Optimize AI Hypotheses with Preregister Skill

Optimize AI Hypotheses with Preregister Skill

The Preregister Skill enables AI developers and research teams to lock confirmatory falsification targets and manage hypothesis testing with controlled error rates. Designed for usage within AI coding environments like Claude Code, Cursor, and Codex, this skill ensures rigorous handling of hypotheses in the development of AI models, particularly when transitioning from exploratory findings to confirmatory claims.

What this skill does

• Locks a confirmatory falsification target and its fixed multiple-comparison family before observing the result.
• Supports the "decide before observing" approach for confirmatory claims.
• Records details such as metric, threshold, family id/size, correction method, and seed budget.
• Applies Bonferroni correction to manage error rates related to multiple hypotheses testing.
• Facilitates the transition of exploratory findings to confirmatory claims through preregistration.

Who it is for

This skill is tailored for AI developers, data scientists, and research teams focused on hypothesis testing and model validation within AI applications. It is particularly beneficial for those using AI coding agents such as Claude Code, Cursor, and Codex.

Use cases

• Before promoting exploratory findings to core claims in academic or industry publications.
• Immediately following hypothesis selection in processes like `bt-tournament` to ensure rigorous confirmatory testing.
• Whenever precise hypothesis registration is required, aiding in structured experimentation protocols.

Technical details

• Compatibility: Supports integration with Claude Code, Cursor, and Codex.
• Preregister Command: Users trigger the function using the command `/preregister`.
• Required Inputs: Includes hypothesis_id, metric_name, direction, threshold, seed_count, alpha, mc_correction, family_id, family_size.
• Correction Methods: Uses Bonferroni as default with options for `none` or legacy `bh`.

Source & Licence

This package is built on open-source work published by whenpoem (whenpoem/aiscientist) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.