AutoResearchClaw is a system that turns a research idea into a scientific paper through autonomous and collaborative AI research workflows. It is for researchers who want agents to investigate questions, run experiments, and produce papers, with optional human guidance. Catalogue skills and agents provide parts of its research workflow.
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/aiming-lab/autoresearchclaw/scientific-visualizationnpx skills add aiming-lab/AutoResearchClaw --skill scientific-visualizationgit clone --depth 1 https://github.com/aiming-lab/AutoResearchClawWrote 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/aiming-lab/autoresearchclaw/scientific-visualization)<a href="https://agentmods.dev/skills/aiming-lab/autoresearchclaw/scientific-visualization"><img src="https://agentmods.dev/badge/skills/aiming-lab/autoresearchclaw/scientific-visualization.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 5.1 | $0.00033 | $0.00692 |
| Opus 5 | $0.00016 | $0.00346 |
| Sonnet 5 | $0.00007 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
scientific-visualization 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 6d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific Visualization Best Practice
Figure Design Principles
- Every figure must have a clear, self-contained message
- Minimize chartjunk: remove gridlines, background shading, and 3D effects
- Use direct labeling instead of legends when possible
- Remove top and right spines for cleaner appearance
- Ensure all text is readable at final print size (minimum 6pt font)
Journal Figure Sizing
- Single column: 3.3-3.5 inches (85-89 mm) wide
- 1.5 column: 4.5-5.5 inches (114-140 mm) wide
- Double column / full width: 6.5-7.1 inches (165-180 mm) wide
- Resolution: 300 DPI minimum for raster; prefer vector formats (PDF, EPS, SVG)
- Check target journal author guidelines for exact specifications
Colorblind-Safe Design
- Use colorblind-friendly palettes: seaborn "colorblind", Okabe-Ito, viridis, cividis
- NEVER rely on color alone — combine with shape, pattern, or line style
- Avoid red-green combinations; prefer blue-orange or blue-yellow contrasts
- Test figures with a colorblind simulator before submission
- Ensure figures work in grayscale for print journals
Multi-Panel Layouts
- Label panels with uppercase letters: (A), (B), (C) in bold, top-left corner
- Use consistent axis scales across panels when comparing related data
- Share axes where appropriate to reduce redundancy
- Maintain consistent font sizes and line widths across all panels
- Use
plt.subplots()withconstrained_layout=Truefor automatic spacing
Statistical Annotations on Figures
- Show individual data points alongside summary statistics (box + strip plots)
- Always include error bars; specify type in caption (SEM, SD, 95% CI)
- Use significance brackets with stars: * p<.05, ** p<.01, *** p<.001
- Annotate effect sizes or key statistics directly on the figure when helpful
- Never use bar charts for small-n data — use dot plots or box plots instead
Export and Quality Checklist
- Save in vector format (PDF/SVG) for line art; TIFF/PNG for photographs
- Embed fonts or convert text to outlines for cross-platform consistency
- Verify axis labels include units in parentheses: "Time (s)", "Force (N)"
- Ensure figure caption fully explains all symbols, abbreviations, and panels
- Check that color-coded elements match between figure and caption
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.
- 6d ago First seen · 57 lines · 33 tokens per session scan A 07ae48cf917a
scientific-visualization is a skill published in the GitHub repository aiming-lab/AutoResearchClaw (14,335 stars, last pushed 17d ago), licensed MIT. It adds 33 tokens to every session and 692 once invoked, about $0.0002 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
aclawdemy
The academic research platform for AI agents. Submit papers, review research, build consensus, and push toward AGI — together.
adme-property-predictor
Predict ADME (Absorption, Distribution, Metabolism, Excretion) properties for drug candidates using cheminformatics models and molecular descriptors. Evaluates drug-likeness, bioavailability, and pharmacokinetic profile to guide lead optimization and candidate selection in drug discovery.
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
baseline-comparison-audit
Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent…
eval-design-forensics
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan…
proof-derivation-forensics
Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation …