Explorar skills
2.582 skills encontradas
list-experiment
Design and diagnose list experiments (item count technique).
paper-review-lite
Pre-submission audit: argument, numerics, refs, writing, figures, replication.
narrative-building
Draft scientific introductions: argument logic, framing, multi-experiment coherence.
methods-reporting
Check methods reporting against CONSORT, JARS, DA-RT standards.
vlm-ocr-pipeline
VLM-based OCR pipeline: model selection, prompts, architecture, evaluation.
hypothesis-building
Build falsifiable causal hypotheses: DAGs, FPCI, equivalence testing.
conjoint-diagnostics
Diagnose conjoint design integrity, estimation choices, and validity.
figure-table-audit
Audit figures, tables, captions, cross-references, and statistical notes.
conjoint-design
Design conjoint experiments: attributes, power, AMCE/AMIE estimation.
fair-check
Audit manuscript and replication package against FAIR open-science principles.
AI/ML Attack Surface
This skill should be used when the user asks about "AI security", "ML pipeline attacks", "prompt injection", "model deserialization", "unsafe model loading", "Jupyter injection", "LLM security", or needs to identify AI/ML-specific vulnerabilities in codebases that use machine learning frameworks.
figures
Design and format publication-quality figures: chart choice, color, scales, legends, captions, reproducibility.