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 TenWalk/ieee-skills --skill ieee-figuregit clone --depth 1 https://github.com/TenWalk/ieee-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/tenwalk/ieee-skills/ieee-figure)<a href="https://agentmods.dev/skills/tenwalk/ieee-skills/ieee-figure"><img src="https://agentmods.dev/badge/skills/tenwalk/ieee-skills/ieee-figure/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/tenwalk/ieee-skills/ieee-figure"><img src="https://agentmods.dev/badge/skills/tenwalk/ieee-skills/ieee-figure.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 | $0.00262 | $0.01129 |
| Opus 5 | $0.00131 | $0.00564 |
| Sonnet 5 | $0.00052 | $0.00226 |
| Haiku 4.5 | $0.00026 | $0.00113 |
Grade A, and why
ieee-figure 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 11d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IEEE Publication Figures
Use this skill to generate or repair figures that will survive IEEE production: vector, correctly sized for the column, with embedded fonts and readable text at print size.
Core stance
- Size to the column from the start. Single-column ≈ 3.5 in (88.9 mm) wide; double-column ≈ 7.16 in (181.6 mm). Design at final size so fonts end up readable — never shrink a big figure.
- Vector first. Output PDF or EPS for line/vector art; embed fonts. Use high-res raster only for photographic content (≥ 300 dpi color/grayscale, ≥ 600 dpi for line art / combinations).
- Readable and grayscale-safe. Minimum ~8 pt text at final size; distinguish series by marker/linestyle/hatch as well as colour so the figure survives B/W printing; use a colorblind-safe palette.
- Comms axis conventions. Error/outage curves use a log y-axis (
semilogy); keep the SNR range wide enough to show the high-SNR slope (diversity order); define the SNR axis (transmit vs receive). Plot a derived expression as a line and its Monte-Carlo check as markers. - One panel, one question. No two panels answer the same thing. The figure must be legible and self-explanatory with its caption.
- No fabricated data. Plot only the user's real numbers; if data is missing, ask or stub with a clearly labelled placeholder.
When to open extra files
| File | Open when |
|---|---|
| references/ieee-figure-spec.md | Sizing, resolution, fonts, colour/grayscale, file format, multi-panel layout, caption rules, submission checklist |
| references/matplotlib-patterns.md | Concrete matplotlib setup (rcParams for embedded fonts, sizing, palettes) and ready patterns for BER/outage-vs-SNR (semilog), rate vs SNR/antennas, analysis-vs-simulation overlay, convergence, CDF, NMSE-vs-SNR, training/validation loss, and ISAC plots (rate–CRB tradeoff, beampattern, ROC) |
Workflow
- Target column: ask single- or double-column; set the width accordingly.
- Pick the chart type that matches the result (see matplotlib-patterns.md): BER/outage vs SNR (semilog y) for reliability, line vs SNR/antennas for rate/efficiency, analysis-line + simulation-marker overlay to validate a derivation, objective-vs-iteration for convergence, CDF for distributions.
- Set the rendering rcParams first (embedded fonts, sans-serif, sizes) — before any plotting.
- Plot the real data; encode each scheme redundantly (colour + marker/linestyle). Use
semilogyfor error/outage; floor the y-axis at the lowest reliably simulated value. - Label fully: axis titles with units (dB, bps/Hz), defined SNR axis, legend; text ≥ 8 pt.
- Export
.pdf(or.eps) as primary and a 300–600 dpi.pngpreview. - Grayscale check: convert to gray and confirm series are still distinguishable.
- Return the script, the output paths, and a one-line caption draft.
What ships with it
3 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.
- 11d ago First seen · 66 lines · 262 tokens per session scan A 878b41ac8bc1
ieee-figure is a skill published in the GitHub repository TenWalk/ieee-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 262 tokens to every session and 1,129 once invoked, about $0.0013 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 2026-08-31.
Other skills, from other repositories
academic-figure
A Chinese-language toolkit for making and checking academic charts, diagrams, flowcharts, and graphical abstracts. A graphical abstract is a visual summary of a research paper, while a flowchart shows the steps or decisions in a process.
awesome-ieee-report
Generates IEEE-format LaTeX technical reports from project requirements and codebase evidence, using academic prose, pseudocode-only explanations, BibTeX references, and IEEEtran formatting.
academic-figure-figma
Use when the user wants a paper figure (framework, pipeline, architecture, method overview) drawn, rebuilt, or refined as an editable vector in Figma via Claude Code — including reproducing a candidate/reference image (e.g. studio-pro C01-C04) at exact print size. Also use when the user needs to set up or fix the…
paper-framework-figure-studio-pro
Human-in-the-loop research-paper framework figure workflow from S0-PAPER-FOUNDATION through terminal S5-CANDIDATE-IMAGE. Use for paper-grounded architecture, pipeline, method overview, agent workflow, system/data-flow, and mechanism figures with generated raster first-round/formal candidates, reviewer-first-glance…
autofigure
Generate clean, EDITABLE vector figures (SVG + exact-size PDF) for research papers — method / architecture / pipeline / system-overview diagrams — with AutoFigure-Edit. Use whenever the user wants to create or vectorize a paper figure from a text description OR from a draft/screenshot/draw.io image: it generates a…
nature-figure
Submission-grade Nature/high-impact journal figure workflow for Python or R. Use whenever the user asks to create, revise, audit, or polish manuscript figures, multi-panel scientific plots, figures4papers-style matplotlib plots, or journal-ready SVG/PDF/TIFF outputs, especially for Nature-family or other high-impact…