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 agentmods add skills/zhoy0409-debug/polish-sci-figures/make-sci-data-figuresnpx skills add zhoy0409-debug/polish-sci-figures --skill make-sci-data-figuresgit clone --depth 1 https://github.com/zhoy0409-debug/polish-sci-figuresWrote 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/zhoy0409-debug/polish-sci-figures/make-sci-data-figures)<a href="https://agentmods.dev/skills/zhoy0409-debug/polish-sci-figures/make-sci-data-figures"><img src="https://agentmods.dev/badge/skills/zhoy0409-debug/polish-sci-figures/make-sci-data-figures.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.02598 |
| Opus 5 | $0.00045 | $0.01299 |
| Sonnet 5 | $0.00018 | $0.00520 |
| Haiku 4.5 | $0.00009 | $0.00260 |
Grade A, and why
make-sci-data-figures 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 3d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make SCI Data Figures
Start from the biological question and experimental unit, not from a preferred chart type. Produce several honest candidates from the same data, keep their canvas and typography identical, and explain why each candidate is or is not appropriate.
For unified CLI inspection and confirmation states, read references/safe_cli_routing.md. Never treat a role inferred from a column name as a declared experimental unit or design.
Minimum intake
Accept tidy CSV, TSV, or XLSX. Route the table by scientific structure rather than forcing every dataset into a group comparison:
| Structure | Required declarations | Script command |
|---|---|---|
| Continuous group comparison | group, value, biological-unit ID, independent/paired design, authoritative order | figure_workbench.py generate |
| Numeric relationship | x, y, biological-unit ID; optional group | data_family_workbench.py relationship |
| Longitudinal response | time, value, group, biological-unit ID | data_family_workbench.py timecourse |
| Composition | sample, category, non-negative value; optional group | data_family_workbench.py composition |
| Tidy matrix | row, column, value; explicit or automatic display clustering | data_family_workbench.py matrix |
| Survival | follow-up time, 0/1 event, group, biological-unit ID | advanced_template_workbench.py survival |
| Dose-response | positive dose, response, group; optional unit ID | advanced_template_workbench.py dose-response |
| Classification | binary outcome, score, biological-unit ID; optional cohort | advanced_template_workbench.py roc |
| Supplied specialist results | family-specific estimate/result columns | advanced_template_workbench.py FAMILY |
Before inferential statistics, establish:
- the outcome, unit, and intended claim;
- the biological experimental unit;
- whether observations are independent, paired, repeated, nested, or technical replicates;
- the reference group and group order;
- whether endpoints or contrasts were pre-specified or exploratory.
What ships with it
26 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 301 B
- assets/palettes.json 332 B
- examples/make_advanced_examples.py 2.8 KB runs code
- examples/make_family_examples.py 3.3 KB runs code
- examples/synthetic_composition.csv 1.7 KB
- examples/synthetic_dose_response.csv 3.8 KB
- examples/synthetic_enrichment.csv 791 B
- examples/synthetic_group_comparison.csv 457 B
- examples/synthetic_matrix.csv 1.2 KB
- examples/synthetic_multigroup_response.csv 888 B
- examples/synthetic_paired_response.csv 382 B
- examples/synthetic_relationship.csv 1.1 KB
- examples/synthetic_roc.csv 3.9 KB
- examples/synthetic_survival.csv 2.4 KB
- examples/synthetic_timecourse.csv 2.0 KB
- references/advanced_template_contracts.md 4.0 KB
- references/data_contract.md 2.6 KB
- references/professional_basis.md 3.6 KB
- references/safe_cli_routing.md 1.3 KB
- references/statistics_and_chart_selection.md 5.3 KB
- scripts/advanced_template_workbench.py 61 KB runs code
- scripts/data_family_workbench.py 37 KB runs code
- scripts/figure_workbench.py 42 KB runs code
- scripts/test_advanced_template_workbench.py 12 KB runs code
- scripts/test_data_family_workbench.py 7.7 KB runs code
- scripts/test_figure_workbench.py 5.7 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.
- 3d ago First seen · 157 lines · 90 tokens per session scan A 93eda83b3d4a
make-sci-data-figures is a skill published in the GitHub repository zhoy0409-debug/polish-sci-figures (4 stars, last pushed 9d ago), licensed MIT. It adds 90 tokens to every session and 2,598 once invoked, about $0.0005 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
xiaobei-skill-image-to-vba
Use when users want XiaoBei skill / xiaobei-skill / 小北在读研 style academic image-to-VBA reconstruction: convert academic figures, scientific diagrams, slides, screenshots, or other images into VBA, Office drawing code, PowerPoint/Excel/Word shapes, editable shape reconstruction, 1:1 recreation, pixel-like approximation…
xiaobei-skill-academic-paper-to-ppt
Use for 小北在读研 / XiaoBei academic paper-to-PPT workflows: generate thesis-defense or project-report decks from uploaded papers, literature, reports, technical documents, and optional PPTX visual templates. Produces a source-grounded outline, an imagegen visual scheme, one complete bitmap per slide, an imagegen…
xiaobei-skill-rebuild-image-in-powerpoint
Use when a user wants Codex to directly operate PowerPoint and reconstruct an entire reference image as editable PowerPoint objects while preserving its full layout, labels, connectors, and visual relationships. Do not use for paper-to-deck generation or VBA-only output.
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…
nice-figures
Generate matplotlib figures in the soft-pastel + warm-earth visual register used by AI alignment research blogs (Anthropic-style) — bold sans-serif display titles, scatter overlaid with smoothed trends and shaded confidence bands, minimal axes, '↓better' badges, warm coral/peach/sage/blue palettes, white background by…
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.…