How do I install the Reproducibility Third Party Verification skill?

Run npx skillmds@latest add yogsoth-ai/reproducibility-third-party-verification in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Reproducibility Third Party Verification safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Reproducibility Third Party Verification?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Reproducibility Third Party Verification free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Reproducibility Third Party Verification?

yogsoth-ai (@yogsoth-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Reproducibility Third Party Verification by yogsoth-ai

Name: Reproducibility Third Party Verification
Author: yogsoth-ai

Reproducibility Third Party Verification

(Proposal, unverified) Attempt to verify a paper's reported results by actually executing its released code/scripts against its own reported configuration — the only SOP in this package whose action type is code execution rather than text reading/judgment. Use this after unit-classification has extracted the paper's reported configuration/hyperparameters as classified units; "not_attempted" is a correct, common output when the paper's own reporting is too incomplete to run, not a failure of this SOP.

yogsoth-ai Updated Sep 17, 2026

File contents

Reproducibility Third-Party Verification (Proposal)

Actually runs code to check reported results against the paper's own extracted configuration — unique action type (execution) in this package. Fills the evidence-verification × engineering-metadata gap in the evaluative-stance × content-layer matrix.

Execution

Subagent — spawned via spawn-agent skill.

Dependency: unit-classification, not raw full_text (graph correction L20)

This SOP needs the paper's reported configuration already pulled out in structured form before attempting to verify it — hence its input is classified_units, not full_text directly. An earlier graph draft had this SOP depending on nothing upstream, which meant it had no defined way to get the structured claims it needs to check.

Proposal Status — Read Before Modifying

No primary-source precedent, no inter-rater-reliability baseline. Keep "(Proposal, unverified)" in the description until real usage validates the method. Given the code-execution action type, treat any scope expansion here with more caution than the other 3 proposal SOPs.

Available SOPs

SOP	When to use
spawn-agent	Spawn a customized CC subagent with full MCP tool access.

Frequently asked questions