alterlab-infographics — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited alterlab-infographics (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Infographics are visual representations of information, data, or knowledge designed to present complex content quickly and clearly. This skill uses Nano Banana Pro AI for infographic generation with Gemini 3.1 Pro quality review and Perplexity Sonar for research.
How it works:
Quality Thresholds by Document Type:
| Document Type | Threshold | Description |
|---|---|---|
| marketing | 8.5/10 | Marketing materials - must be compelling |
| report | 8.0/10 | Business reports - professional quality |
| presentation | 7.5/10 | Slides, talks - clear and engaging |
| social | 7.0/10 | Social media content |
| internal | 7.0/10 | Internal use |
| draft | 6.5/10 | Working drafts |
| default | 7.5/10 | General purpose |
Use the infographics skill when:
| Scenario | Use Instead |
|---|---|
| Technical flowchart, CONSORT/PRISMA diagram, biological pathway, circuit, or neural-network architecture | alterlab-scientific-schematics |
| Photo, illustration, concept art, or hero image with no data layout | alterlab-generate-image |
| Exact chart of a dataset (every value must match the data) for a paper or report | alterlab-matplotlib / alterlab-scientific-viz |
| Full research poster for a conference session | alterlab-latex-posters |
Generate any infographic by describing it; the script handles generation, review, and iteration.
# Generate a list infographic (default threshold 7.5/10)
python scripts/generate_infographic.py \
"5 benefits of regular exercise" \
-o figures/exercise_benefits.png --type list
# Marketing (highest threshold: 8.5/10)
python scripts/generate_infographic.py \
"Product features comparison" \
-o figures/product_comparison.png --type comparison --doc-type marketing
# Corporate style + colorblind-safe palette
python scripts/generate_infographic.py \
"Company milestones 2010-2025" \
-o figures/timeline.png --type timeline --style corporate
# WITH RESEARCH for accurate, up-to-date data
python scripts/generate_infographic.py \
"Global AI market size and growth projections" \
-o figures/ai_market.png --type statistical --researchWhat happens behind the scenes:
Output: Versioned images plus a detailed JSON review log with quality scores, critiques, and early-stop info. With --research, a _research.json file also records the gathered facts and the source URLs returned by the search model.
Check the numbers before you publish. The image model draws every figure and label itself, so it can misspell words or alter digits even when the prompt was correct, and the review model scores design quality, not factual accuracy. Compare each statistic in the finished graphic against your data or the _research.json sources, and cite those sources wherever the infographic is used. If the review call fails, the script keeps the image and records "review_skipped": true with a null score in the log instead of inventing one.
--type) — one of 10 presets (statistical, timeline, process, comparison, list, geographic, hierarchical, anatomical, resume, social). Full catalog with examples in references/type_catalog.md.--style presets, 3 colorblind-safe --palette presets. Tables in references/type_catalog.md.OPENROUTER_API_KEY) and run; review the JSON log and regenerate with a more specific prompt if needed.Set the OpenRouter API key in the environment, or in a .env file if python-dotenv is installed:
export OPENROUTER_API_KEY='your_api_key_here' # https://openrouter.ai/keysDefault models (verified on OpenRouter 2026-09-23): google/gemini-3-pro-image (Nano Banana Pro) for generation, google/gemini-3.1-pro-preview for review, and perplexity/sonar-pro for research. Override the first two with ALTERLAB_IMAGE_MODEL / ALTERLAB_REVIEW_MODEL.
Data & privacy: prompts and research/infographic content are sent to a third-party API (OpenRouter) for generation and quality review. Avoid sending confidential, clinical, or unpublished material.
| File | Contents |
|---|---|
references/type_catalog.md | All 10 --type presets with runnable examples; --style and --palette tables |
references/cli_and_workflow.md | Full CLI options, smart-refinement loop + Gemini review criteria + review-log schema, --research integration, prompt-engineering tips, troubleshooting, cross-skill integration, checklist |
references/design_principles.md | Visual hierarchy, layout, typography |
references/color_palettes.md | Full palette specifications |
references/infographic_types.md | Extended layout templates for all types |
Use this skill to create professional, accessible, and visually compelling infographics using Nano Banana Pro AI with intelligent Gemini 3.1 Pro quality review.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.