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 zhoy0409-debug/polish-sci-figures --skill polish-sci-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/polish-sci-figures)<a href="https://agentmods.dev/skills/zhoy0409-debug/polish-sci-figures/polish-sci-figures"><img src="https://agentmods.dev/badge/skills/zhoy0409-debug/polish-sci-figures/polish-sci-figures/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/zhoy0409-debug/polish-sci-figures/polish-sci-figures"><img src="https://agentmods.dev/badge/skills/zhoy0409-debug/polish-sci-figures/polish-sci-figures.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 | $0.00107 | $0.07252 |
| Opus 5.5 | $0.00043 | $0.02901 |
| Sonnet 5.5 | $0.00021 | $0.01450 |
| Haiku 4.5 | $0.00011 | $0.00725 |
Grade A, and why
polish-sci-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 4d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polish Scientific Figures
Deliver the near-final figure in one internal pass: establish the claim and final placement, trace the authoritative data, compare the existing and proposed forms, draw, export, inspect at real size, correct, and package. Do not make the user rediscover alignment, canvas, font, overlap, scientific-label, or editability defects.
Accept everyday requests such as “帮我把这张表画成适合论文的图”. Inspect the input first, present a few suitable candidates with plain-language explanations, and ask only for consequential facts the data cannot establish. Let users make routine appearance changes directly in Studio without another model call; do not require specialist vocabulary or a structured prompt.
Verify the agent's Python runtime first
Before running a bundled Python script, choose and verify an existing interpreter yourself. Prefer the current project's .venv/Scripts/python.exe (Windows) or .venv/bin/python, then a runtime exposed by the host's dependency tools; only then inspect registered Python launchers or python3. Do not assume that bare python is Python 3, or that a host-bundled interpreter includes scientific packages. Read-only checks should try the next available candidate before asking the user to install anything.
First run the candidate with -c "import sys; print(sys.executable); print(sys.version); sys.exit(0 if (3,10) <= sys.version_info[:2] <= (3,12) else 2)". For a supported interpreter, actually import numpy, pandas, scipy, matplotlib, openpyxl and PIL; a package-directory listing is not a successful import. If the full suite is present, run that interpreter's sci_figures.py doctor --font SELECTED_FONT --json for the remaining font and environment checks. Reuse the verified executable for every command and subprocess, with -X utf8 on Windows; python in examples means this verified executable.
If no candidate passes, identify the specific missing runtime/package and propose a task-local environment or the installed Figure Studio option. Do not modify PATH, install into the global interpreter, or ask a novice to guess executable paths. Runtime checks are the agent's work; the user's ordinary-language request is sufficient.
What ships with it
60 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 300 B
- assets/figure-studio/alignment-icons.js 9.5 KB runs code
- assets/figure-studio/axis-editing.js 22 KB runs code
- assets/figure-studio/axis-settings-ui.css 1.8 KB
- assets/figure-studio/axis-settings-ui.js 29 KB runs code
- assets/figure-studio/canvas-clipboard.js 26 KB runs code
- assets/figure-studio/catalogue-previews.json 7220 KB
- assets/figure-studio/catalogue.js 6.3 KB runs code
- assets/figure-studio/chart-knowledge.json 39 KB
- assets/figure-studio/compact-whitespace.js 12 KB runs code
- assets/figure-studio/component-style.js 6.5 KB runs code
- assets/figure-studio/discovery-offline.js 5.9 KB runs code
- assets/figure-studio/discovery-ui.css 4.4 KB
- assets/figure-studio/discovery-ui.js 31 KB runs code
- assets/figure-studio/discovery.js 22 KB runs code
- assets/figure-studio/duplicate-check.css 8.2 KB
- assets/figure-studio/duplicate-check.js 43 KB runs code
- assets/figure-studio/duplicate-review.js 4.7 KB runs code
- assets/figure-studio/duplicate-viewer.css 6.9 KB
- assets/figure-studio/duplicate-viewer.js 24 KB runs code
- assets/figure-studio/element-insertions.js 10 KB runs code
- assets/figure-studio/experience-tools.css 3.1 KB
- assets/figure-studio/experience-tools.js 13 KB runs code
- assets/figure-studio/gallery-contracts.js 167 KB runs code
- assets/figure-studio/grid-resize-ui.js 33 KB runs code
- assets/figure-studio/group-spacing.js 21 KB runs code
- assets/figure-studio/i18n.js 138 KB runs code
- assets/figure-studio/image-color-ui.js 46 KB runs code
- assets/figure-studio/image-color.js 19 KB runs code
- assets/figure-studio/image-insets-controller.js 20 KB runs code
- assets/figure-studio/image-insets-ui.js 20 KB runs code
- assets/figure-studio/image-insets.js 30 KB runs code
- assets/figure-studio/image-links-controller.js 12 KB runs code
- assets/figure-studio/image-links-ui.js 41 KB runs code
- assets/figure-studio/image-links.js 14 KB runs code
- assets/figure-studio/image-rectify-detect.js 26 KB runs code
- assets/figure-studio/image-rectify-ui.js 41 KB runs code
- assets/figure-studio/image-rectify.css 5.2 KB
- assets/figure-studio/image-rectify.js 28 KB runs code
- assets/figure-studio/image-straighten.js 6.2 KB runs code
- assets/figure-studio/layers-panel.js 12 KB runs code
- assets/figure-studio/layout-lock.js 34 KB runs code
- assets/figure-studio/legacy-stat-cleanup.js 9.3 KB runs code
- assets/figure-studio/library.js 1.2 KB runs code
- assets/figure-studio/literature.css 5.0 KB
- assets/figure-studio/literature.js 30 KB runs code
- assets/figure-studio/mark-style.js 25 KB runs code
- assets/figure-studio/mascot-border-collie.svg 4.7 KB
- assets/figure-studio/mascot-maine-coon.svg 5.2 KB
- assets/figure-studio/mascot-minimal-cat.svg 1.5 KB
- assets/figure-studio/mascot-minimal-dog.svg 1.2 KB
- assets/figure-studio/mascot-scene.svg 3.5 KB
- assets/figure-studio/master-frame.js 5.3 KB runs code
- assets/figure-studio/memory.js 2.6 KB runs code
- assets/figure-studio/mobile-ui.css 12 KB
- assets/figure-studio/mobile-ui.js 16 KB runs code
- assets/figure-studio/object-borders.js 35 KB runs code
- assets/figure-studio/panel-commands.js 9.0 KB runs code
- assets/figure-studio/preview-sessions.js 7.4 KB runs code
- assets/figure-studio/research-discovery.js 13 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.
- 4d ago Changed · +8 lines 4fa03c9fe20b
- 6d ago Changed · +4 lines ea631331745b
- 7d ago Changed · +12 lines · +8 tokens per session f3311ce0256b
- 8d ago Changed · +32 lines · -3 tokens per session 1d28ee429064
- 17d ago Changed · +4 lines 9655bbe92752
- 1mo ago First seen · 220 lines · 102 tokens per session scan A d77d1da80680
polish-sci-figures is a skill published in the GitHub repository zhoy0409-debug/polish-sci-figures (58 stars, last pushed 2d ago), licensed MIT. It adds 107 tokens to every session and 7,252 once invoked, about $0.0004 per session on Opus 5.5. 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-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.
xiaobei-skill-image-to-vba
An image-to-VBA skill that converts academic figures, diagrams, screenshots, and slides into Office drawing code and editable shapes. VBA is the programming language built into Microsoft Office.
xiaobei-skill-academic-paper-to-ppt
A workflow that turns academic papers, reports, and technical documents into presentation slides, optionally following a supplied PowerPoint template. It creates a written outline, full-slide images, and a PowerPoint file.
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…
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-figure
Create, advise on, or audit academic figures in four modes. advise profiles the data and recommends a chart type when none is fixed. journal-spec creates or reviews publication-ready figures for journal submission specs using matplotlib, seaborn, plotly, industrytslib, or the optional pubfig backend. from-data fills a…