Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hdu-ailab/EasyResearchnpx agentmods add skills/hdu-ailab/easyresearch/drawio-academic-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/hdu-ailab/easyresearch/drawio-academic-skills)<a href="https://agentmods.dev/skills/hdu-ailab/easyresearch/drawio-academic-skills"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/drawio-academic-skills/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/hdu-ailab/easyresearch/drawio-academic-skills"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/drawio-academic-skills.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 | $0.00093 | $0.02843 |
| Opus 5 | $0.00046 | $0.01422 |
| Sonnet 5 | $0.00019 | $0.00569 |
| Haiku 4.5 | $0.00009 | $0.00284 |
Grade A, and why
drawio-academic-skills 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 12d 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.
This is a copy
89% identical to drawio-academic-skills — 29 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draw.io Academic Overlay
Create, edit, replicate, validate, and export publication-ready draw.io figures by applying academic policy on top of the sibling Draw.io Base Skill. This overlay is intentionally thin: it owns academic policy/gates, academic docs, and paper examples; the sibling base at ../drawio owns all shared execution (CLI, schema, renderer, themes including academic/academic-color, references, examples, style presets, Desktop export).
Required Sibling Base
Resolve shared resources relative to this overlay directory:
- CLI
../drawio/scripts/cli.js; URL fallback../drawio/scripts/runtime/diagrams-net-url.js - Schema
../drawio/assets/schemas/spec.schema.json; themes../drawio/assets/themes/; palettes../drawio/assets/palettes/ - References
../drawio/references/docs/,../drawio/references/official/,../drawio/references/workflows/,../drawio/references/examples/; shared rework contract../drawio/references/workflows/visual-review.md - Built-in style presets
../drawio/styles/built-in/
Overlay-local assets: references/docs/publication-overlay.md, academic-figure-playbook.md, academic-export-checklist.md, references/examples/, references/templates/.
If ../drawio/scripts/cli.js is missing, stop and report that the sibling base skill must be installed next to this overlay; never silently recreate or vendor-copy base resources into the overlay.
Non-Negotiable Contract
- Keep academic authoring YAML-first and offline-first. Never create, require, or route through
.mcp.json, MCP, or a live backend. - Treat
.drawioand a 300dpi.png(via draw.io Desktop) as the default academic final deliverables; SVG is the offline fallback without Desktop — report the fallback and never claim files that were not produced. - Keep
.spec.yaml,.arch.json, raw YAML, and diagnostics in a project-local work directory such as.drawio-tmp/<name>/, unless the user explicitly asks for a reproducible sidecar bundle beside the final output. - Perform paper-readability and visual self-checks on the exported PNG (or the fallback SVG) first. Do not substitute browser or Playwright screenshots when an exported artifact exists.
- Use the sibling base
../drawio/references/workflows/visual-review.mdfor preview structure, issue records, YAML-first rework, and stopping rules; this overlay adds only publication checks. - Treat external image-generation previews as optional concept previews only. They never replace YAML, artifacts, sidecars, or exported-artifact verification.
- Do not create or modify scratch JS scripts under a user's project-local
.agents/skills/drawio; port durable fixes to the sibling base skill source instead.
What ships with it
24 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.
- .gitignore 204 B
- agents/interface.yaml 1.3 KB
- agents/openai.yaml 1.2 KB
- CHANGELOG.md 3.4 KB
- evals/baseline-prompts.json 2.8 KB
- evals/darwin-results.tsv 547 B
- evals/evals.json 15 KB
- evals/README.md 897 B
- evals/test-prompts.json 720 B
- README_CN.md 3.5 KB
- README.md 3.6 KB
- references/docs/academic-export-checklist.md 3.1 KB
- references/docs/academic-figure-playbook.md 14 KB
- references/docs/publication-overlay.md 13 KB
- references/examples/ablation-study-pipeline.yaml 789 B
- references/examples/ieee-network-paper.yaml 898 B
- references/examples/industrial-architecture-cn-paper.yaml 2.6 KB
- references/examples/max-pooling-operation-paper.yaml 2.2 KB
- references/examples/research-pipeline.yaml 994 B
- references/examples/system-architecture-paper.yaml 831 B
- references/examples/technical-roadmap-paper.yaml 1006 B
- references/examples/yolo-model-architecture-paper.yaml 2.5 KB
- references/templates/multi-module-system-compact.yaml 5.5 KB
- references/templates/neural-network-architecture-compact.yaml 7.1 KB
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.
- 12d ago First seen · 172 lines · 93 tokens per session scan A 8e2c77f577d3
drawio-academic-skills is a skill published in the GitHub repository hdu-ailab/EasyResearch (13 stars, last pushed 2d ago), licensed MIT. It adds 93 tokens to every session and 2,843 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to drawio-academic-skills, differing in 29 lines, and is treated as a copy.
Other skills, from other repositories
paper-visual-craft
Use when designing, redrawing, or validating research-paper figures and tables, including Matplotlib plots, LaTeX tables, benchmarks, captions, legends, annotations, color, and typography. Preserves exact evidence and checks rendered PDFs for clipping, overlap, and readability.
paper-framework-figure-studio-pro
Use when planning a source-grounded method overview, architecture, pipeline, system/data-flow, mechanism, or agent-workflow figure for a CS or deep-learning paper. Produces an editable figure brief before image generation or manual redrawing; not for plots, tables, or general prose.
academic-poster
A guide for turning a research paper or abstract into a printable academic conference poster. It covers large single-page layouts, including traditional columns and a design that enlarges the main finding.
scientific-schematics
Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.6 Flash for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and…
paper-poster-html
A workflow for building an academic conference poster as one HTML/CSS file and printing it to a PDF at an exact page size. It uses the paper’s real figures and checks layout details before review.
ccf-visual-composer
A visual design assistant for research papers, presentations, posters, and README graphics. It can lay out figures, tables, diagrams, icons, colors, and other visual elements, including editable SVG, PDF, and PPTX outputs.