autoresearch
Runs a hill-climbing study over many training or analysis runs with the study and experiments tools, one metric and direction, a baseline, ideas ranked by expected value, exactly one run per idea, kill criteria and a budget, verdicts with analysis and lessons, and a conclusion. Use for autoresearch, hyperparameter or ablation sweeps left to run, "make this metric better", or any loop of experiments the user wants driven for hours. For a single reproduction use reproduce; for designing the study's hypotheses first use hypotheses.
Quality
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' must be a string, got object | Fail |
metadata_version | 'metadata.version' is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Failed | |
- Repository
synthetic-sciences/openscience
- Revision
a08e0ad
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.