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 Azhi-ss/academic-figure-skills --skill fig-drawgit clone --depth 1 https://github.com/Azhi-ss/academic-figure-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/azhi-ss/academic-figure-skills/fig-draw)<a href="https://agentmods.dev/skills/azhi-ss/academic-figure-skills/fig-draw"><img src="https://agentmods.dev/badge/skills/azhi-ss/academic-figure-skills/fig-draw/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/azhi-ss/academic-figure-skills/fig-draw"><img src="https://agentmods.dev/badge/skills/azhi-ss/academic-figure-skills/fig-draw.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 | $0.00085 | $0.05009 |
| Opus 5.5 | $0.00034 | $0.02004 |
| Sonnet 5.5 | $0.00017 | $0.01002 |
| Haiku 4.5 | $0.00009 | $0.00501 |
Grade A, and why
fig-draw 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 5d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fig-draw
Produce a grounded academic figure and a stable local artifact. Preserve the user's chosen backend, reference assets, style direction, review preference, and output scope.
If the user asks only to construct, diagnose, or revise a figure prompt, use this skill's matching output mode and stop before rendering. A prompt-only request does not require invented render paths or an extra approval gate.
将科学内容编译成可验收的图示。这里是唯一的设计与 prompt 编译入口；不把提示词修辞当作第二次科学设计。
按请求选择输出
| 用户意图 | 行动与停止点 |
|---|---|
| 构造画图提示词 / 只写 prompt | construct：设计简报与完整 prompt；不生图 |
| 检查或诊断已有 prompt | diagnose：定位问题、影响与最小修正；不擅改文件或生图 |
| 按反馈修改 prompt | revise：改动、保留项及完整新 prompt；不自动生图 |
| 制作图 / 修改图片 | construct 或 revise 后，本 skill 继续渲染、目检 |
| 只咨询配色或风格 | Palette Decision；不要求完整拓扑，不生图 |
| 把 AI 图做成可编辑 PPT | 交给 fig-pptx。本 skill 不拆层、不组装 PPTX |
只问方案时不启动绘图。直接画图时不强加 prompt 确认；按用户的 review 偏好执行。直接画图不代替风格选择。
按需读取
Load only what the current stage needs:
- 构造、诊断或修订决策 →
references/prompt-design-logic.md - 编译 renderer prompt →
references/json-to-prompt.md - 可直接填充的构造/修订样板 →
references/prompt-templates.md - 密度、布局、文字或风格细节 →
references/image-prompt-guide.md - 案例与迁移检验 →
references/prompt-design-cases.md - 实际渲染的结构契约 →
json-schema.md和figure-spec.schema.json - 视觉锚点 →
references/architecture-icons.md，仅使用符合证据的元素 - 第一次出图前的风格菜单 →
references/style-catalog.md与references/previews/ - 色彩与可选风格库 →
references/palettes.md、references/styles/ - Codex native image execution →
references/codex-image-workflow.md - 图片验收 →
references/render-audit.md(required before accepting an image)
超出证据的内容标推断或待确认；用占位符代替编造的模块、损失、维度或结果；没有任何可用来源时停下，并列出最少需要补充的材料。
Route inputs by inspected content
A URL is not automatically a repository. Inspect it first.
| Input | Route | Execution Behavior |
|---|---|---|
| Direct User Architecture (Passthrough) | This skill's design flow | Skip fig-analyze. User gave explicit nodes/flow; compile FigureSpec v1 and render directly. |
| Draft Notes / Outline / Partial Draft | ../fig-analyze/SKILL.md |
Draft-to-Figure Fast-Track. For rough notes, outlines, or sections without full results: focus on Figure 1 framework. |
| Complete Manuscript (Markdown / LaTeX / PDF / URL) | ../fig-analyze/SKILL.md |
Full Planning. For complete papers with experiments/results: multi-figure strategy, claim verification, and constraints. |
| Repository path or repository URL | ../fig-analyze/SKILL.md |
Extract semantic architecture graph; omit engineering plumbing (data loaders, trainers). |
| Paper plus repository | ../fig-analyze/SKILL.md |
Paper/user defines narrative & topology; repository supplies parameter & dimension verification. |
| External style reference | ../fig-analyze/SKILL.md |
Extract transferable style from external references. |
| Existing render to edit | This skill's revise mode | Preserve its scientific content, topology and visible text, then apply only the requested delta. |
What ships with it
28 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.
- figure-spec.schema.json 8.5 KB
- json-schema.md 9.0 KB
- prompts/figure-worker.md 6.7 KB
- references/architecture-icons.md 11 KB
- references/codex-image-workflow.md 9.8 KB
- references/image-prompt-guide.md 6.4 KB
- references/json-to-prompt.md 7.2 KB
- references/palettes.md 21 KB
- references/previews/contrast_ablation_kan.jpg 572 KB
- references/previews/dual_fidelity_loop_labo.jpg 579 KB
- references/previews/illustrated_modular_agentic_matribo.jpg 776 KB
- references/previews/modern_technical_vector_deepseek_mla.jpg 612 KB
- references/previews/paired_semantic_zones_dash.jpg 561 KB
- references/previews/pastel_airy_ui_agentic_bo.jpg 194 KB
- references/prompt-design-cases.md 6.8 KB
- references/prompt-design-logic.md 9.0 KB
- references/prompt-templates.md 5.8 KB
- references/render-audit.md 11 KB
- references/style-catalog.md 1.5 KB
- references/styles/双保真度引导闭环风.md 7.2 KB
- references/styles/对比消融实验风.md 3.3 KB
- references/styles/有色语义分区图示风.md 5.2 KB
- references/styles/现代前沿技术框线风.md 3.4 KB
- references/styles/现代柔彩空气风.md 8.0 KB
- references/styles/编辑手绘模块风.md 11 KB
- scripts/clean_image_metadata.py 4.3 KB runs code
- scripts/validate_figure_spec.py 24 KB runs code
- scripts/validate_render_audit.py 11 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.
- 5d ago First seen · 297 lines · 85 tokens per session scan A 33866f529d55
fig-draw is a skill published in the GitHub repository Azhi-ss/academic-figure-skills (158 stars, last pushed 5d ago), licensed MIT. It adds 85 tokens to every session and 5,009 once invoked, about $0.0003 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 2026-10-12.
Other skills, from other repositories
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.…
paper-read
Summarize and critically analyze academic papers supplied as PDFs, text, arXiv links, or journal URLs. Ground claims in the inspected version and source locations; support focused questions, deeper appraisal, and cross-paper comparison.
ml-paper-writing
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification…
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews, finding related work, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, citation verification workflows, and paper…