Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jqaisystems/jqai-ai-skills --skill thumbnail-legibility-checkgit clone --depth 1 https://github.com/jqaisystems/jqai-ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jqaisystems/jqai-ai-skills/thumbnail-legibility-check)<a href="https://agentmods.dev/skills/jqaisystems/jqai-ai-skills/thumbnail-legibility-check"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/thumbnail-legibility-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jqaisystems/jqai-ai-skills/thumbnail-legibility-check"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/thumbnail-legibility-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.01017 |
| Opus 5.5 | $0.00034 | $0.00407 |
| Sonnet 5.5 | $0.00017 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
thumbnail-legibility-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thumbnail Legibility Check
Thumbnails are designed at 1280 pixels wide or larger and seen at about 168. Almost every bad thumbnail decision comes from judging it at the wrong size.
This skill measures what actually survives, then puts the candidates through the conditions they will really face.
When to use
- Choosing between several thumbnail, cover, or preview-image candidates.
- An image that looks strong at full size and disappears in a feed.
- Checking whether on-image text or a face reads at small size.
- Comparing a new candidate against what already performs.
Step 1: measure
python scripts/legibility.py path/to/candidates --recursive
Requires Pillow (python -m pip install Pillow). Add --json for machine
output. Every candidate is cover-cropped and downscaled to 168x94, then measured:
| Metric | What it means | Risk below or above |
|---|---|---|
bright |
Mean luminance | Under 45 sinks into a dark feed; over 200 washes out on white |
contr |
Mean per-channel spread | Under 40 reads as flat at small size |
pop |
Distance between strongest and weakest channel | Under 12 means muted, no colour signal in a feed |
glance |
Contrast surviving a heavy blur | Low means it turns to mush during a fast scroll |
gray |
Contrast with colour removed | Low means the design leans on hue alone for separation |
These are risk signals, not verdicts. A dark thumbnail can be the right choice when the channel's whole look is dark. Use the numbers to know what you are choosing, not to choose for you.
Step 2: look at it small
Render each candidate at real display size and actually look. The measurement catches what is measurable; your eye catches a face cropped at the jaw, or two candidates that are indistinguishable at that size.
Step 3: the stress tests
Run each candidate through all four. They fail differently.
- Glance blur. Blur heavily. What is still readable is what a scrolling viewer gets. If nothing survives, the composition has no focal hierarchy.
- Grayscale. Strip colour. Structure should hold. If it collapses, the design is doing its work with hue alone, which fails against every background.
- Real feed. Place the candidate in the newest slot of the actual feed it will live in, surrounded by genuinely published neighbours. This is the only test that catches "it looks like everything else we publish" and "it clashes with the three above it".
- Decoy feed. Hide all candidates among unrelated images and ask someone to find yours. If they cannot, it does not stand out, whatever the numbers say.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 99 lines · 85 tokens per session scan A 286f08ce8693
thumbnail-legibility-check is a skill published in the GitHub repository jqaisystems/jqai-ai-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 85 tokens to every session and 1,017 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
understand-figma
Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
design-system-synthesizer
Use when the user says 'build a design system for my site', 'extract design tokens', 'capture my brand', or 'build my style guide', or after a rebrand. Reads representative pages, theme files, and media to extract logo, colors, typography, spacing, and components, then writes a visible style-guide page.
art-direction
Use on any page build, redesign, or 'make it look better' request on a site that has (or needs) a saved Art Direction. Loads the direction before the first element is written, plans tokens in two passes against the direction's donts and the known AI-default aesthetics, builds with tokens preserved, checks the result…
page-template-library
Use when the user says 'save this as a template', 'create a playbook from this page', 'capture this layout', or has hand-built the same page type three times. Captures canonical page patterns as reusable playbooks that later page generation can spawn from in seconds.