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 CloudWave818/ieee-skills --skill ieee-figure-tablegit clone --depth 1 https://github.com/CloudWave818/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/cloudwave818/ieee-skills/ieee-figure-table)<a href="https://agentmods.dev/skills/cloudwave818/ieee-skills/ieee-figure-table"><img src="https://agentmods.dev/badge/skills/cloudwave818/ieee-skills/ieee-figure-table/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/cloudwave818/ieee-skills/ieee-figure-table"><img src="https://agentmods.dev/badge/skills/cloudwave818/ieee-skills/ieee-figure-table.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00142 | $0.00831 |
| Opus 5 | $0.00071 | $0.00415 |
| Sonnet 5 | $0.00028 | $0.00166 |
| Haiku 4.5 | $0.00014 | $0.00083 |
Grade A, and why
ieee-figure-table 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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IEEE Figure Table Router
Use this skill to make figures and tables function as professional IEEE evidence. The goal is not decoration; it is readable, fair, claim-aligned visual proof that still works after IEEE column scaling.
Do not rely on general design intuition alone. Follow the routing protocol and load the selected fragments.
Routing Protocol
- Read
manifest.yaml. - Read every file listed under
always_load. - Detect the axes:
visual_type: line-plot / bar-chart / scatter / confusion-matrix / comparison-table / ablation-table / architecture-diagram / algorithm-flowchart / multi-panel / generic.check_type: readability / accessibility / caption / layout / evidence-mapping / statistical-presentation.failure_mode: blurry-figure / bad-axis / overlapping-legend / misleading-scale / inconsistent-precision / weak-caption / unreadable-two-column.stage: audit / redesign / caption-writing / latex-placement.backend: python / r / hybrid / no-plot. Usehybridwhen a figure is partly generated from data/code and partly finished in a vector/design tool. Useno-plotfor audit-only, caption-only, table-only, or LaTeX-placement tasks that do not generate plotting code or image files.
- For plotting/redrawing tasks, resolve
backendby explicit request, input workflow, or saved preference. If the intended output is a mechanism schematic, graphical workflow, polished composite, annotated experiment pipeline, or figure that cannot be cleanly produced end-to-end in Python/R, choosehybrid. If no preference exists for a pure plotting task, ask once: Python or R? I will remember this as your default for IEEE figures. - State the detected axes in one short line.
- Load only the matching fragments.
- For plotting/redrawing, establish an IEEE figure contract before code: core engineering claim, evidence-panel map, final column size, metric/condition definitions, export formats, visual style target, and QA risks.
- Map each figure/table to the claim it supports.
- For Python plotting, prefer the bundled
scripts/ieee_plot_style.pyhelper or mirror its API when writing standalone manuscript code. For hybrid figures, separate data-generated layers from manually edited vector/layout layers and keep an edit log. - Report first-impression risks before cosmetic suggestions.
What ships with it
46 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.
- agents/openai.yaml 246 B
- manifest.yaml 5.4 KB
- references/ieee-chart-patterns.md 2.9 KB
- references/ieee-export-qa.md 2.1 KB
- references/ieee-hybrid-figure-workflow.md 4.1 KB
- references/ieee-plotting-api.md 2.4 KB
- references/ieee-plotting-contract.md 2.1 KB
- references/ieee-visual-style.md 5.4 KB
- scripts/ieee_figure_backend.py 1.5 KB runs code
- scripts/ieee_plot_style.py 11 KB runs code
- static/core/figure-contract.md 1.3 KB
- static/core/first-impression.md 478 B
- static/core/output-format.md 405 B
- static/core/stance.md 763 B
- static/core/workflow.md 849 B
- static/fragments/backend/hybrid.md 1.1 KB
- static/fragments/backend/no-plot.md 372 B
- static/fragments/backend/python.md 1.8 KB
- static/fragments/backend/r.md 1.5 KB
- static/fragments/check_type/accessibility.md 309 B
- static/fragments/check_type/caption.md 251 B
- static/fragments/check_type/evidence-mapping.md 275 B
- static/fragments/check_type/layout.md 276 B
- static/fragments/check_type/readability.md 215 B
- static/fragments/check_type/statistical-presentation.md 348 B
- static/fragments/failure_mode/bad-axis.md 203 B
- static/fragments/failure_mode/blurry-figure.md 318 B
- static/fragments/failure_mode/inconsistent-precision.md 246 B
- static/fragments/failure_mode/misleading-scale.md 320 B
- static/fragments/failure_mode/overlapping-legend.md 240 B
- static/fragments/failure_mode/unreadable-two-column.md 295 B
- static/fragments/failure_mode/weak-caption.md 262 B
- static/fragments/stage/audit.md 118 B
- static/fragments/stage/caption-writing.md 182 B
- static/fragments/stage/latex-placement.md 401 B
- static/fragments/stage/redesign.md 251 B
- static/fragments/visual_type/ablation-table.md 319 B
- static/fragments/visual_type/algorithm-flowchart.md 269 B
- static/fragments/visual_type/architecture-diagram.md 864 B
- static/fragments/visual_type/bar-chart.md 371 B
- static/fragments/visual_type/comparison-table.md 315 B
- static/fragments/visual_type/confusion-matrix.md 284 B
- static/fragments/visual_type/generic.md 242 B
- static/fragments/visual_type/line-plot.md 356 B
- static/fragments/visual_type/multi-panel.md 294 B
- static/fragments/visual_type/scatter.md 262 B
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.
- 10d ago First seen · 74 lines · 142 tokens per session scan A f856aafc643e
ieee-figure-table is a skill published in the GitHub repository CloudWave818/ieee-skills (278 stars, last pushed 28d ago), licensed MIT. It adds 142 tokens to every session and 831 once invoked, about $0.0007 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…