Review program.md for hypothesis clarity, measurement validity, and control adequacy.
npx skills add https://github.com/Borda/AI-Rig --skill judge-borda
Please help me install this Agent Skill. Skill: judge Source: https://github.com/Borda/AI-Rig/tree/main/plugins/research/skills/judge Command: npx skills add https://github.com/Borda/AI-Rig --skill judge-borda
This skill provides a structured, automated review workflow to validate experimental methodology, enabling teams to detect design weaknesses before conducting expensive runs.
Run the judge skill against your project by invoking /research:judge path/to/program.md from the project root.
High-intent search queries and answers about installing and using this skill.
Review experimental design by evaluating program.md against seven methodology dimensions, producing a formal verdict and completeness audit. This agent-assisted workflow assesses hypothesis clarity, measurement validity, and control adequacy before run execution.
A structured research review of program.md is an agent-assisted evaluation that identifies methodological flaws by assessing hypothesis clarity, measurement validity, and control adequacy. It outputs a formal verdict, completeness audit, and methodology report covering goals, metrics, and reproducibility.
Yes, automated methodology review supports ML research campaigns, A/B experiments, and codebase experiments requiring rigorous planning. It evaluates program.md to ensure accurate experimental design across goals, metrics, guards, scope, and reproducibility before run execution.
Run a formal methodology report by invoking the judge workflow against your campaign program. The workflow executes steps J1–J6, performing parallel reviews of program.md to generate a verdict, completeness audit, and reproducibility artifacts for your research campaign.
Yes, you need a campaign program.md file to assess hypothesis clarity and measurement validity. The structured review workflow requires access to this program file to evaluate experimental design dimensions and generate the formal methodology report.
labs21-devDraft PRD-style feature specifications with goals, metrics, and open questions.
BordaScan Python/ML codebases to generate program.md run specs with metric and guard configurations.
sean-sunagakuReview software project plans with Codex, Gemini, and Claude in parallel.
XWIlluDeluEvaluate scientific claims by critiquing methodology, bias, and statistical validity.
