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 bahayonghang/my-ai-cli-toolkit --skill academic-figuregit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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/bahayonghang/my-ai-cli-toolkit/academic-figure)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/academic-figure"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/academic-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/bahayonghang/my-ai-cli-toolkit/academic-figure"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/academic-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 | $0.00225 | $0.01195 |
| Opus 5 | $0.00112 | $0.00598 |
| Sonnet 5 | $0.00045 | $0.00239 |
| Haiku 4.5 | $0.00022 | $0.00120 |
Grade A, and why
academic-figure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Figure
Pick one mode before loading its reference or writing plotting code.
Replace
<skill-dir>with the loaded skill directory. In Windows PowerShell, set$env:PYTHONUTF8 = '1'before UTF-8 Python commands.
Pick a mode
| Input intent | Mode | Read |
|---|---|---|
Journal/thesis target, generic 论文配图, or compliance review |
journal-spec | references/modes/journal-spec.md |
| User data plus a named catalog style | from-data | references/modes/from-data.md |
| Uploaded paper figure, with no journal target | from-image | references/modes/from-image.md |
Data in hand with the chart type still open, or a request for a chart recommendation (不知道用什么图) |
advise | references/modes/advise.md |
Resolve conflicts in order:
- An explicit journal target selects journal-spec; a style or image is visual reference only.
- If exact mimicry and journal compliance are both explicit, ask once which contract wins.
- If the chart type is open, and no catalog style or reference image is given, run advise first. Its hand-off then applies rule 1.
Output contracts
The selected row is authoritative.
| Mode | Required output behavior |
|---|---|
| journal-spec | Vector-first PDF/SVG/EPS; target size, font, and DPI; colorblind-safe defaults; fonttype=42; every applicable QA item checked |
| from-data / from-image | Matplotlib script and dpi=300 PNG; deliberately mimic the selected style or source; journal QA is not imposed by default |
| advise | One recommended chart type with the reason and one or two alternates, every matched pitfall reported, and a named hand-off mode; advise draws no figure |
What ships with it
57 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/interface.yaml 1.4 KB
- assets/originals/bar_memevolve.png 56 KB
- assets/originals/bar_spice.png 304 KB
- assets/originals/classwise_iou.png 65 KB
- assets/originals/line_aime.png 60 KB
- assets/originals/line_loss_inset.png 62 KB
- assets/originals/line_selfdistill_scale.png 66 KB
- assets/originals/line_selfdistill_train.png 59 KB
- assets/originals/radar_dora.png 307 KB
- assets/originals/scatter_break.png 71 KB
- assets/originals/scatter_tsne.png 319 KB
- evals/evals.json 17 KB
- references/agent-figure-gallery-integration.md 5.9 KB
- references/attribution.md 7.6 KB
- references/chart-recipes.md 15 KB
- references/chart-selection.md 7.3 KB
- references/design-theory.md 5.4 KB
- references/figure-contract.md 6.6 KB
- references/figure-legend-conventions.md 4.1 KB
- references/industrytslib-integration.md 15 KB
- references/journal-specs.md 24 KB
- references/layout-defaults.md 3.7 KB
- references/matplotlib-recipes.md 17 KB
- references/modes/advise.md 3.3 KB
- references/modes/from-data.md 4.6 KB
- references/modes/from-image.md 4.0 KB
- references/modes/journal-spec.md 3.3 KB
- references/panel-layout-patterns.md 6.2 KB
- references/plotly-recipes.md 9.0 KB
- references/pubfig-integration.md 6.5 KB
- references/qa-checklist.md 12 KB
- references/reproduction_guide.md 4.1 KB
- references/styles/bar_grouped_hatch.md 4.4 KB
- references/styles/bar_paired_delta.md 2.8 KB
- references/styles/line_confidence_band.md 2.7 KB
- references/styles/line_loss_with_inset.md 2.3 KB
- references/styles/line_training_curve.md 1.2 KB
- references/styles/radar_dual_series.md 2.2 KB
- references/styles/scatter_broken_axis.md 2.1 KB
- references/styles/scatter_tsne_cluster.md 2.2 KB
- references/visual-review.md 5.9 KB
- references/viz-pitfalls.md 9.6 KB
- scripts/academic_figure_pref.py 3.1 KB runs code
- scripts/audit_pdf_text.py 6.7 KB runs code
- scripts/bar_memevolve.py 4.6 KB runs code
- scripts/bar_spice.py 5.9 KB runs code
- scripts/classwise_iou_table.py 4.5 KB runs code
- scripts/line_aime.py 2.9 KB runs code
- scripts/line_loss_inset.py 5.3 KB runs code
- scripts/line_selfdistill.py 6.9 KB runs code
- scripts/radar_dora.py 4.6 KB runs code
- scripts/scatter_break.py 5.7 KB runs code
- scripts/scatter_tsne.py 4.4 KB runs code
- scripts/visual_qa.py 16 KB runs code
- tests/audit-pdf-text.test.mjs 4.0 KB runs code
- tests/pref-script.test.mjs 3.0 KB runs code
- tests/visual-qa.test.mjs 5.5 KB runs code
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 · 106 lines · 225 tokens per session scan A 845f05f28f9f
academic-figure is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed yesterday), licensed MIT. It adds 225 tokens to every session and 1,195 once invoked, about $0.0011 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
elsevier-figure-style
Generate, revise, and audit source-backed quantitative manuscript figures, and visually audit exported schematic/conceptual figures and graphical abstracts without redrawing them in v0.1. Use for Elsevier-style manuscript figure generation, matplotlib or ggplot2 result plots, line charts, heatmaps, bar charts, scatter…
econ-visualization
Generates publication-quality economics figures produced by code (R ggplot2, Python matplotlib/seaborn, Stata twoway/coefplot) and exported in vector format directly to the paper's figs/ folder. Defaults to DIME's "full replicability" tier and the Reviewing Graphs checklist — clear titles for standalone use, intuitive…
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
polish-sci-figures
A final review and preparation workflow for scientific figures, including charts, image panels, manuscripts, slides, and posters.
make-sci-data-figures
A workbench for turning raw CSV, TSV, or Excel tables into defensible scientific figures. It chooses charts based on the biological question and data structure rather than assuming one chart type fits every dataset.