdict can be two short paragraphs.
  • A detailed critique can use sections for integrity, comparison, and redesign.
  • A dashboard review can group issues by workflow or panel family.
  • A code handoff can start with a spec and end with checks.
  • A teaching answer can explain the design principle first, then the example.

Avoid using the same numbered structure in every output unless the user asked for standardization.

Stock-phrase check

For long or repeated deliverables, run:

python3 scripts/fingerprint_text.py --input draft.md --format markdown

Treat warnings as prompts to revise, not automatic failures. Technical terms can repeat when they are genuinely needed.

Source: SKILL.md on GitHub

Skill behaviors

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

No alerts1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill is safe to use and adheres to best practices for data visualization auditing. It provides analytical scripts to evaluate chart integrity based on Tufte's principles. All scripts use only the Python standard library, do not perform network requests, and do not access sensitive system files. A minor risk is documented regarding the attack surface for indirect prompt injection when processing untrusted user data.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

Provenance

Signed by skilld at 3323bc9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Steadyupdated last month

Capability

Other metadata
compatibility
Bundled helpers require Python 3.10+ and use the standard library. The SVG renderer is a first-pass tool, not a full plotting or accessibility-validation system.
metadata
{
  "version": "2.1.0",
  "reviewed": "2026-09-13",
  "source-note": "Tufte-informed methods adapted from previously supplied study material; source book text and images are not bundled. No missing licence terms have been reconstructed."
}

README badge

README badge for tristanmanchester/agent-skills/display-quantitative-information