ml-science-discipline
ml-science-discipline is a Model training & evaluation skill for AI agents, published by CRAG666 in the dotfiles repository on GitHub. Skillspace rates ml-science-discipline C (74/100) and it passed the safety scan; the rating is based on static analysis only.
Enforces rigorous scientific methodology for machine learning experiments intended to support publication-grade claims (Q1 journals, conference papers, regulated decisions). Use this skill when designing an ML pipeline, splitting datasets, evaluating performance, selecting features, tuning hyperparameters, comparing models, quantifying uncertainty, validating externally, or preparing results for a paper. Consult it for any task where experimental validity, reproducibility, or publication standards (TRIPOD+AI, CLAIM, STARD-AI, CONSORT-AI) are in scope. Routine "train a model" or "compute accuracy" requests do NOT automatically trigger this skill unless results will be reported, compared, or acted on.
- Grade
- C
- Quality
- 74 / 100
- Safety
- Passed
- GitHub stars
- 45
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.