run-autotrain
run-autotrain is a Model training & evaluation skill for AI agents, published by oscmcompany in the fund repository on GitHub. Skillspace rates run-autotrain D (64/100) and it passed the safety scan; the rating is based on static analysis only.
Autonomous model training optimization loop using autoresearch methodology. Invoked as `/autotrain <model-name>` (e.g., `/autotrain tide`). Iteratively modifies model architecture code, runs training via parallel local execution, evaluates a target metric, and keeps or reverts changes to find the best model. Uses parallel Agent workers for hyperparameter search and sequential iterations for architecture changes. Use when the user wants to optimize a model, run autoresearch, find the best architecture, or improve training metrics. Includes epoch escalation (Mode C) for pushing past plateaus. Optionally accepts `--metric <name>` to specify the optimization target.
- Grade
- D
- Quality
- 64 / 100
- Safety
- Passed
- GitHub stars
- 24
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
- 82 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- MIT
- 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.