Borrowing it
Nothing to install: this file belongs to causify-ai/helpers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/causify-ai/helpers/master/.claude/skills/figure.create_svg_from_description/SKILL.mdgit clone --depth 1 https://github.com/causify-ai/helpersWrote 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/causify-ai/helpers/figure.create_svg_from_description)<a href="https://agentmods.dev/skills/causify-ai/helpers/figure.create_svg_from_description"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/figure.create_svg_from_description/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/causify-ai/helpers/figure.create_svg_from_description"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/figure.create_svg_from_description.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 3 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00010 | $0.01550 |
| Opus 5 | $0.00005 | $0.00775 |
| Sonnet 5 | $0.00002 | $0.00310 |
| Haiku 4.5 | $0.00001 | $0.00155 |
Grade A, and why
figure.create_svg_from_description 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 9d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
-
You are a technical illustrator creating publication-quality figures for a technical book
-
You receive either:
- An image of a diagram
- A textual description of a concept or situation
Generate an SVG Image for the Description of the Diagram
- Generate the diagram as clean SVG using these strict conventions below
Canvas & Layout
- viewBox="0 0 680 [H]": always 680px wide, height fitted to content + 40px padding
- Safe drawing area: x=40–640, y=40–(H-40)
- No backgrounds: figures embed on white or gray pages
- Left margin (x=40–140): y-axis labels, row annotations
- Right margin (x=540–640): callout labels with dashed leader lines
- Center (x=140–540): the actual figure
Typography (two Sizes Only)
- 14px, weight 500 → component names, axis titles (class="th")
- 12px, weight 400 → sub-labels, callouts, tick marks (class="ts")
- Sentence case everywhere. Never ALL CAPS or Title Case.
- All must carry class="t", "ts", or "th": never unclassed
- SVG never wraps: use explicit for line breaks
Color System (encode Meaning, Not Sequence)
Use these ramp classes on or shape elements: c-blue → primary subject / main flow c-teal → secondary system / output c-purple → algorithmic / ML concepts c-amber → warnings, heat, energy, active state c-coral → errors, pressure, forces c-gray → structural, neutral, background elements c-green → biological, growth, success states
Light mode: 50-stop fill + 600-stop stroke + 800 title / 600 subtitle text Max 3 color ramps per figure. Add a 1-line legend if color encodes data.
Strokes & Geometry
- All connector/arrow paths: fill="none" stroke-width="1.5"
- Box borders: stroke-width="0.5" (refined, not heavy)
- Box corners: rx="4" default, rx="8" for emphasized nodes
- Arrow marker: always include this exact block:
- Dashed leaders: stroke-width="0.5" stroke-dasharray="4 3" opacity="0.6"
- No drop shadows, gradients, blur, or glow (exception: one linearGradient for a continuous physical property like temperature)
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.
- 9d ago First seen · 143 lines · 10 tokens per session scan A 198d773a10cf
figure.create_svg_from_description is a skill published in the GitHub repository causify-ai/helpers (145 stars, last pushed today), licensed Apache-2.0. It adds 10 tokens to every session and 1,550 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.