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 Lzy599775/agent-auto-sci-skills --skill agent-auto-sci-ai-mlgit clone --depth 1 https://github.com/Lzy599775/agent-auto-sci-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/lzy599775/agent-auto-sci-skills/agent-auto-sci-ai-ml)<a href="https://agentmods.dev/skills/lzy599775/agent-auto-sci-skills/agent-auto-sci-ai-ml"><img src="https://agentmods.dev/badge/skills/lzy599775/agent-auto-sci-skills/agent-auto-sci-ai-ml/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/lzy599775/agent-auto-sci-skills/agent-auto-sci-ai-ml"><img src="https://agentmods.dev/badge/skills/lzy599775/agent-auto-sci-skills/agent-auto-sci-ai-ml.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 | $0.00113 | $0.00535 |
| Opus 5.5 | $0.00045 | $0.00214 |
| Sonnet 5.5 | $0.00023 | $0.00107 |
| Haiku 4.5 | $0.00011 | $0.00053 |
Grade A, and why
agent-auto-sci-ai-ml 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 1mo 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.
What it actually says
Agent Auto Sci AI ML
Use this subskill when the project needs modeling rather than only descriptive analysis.
Fast Workflow
- Define prediction or explanation target.
- Build a data dictionary and leakage checklist.
- Establish simple baselines before complex models.
- Choose model family: classical ML, deep learning, time series, spatial ML, or NLP/transformer.
- Split data correctly: spatial, temporal, group, or external validation as needed.
- Evaluate with task-appropriate metrics and uncertainty.
- Interpret with SHAP, permutation importance, partial dependence, or ablation.
- Translate model results into manuscript claims only after robustness checks.
Read references/ml_ai_workflows.md.
For full paper projects, this skill owns baseline design, model/method selection, leakage checks, train/test split logic, hyperparameter search, ablation, robustness, error-case analysis, XAI, and methods/results reporting boundaries. It must work with agent-auto-sci-methodology before turning feature importance into mechanism language.
For deeper K-Dense-style encapsulation:
references/k_dense_ml_ai_mapping.md: how scikit-learn, PyTorch Lightning, transformers, SHAP, time-series, and XAI skills are adapted.references/sport_geography_ml_playbook.md: sport geography modeling patterns, leakage checks, baselines, and manuscript reporting.
Related Helper Skills
Use installed helper skills when useful:
scikit-learnpytorch-lightningtransformersshapaeontimesfm-forecastingstatistical-analysisagent-auto-sci-data-vizagent-auto-sci-geospatial
Must Not Do
- Do not use ML if the research question only needs transparent spatial/statistical analysis.
- Do not report accuracy without baselines and uncertainty.
- Do not mix train/test spatial units when spatial leakage is possible.
- Do not use SHAP as causal evidence.
What ships with it
4 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.
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.
- 1mo ago First seen · 51 lines · 113 tokens per session scan A d7e19f03ae99
agent-auto-sci-ai-ml is a skill published in the GitHub repository Lzy599775/agent-auto-sci-skills (2 stars, last pushed 9d ago), licensed MIT. It adds 113 tokens to every session and 535 once invoked, about $0.0005 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
code-execution
Execute scientific Python code for computation, data analysis, simulation, and verification. Use when: (1) running statistical analyses, (2) numerical computation, (3) data processing pipelines, (4) verifying calculations, (5) running simulations. NOT for: literature search (use literature-search), writing papers (use…
model-assessment
Use when validating or evaluating a trained medical-imaging model. Audits split leakage and validation design, computes task-correct held-out metrics (Dice + HD95, AUROC + AUPRC, FROC, calibration), and covers uncertainty/OOD and Grad-CAM explainability, each with a gate.
model-scaffold
Use when you need a runnable PyTorch training repo for a medical-imaging task (segmentation, classification, detection, synthesis, self-supervised, or fine-tuning a pretrained backbone). Emits a patient-level seed-locked split, train/evaluate scripts, config and a Methods stub.
radiomics-ml
Use when building or auditing a radiomics or tabular clinical-ML prediction model with a classical learner (LASSO, SVM, random forest, XGBoost and similar). Enforces nested CV, dimensionality control, in-fold feature selection, feature stability, calibration and external validation.
imaging-data
Use when preparing a medical-imaging dataset (DICOM/NIfTI) for modelling. Profiles spacing, orientation, intensity, label integrity, foreground fraction and target volume, gates them against the plan, then plans and audits preprocessing and augmentation for leakage.
model-selection
Use when choosing the model for a medical-imaging study. Picks a paper-grounded architecture family (CNN/ViT, U-Net/nnU-Net, detection, SAM/foundation, GNN), then vets the concrete repo or checkpoint for licence, version pin, weight provenance and benchmark overlap.